<script src="https://bibbase.org/show?bib=https%3A%2F%2Fsites.northwestern.edu%2Fivpl%2Ffiles%2F2023%2F06%2FIVPL_Updated_publications-1.bib&jsonp=1"></script>
<?php
$contents = file_get_contents("https://bibbase.org/show?bib=https%3A%2F%2Fsites.northwestern.edu%2Fivpl%2Ffiles%2F2023%2F06%2FIVPL_Updated_publications-1.bib");
print_r($contents);
?>
<iframe src="https://bibbase.org/show?bib=https%3A%2F%2Fsites.northwestern.edu%2Fivpl%2Ffiles%2F2023%2F06%2FIVPL_Updated_publications-1.bib"></iframe>
For more details see the documention.
To the site owner:
Action required! Mendeley is changing its API. In order to keep using Mendeley with BibBase past April 14th, you need to:
@article{banerjee2023learning, abstract = {Room-temperature semiconductor radiation detectors (RTSD) have broad applications in medical imaging, homeland security, astrophysics and others. RTSDs such as CdZnTe, CdTe are often pixelated, and characterization of these detectors at micron level can benefit 3-D event reconstruction at sub-pixel level. Material defects alongwith electron and hole charge transport properties need to be characterized which requires several experimental setups and is labor intensive. The current state-of-art approaches characterize each detector pixel, considering the detector in bulk. In this article, we propose a new microscopic learning-based physical models of RTSD based on limited data compared to what is dictated by the physical equations. Our learning models uses a physical charge transport considering trapping centers. Our models learn these material properties in an indirect manner from the measurable signals at the electrodes and/or free and/or trapped charges distributed in the RTSD for electron–hole charge pair injections in the material. Based on the amount of data used during training our physical model, our algorithm characterizes the detector for charge drifts, trapping, detrapping and recombination coefficients considering multiple trapping centers or as a single equivalent trapping center. The RTSD is segmented into voxels spatially, and in each voxel, the material properties are modeled as learnable parameters. Depending on the amount of data, our models can characterize the RTSD either completely or in an equivalent manner.}, author = {Banerjee, Srutarshi and Rodrigues, Miesher and Ballester, Manuel and Vija, Alexander Hans and Katsaggelos, Aggelos K.}, doi = {10.1038/s41598-022-27125-7}, issn = {20452322}, journal = {Scientific Reports}, number = {1}, pages = {168}, pmid = {36599876}, publisher = {Nature Publishing Group UK London}, title = {{Learning-based physical models of room-temperature semiconductor detectors with reduced data}}, volume = {13}, year = {2023} }
@article{ruiz2023probabilistic, author = {Ruiz, Pablo and Morales-{\'{A}}lvarez, Pablo and Coughlin, Scott and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1016/j.knosys.2022.110183}, issn = {09507051}, journal = {Knowledge-Based Systems}, pages = {110183}, publisher = {Elsevier}, title = {{Probabilistic fusion of crowds and experts for the search of gravitational waves}}, volume = {261}, year = {2023} }
@article{lopez2023deep, author = {Lopez-Perez, Miguel and Morales-Alvarez, Pablo and Cooper, Lee A. D. and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1109/access.2023.3237990}, issn = {21693536}, journal = {IEEE Access}, pages = {6922--6934}, publisher = {IEEE}, title = {{Deep Gaussian Processes for Classification With Multiple Noisy Annotators. Application to Breast Cancer Tissue Classification}}, volume = {11}, year = {2023} }
@article{Yunan2023, author = {Wu, Yunan and Dravid, Amil and Wehbe, Ramsey Michael and Katsaggelos, Aggelos K}, doi = {https://doi.org/10.48550/arXiv.2301.08798}, journal = {arXiv preprint arXiv:2301.08798}, title = {{DeepCOVID-Fuse: A Multi-modality Deep Learning Model Fusing Chest X-Radiographs and Clinical Variables to Predict COVID-19 Risk Levels}}, year = {2023} }
@article{Fragos2023, abstract = {Most massive stars are members of a binary or a higher-order stellar system, where the presence of a binary companion can decisively alter their evolution via binary interactions. Interacting binaries are also important astrophysical laboratories for the study of compact objects. Binary population synthesis studies have been used extensively over the last two decades to interpret observations of compact-object binaries and to decipher the physical processes that lead to their formation. Here, we present POSYDON , a novel, publicly available, binary population synthesis code that incorporates full stellar structure and binary-evolution modeling, using the MESA code, throughout the whole evolution of the binaries. The use of POSYDON enables the self-consistent treatment of physical processes in stellar and binary evolution, including: realistic mass-transfer calculations and assessment of stability, internal angular-momentum transport and tides, stellar core sizes, mass-transfer rates, and orbital periods. This paper describes the detailed methodology and implementation of POSYDON , including the assumed physics of stellar and binary evolution, the extensive grids of detailed single- and binary-star models, the postprocessing, classification, and interpolation methods we developed for use with the grids, and the treatment of evolutionary phases that are not based on precalculated grids. The first version of POSYDON targets binaries with massive primary stars (potential progenitors of neutron stars or black holes) at solar metallicity.}, archivePrefix = {arXiv}, arxivId = {2202.05892}, author = {Fragos, Tassos and {J. Andrews}, Jeff and Bavera, Simone S. and Berry, Christopher P. L. and Coughlin, Scott and Dotter, Aaron and Giri, Prabin and Kalogera, Vicky and Katsaggelos, Aggelos and Kovlakas, Konstantinos and Lalvani, Shamal and Misra, Devina and Srivastava, Philipp M. and Qin, Ying and Rocha, Kyle A. and Rom{\'{a}}n-Garza, Jaime and Serra, Juan Gabriel and Stahle, Petter and Sun, Meng and Teng, Xu and Trajcevski, Goce and Tran, Nam Hai and Xing, Zepei and Zapartas, Emmanouil and Zevin, Michael}, chapter = {45}, doi = {10.3847/1538-4365/ac90c1}, eprint = {2202.05892}, isbn = {0067-0049 1538-4365}, issn = {0067-0049}, journal = {The Astrophysical Journal Supplement Series}, month = {feb}, number = {2}, pages = {45}, title = {{POSYDON: A General-purpose Population Synthesis Code with Detailed Binary-evolution Simulations}}, url = {http://arxiv.org/abs/2202.05892 https://iopscience.iop.org/article/10.3847/1538-4365/ac90c1}, volume = {264}, year = {2023} }
@article{Jane2022, abstract = {Understanding the noise in gravitational-wave detectors is central to detecting and interpreting gravitational-wave signals. Glitches are transient, non-Gaussian noise features that can have a range of environmental and instrumental origins. The Gravity Spy project uses a machine-learning algorithm to classify glitches based upon their time–frequency morphology. The resulting set of classified glitches can be used as input to detector-characterisation investigations of how to mitigate glitches, or data-analysis studies of how to ameliorate the impact of glitches. Here we present the results of the Gravity Spy analysis of data up to the end of the third observing run of advanced laser interferometric gravitational-wave observatory (LIGO). We classify 233981 glitches from LIGO Hanford and 379805 glitches from LIGO Livingston into morphological classes. We find that the distribution of glitches differs between the two LIGO sites. This highlights the potential need for studies of data quality to be individually tailored to each gravitational-wave observatory.}, archivePrefix = {arXiv}, arxivId = {2208.12849}, author = {Glanzer, Jane and Banagiri, S and Coughlin, S B and Soni, Siddharth and Zevin, Michael and Berry, Christopher Philip Luke and Patane, Oli and Bahaadini, Sara and Rohani, Neda and Crowston, Kevin and Kalogera, V and {\O}sterlund, Carsten and Trouille, Laura and Katsaggelos, A}, doi = {10.1088/1361-6382/acb633}, eprint = {2208.12849}, issn = {0264-9381}, journal = {Classical and Quantum Gravity}, month = {mar}, number = {6}, pages = {065004}, title = {{Data quality up to the third observing run of advanced LIGO: Gravity Spy glitch classifications}}, url = {https://iopscience.iop.org/article/10.1088/1361-6382/acb633}, volume = {40}, year = {2023} }
@article{Zixiao2023, author = {Yu, Zixiao and Wang, Haohong and Katsaggelos, Aggelos K and Ren, Jian}, journal = {IEEE Internet of Things Journal}, title = {{A Novel Automatic Content Generation And Optimization Framework}}, year = {2023} }
@article{Henry2022, abstract = {Macro x-ray fluorescence (XRF) imaging of cultural heritage objects, while a popular non-invasive technique for providing elemental distribution maps, is a slow acquisition process in acquiring high signal-to-noise ratio XRF volumes. Typically on the order of tenths of a second per pixel, a raster scanning probe counts the number of photons at different energies emitted by the object under x-ray illumination. In an effort to reduce the scan times without sacrificing elemental map and XRF volume quality, we propose using dictionary learning with a Poisson noise model as well as a color image-based prior to restore noisy, rapidly acquired XRF data.}, archivePrefix = {arXiv}, arxivId = {2206.01740}, author = {Chopp, Henry and McGeachy, Alicia and Alfeld, Matthias and Cossairt, Oliver and Walton, Marc and Katsaggelos, Aggelos}, eprint = {2206.01740}, journal = {arXiv preprint arXiv:2206.01740}, month = {jun}, title = {{Denoising Fast X-Ray Fluorescence Raster Scans of Paintings}}, url = {http://arxiv.org/abs/2206.01740}, year = {2022} }
@article{Sara2022, abstract = {In this paper, leveraging the capabilities of neural networks for modeling the non-linearities that exist in the data, we propose several models that can project data into a low dimensional, discriminative, and smooth manifold. The proposed models can transfer knowledge from the domain of known classes to a new domain where the classes are unknown. A clustering algorithm is further applied in the new domain to find potentially new classes from the pool of unlabeled data. The research problem and data for this paper originated from the Gravity Spy project which is a side project of Advanced Laser Interferometer Gravitational-wave Observatory (LIGO). The LIGO project aims at detecting cosmic gravitational waves using huge detectors. However non-cosmic, non-Gaussian disturbances known as "glitches", show up in gravitational-wave data of LIGO. This is undesirable as it creates problems for the gravitational wave detection process. Gravity Spy aids in glitch identification with the purpose of understanding their origin. Since new types of glitches appear over time, one of the objective of Gravity Spy is to create new glitch classes. Towards this task, we offer a methodology in this paper to accomplish this.}, archivePrefix = {arXiv}, arxivId = {2205.13672}, author = {Bahaadini, Sara and Wu, Yunan and Coughlin, Scott and Zevin, Michael and Katsaggelos, Aggelos K.}, eprint = {2205.13672}, journal = {arXiv e-prints}, month = {may}, title = {{Discriminative Dimensionality Reduction using Deep Neural Networks for Clustering of LIGO Data}}, url = {http://arxiv.org/abs/2205.13672}, year = {2022} }
@article{Semih2022, abstract = {Ptychography is a well-established coherent diffraction imaging technique that enables non-invasive imaging of samples at a nanometer scale. It has been extensively used in various areas such as the defense industry or materials science. One major limitation of ptychography is the long data acquisition time due to mechanical scanning of the sample; therefore, approaches to reduce the scan points are highly desired. However, reconstructions with less number of scan points lead to imaging artifacts and significant distortions, hindering a quantitative evaluation of the results. To address this bottleneck, we propose a generative model combining deep image priors with deep generative priors. The self-training approach optimizes the deep generative neural network to create a solution for a given dataset. We complement our approach with a prior acquired from a previously trained discriminator network to avoid a possible divergence from the desired output caused by the noise in the measurements. We also suggest using the total variation as a complementary before combat artifacts due to measurement noise. We analyze our approach with numerical experiments through different probe overlap percentages and varying noise levels. We also demonstrate improved reconstruction accuracy compared to the state-of-the-art method and discuss the advantages and disadvantages of our approach.}, archivePrefix = {arXiv}, arxivId = {2205.02397}, author = {Barutcu, Semih and G{\"{u}}rsoy, Doğa and Katsaggelos, Aggelos K.}, eprint = {2205.02397}, journal = {arXiv preprint arXiv:2205.02397}, month = {may}, title = {{Compressive Ptychography using Deep Image and Generative Priors}}, url = {http://arxiv.org/abs/2205.02397}, year = {2022} }
@article{banerjee2022joint, abstract = {We present a novel adaptive multimodal intensity-event algorithm to optimize an overall objective of object tracking under bit rate constraints for a host-chip architecture. The chip is a computationally resource-constrained device acquiring high-resolution intensity frames and events, while the host is capable of performing computationally expensive tasks. We develop a joint intensity-neuromorphic event rate-distortion compression framework with a quadtree (QT)-based compression of intensity and events scheme. The goal of this compression framework is to optimally allocate bits to the intensity frames and neuromorphic events based on the minimum distortion at a given communication channel capacity. The data acquisition on the chip is driven by the presence of objects of interest in the scene as detected by an object detector. The most informative intensity and event data are communicated to the host under rate constraints so that the best possible tracking performance is obtained. The detection and tracking of objects in the scene are done on the distorted data at the host. Intensity and events are jointly used in a fusion framework to enhance the quality of the distorted images, in order to improve the object detection and tracking performance. The performance assessment of the overall system is done in terms of the multiple object tracking accuracy (MOTA) score. Compared with using intensity modality only, there is an improvement in MOTA using both these modalities in different scenarios.}, author = {Banerjee, Srutarshi and Chopp, Henry H. and Zhang, Jianping and Wang, Zihao W. and Kang, Peng and Cossairt, Oliver and Katsaggelos, Aggelos}, doi = {10.1109/TNNLS.2022.3214779}, issn = {21622388}, journal = {IEEE Transactions on Neural Networks and Learning Systems}, keywords = {Compressed domain object detection and tracking,Computer architecture,Image reconstruction,Neuromorphics,Object detection,Optimization,Rate-distortion,Task analysis,dynamic programming (DP),joint intensity-event imaging system,joint intensity-event rate-distortion optimization,quadtree (QT) segmentation}, publisher = {IEEE}, title = {{A Joint Intensity-Neuromorphic Event Imaging System With Bandwidth-Limited Communication Channel}}, year = {2022} }
@article{Semih2022a, abstract = {Ptychography is a well-studied phase imaging method that makes non-invasive imaging possible at a nanometer scale. It has developed into a mainstream technique with various applications across a range of areas such as material science or the defense industry. One major drawback of ptychography is the long data acquisition time due to the high overlap requirement between adjacent illumination areas to achieve a reasonable reconstruction. Traditional approaches with reduced overlap between scanning areas result in reconstructions with artifacts. In this paper, we propose complementing sparsely acquired or undersampled data with data sampled from a deep generative network to satisfy the oversampling requirement in ptychography. Because the deep generative network is pre-trained and its output can be computed as we collect data, the experimental data and the time to acquire the data can be reduced. We validate the method by presenting the reconstruction quality compared to the previously proposed and traditional approaches and comment on the strengths and drawbacks of the proposed approach.}, archivePrefix = {arXiv}, arxivId = {2207.14392}, author = {Barutcu, Semih and Katsaggelos, Aggelos K. and G{\"{u}}rsoy, Doğa}, eprint = {2207.14392}, journal = {arXiv preprint arXiv:2207.14392}, month = {jul}, title = {{A Deep Generative Approach to Oversampling in Ptychography}}, url = {http://arxiv.org/abs/2207.14392}, year = {2022} }
@article{bari2022psychotic, abstract = {Background: The COVID-19 disease results from infection by the SARS-CoV-2 virus to produce a range of mild to severe physical, neurological, and mental health symptoms. The COVID-19 pandemic has indirectly caused significant emotional distress, triggering the emergence of mental health symptoms in individuals who were not previously affected or exacerbating symptoms in those with existing mental health conditions. Emotional distress and certain mental health conditions can lead to violent ideation and disruptive behavior, including aggression, threatening acts, deliberate harm toward other people or animals, and inattention to or noncompliance with education or workplace rules. Of the many mental health conditions that can be associated with violent ideation and disruptive behavior, psychosis can evidence greater vulnerability to unpredictable changes and being at a greater risk for them. Individuals with psychosis can also be more susceptible to contracting COVID-19 disease. Objective: This study aimed to investigate whether violent ideation, disruptive behavior, or psychotic symptoms were more prevalent in a population with COVID-19 and did not precede the pandemic. Methods: In this preliminary study, we analyzed questionnaire responses from a population sample (N=366), received between the end of February 2021 and the start of March 2021 (1 year into the COVID-19 pandemic), regarding COVID-19 illness, violent ideation, disruptive behavior, and psychotic symptoms. Using the Wilcoxon rank sum test followed by multiple comparisons correction, we compared the self-reported frequency of these variables for 3 time windows related to the past 1 month, past 1 month to 1 year, and >1 year ago among the distributions of people who answered whether they tested positive or were diagnosed with COVID-19 by a clinician. We also used multivariable logistic regression with iterative resampling to investigate the relationship between these variables occurring >1 year ago (ie, before the pandemic) and the likelihood of contracting COVID-19. Results: We observed a significantly higher frequency of self-reported violent ideation, disruptive behavior, and psychotic symptoms, for all 3 time windows of people who tested positive or were diagnosed with COVID-19 by a clinician. Using multivariable logistic regression, we observed 72% to 94% model accuracy for an increased incidence of COVID-19 in participants who reported violent ideation, disruptive behavior, or psychotic symptoms >1 year ago. Conclusions: This preliminary study found that people who reported a test or clinician diagnosis of COVID-19 also reported higher frequencies of violent ideation, disruptive behavior, or psychotic symptoms across multiple time windows, indicating that they were not likely to be the result of COVID-19. In parallel, participants who reported these behaviors >1 year ago (ie, before the pandemic) were more likely to be diagnosed with COVID-19, suggesting that violent ideation, disruptive behavior, in addition to psychotic symptoms, were associated with COVID-19 with an approximately 70% to 90% likelihood.}, author = {Bari, Sumra and Vike, Nicole L. and Stetsiv, Khrystyna and Woodward, Sean and Lalvani, Shamal and Stefanopoulos, Leandros and Kim, Byoung Woo and Maglaveras, Nicos and Breiter, Hans C. and Katsaggelos, Aggelos K.}, doi = {10.2196/36444}, issn = {2561-326X}, journal = {JMIR Formative Research}, keywords = {COVID-19,delusions,disruptive behavior,distress,machine learning,mental health,pandemic,paranoia,psychological health,psychosis,psychotic symptoms,risk,stress,violent ideation}, month = {aug}, number = {8}, pages = {e36444}, publisher = {JMIR Publications}, title = {{The Prevalence of Psychotic Symptoms, Violent Ideation, and Disruptive Behavior in a Population With SARS-CoV-2 Infection: Preliminary Study}}, url = {https://formative.jmir.org/2022/8/e36444}, volume = {6}, year = {2022} }
@article{Yunan2022, abstract = {The relationship of human brain structure to cognitive function is complex, and how this relationship differs between childhood and adulthood is poorly understood. One strong hypothesis suggests the cognitive function of Fluid Intelligence (Gf) is dependent on prefrontal cortex and parietal cortex. In this work, we developed a novel graph convolutional neural networks (gCNNs) for the analysis of localized anatomic shape and prediction of Gf. Morphologic information of the cortical ribbons and subcortical structures was extracted from T1-weighted MRIs within two independent cohorts, the Adolescent Brain Cognitive Development Study (ABCD; age: 9.93 ± 0.62 years) of children and the Human Connectome Project (HCP; age: 28.81 ± 3.70 years). Prediction combining cortical and subcortical surfaces together yielded the highest accuracy of Gf for both ABCD (R = 0.314) and HCP datasets (R = 0.454), outperforming the state-of-the-art prediction of Gf from any other brain measures in the literature. Across both datasets, the morphology of the amygdala, hippocampus, and nucleus accumbens, along with temporal, parietal and cingulate cortex consistently drove the prediction of Gf, suggesting a significant reframing of the relationship between brain morphology and Gf to include systems involved with reward/aversion processing, judgment and decision-making, motivation, and emotion.}, author = {Wu, Yunan and Besson, Pierre and Azcona, Emanuel A. and Bandt, S. Kathleen and Parrish, Todd B. and Breiter, Hans C. and Katsaggelos, Aggelos K.}, doi = {10.1038/s41598-022-22313-x}, issn = {2045-2322}, journal = {Scientific Reports}, month = {oct}, number = {1}, pages = {17760}, pmid = {36273036}, title = {{A multicohort geometric deep learning study of age dependent cortical and subcortical morphologic interactions for fluid intelligence prediction}}, url = {https://www.nature.com/articles/s41598-022-22313-x}, volume = {12}, year = {2022} }
@article{Miguel2022, abstract = {Background and objective: Intracranial hemorrhage (ICH) is a life-threatening emergency that can lead to brain damage or death, with high rates of mortality and morbidity. The fast and accurate detection of ICH is important for the patient to get an early and efficient treatment. To improve this diagnostic process, the application of Deep Learning (DL) models on head CT scans is an active area of research. Although promising results have been obtained, many of the proposed models require slice-level annotations by radiologists, which are costly and time-consuming. Methods: We formulate the ICH detection as a problem of Multiple Instance Learning (MIL) that allows training with only scan-level annotations. We develop a new probabilistic method based on Deep Gaussian Processes (DGP) that is able to train with this MIL setting and accurately predict ICH at both slice- and scan-level. The proposed DGPMIL model is able to capture complex feature relations by using multiple Gaussian Process (GP) layers, as we show experimentally. Results: To highlight the advantages of DGPMIL in a general MIL setting, we first conduct several controlled experiments on the MNIST dataset. We show that multiple GP layers outperform one-layer GP models, especially for complex feature distributions. For ICH detection experiments, we use two public brain CT datasets (RSNA and CQ500). We first train a Convolutional Neural Network (CNN) with an attention mechanism to extract the image features, which are fed into our DGPMIL model to perform the final predictions. The results show that DGPMIL model outperforms VGPMIL as well as the attention-based CNN for MIL and other state-of-the-art methods for this problem. The best performing DGPMIL model reaches an AUC-ROC of 0.957 (resp. 0.909) and an AUC-PR of 0.961 (resp. 0.889) on the RSNA (resp. CQ500) dataset. Conclusion: The competitive performance at slice- and scan-level shows that DGPMIL model provides an accurate diagnosis on slices without the need for slice-level annotations by radiologists during training. As MIL is a common problem setting, our model can be applied to a broader range of other tasks, especially in medical image classification, where it can help the diagnostic process.}, author = {L{\'{o}}pez-P{\'{e}}rez, Miguel and Schmidt, Arne and Wu, Yunan and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1016/j.cmpb.2022.106783}, issn = {01692607}, journal = {Computer Methods and Programs in Biomedicine}, keywords = {Deep Gaussian processes,Intracranial hemorrhage detection,Multiple instance learning,Weakly supervised learning}, month = {jun}, pages = {106783}, pmid = {35390723}, title = {{Deep Gaussian processes for multiple instance learning: Application to CT intracranial hemorrhage detection}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S0169260722001699}, volume = {219}, year = {2022} }
@article{Woodward2022, abstract = {Background: Although the mental health impacts of COVID-19 on the general population have been well studied, studies of the long-term impacts of COVID-19 on infected individuals are relatively new. To date, depression, anxiety, and neurological symptoms associated with post-COVID-19 syndrome (PCS) have been observed in the months following COVID-19 recovery. Suicidal thoughts and behavior (STB) have also been preliminarily proposed as sequelae of COVID-19. Objective: We asked 3 questions. First, do participants reporting a history of COVID-19 diagnosis or a close relative having severe COVID-19 symptoms score higher on depression (Patient Health Questionnaire-9 [PHQ-9]) or state anxiety (State Trait Anxiety Index) screens than those who do not? Second, do participants reporting a COVID-19 diagnosis score higher on PCS-related PHQ-9 items? Third, do participants reporting a COVID-19 diagnosis or a close relative having severe COVID-19 symptoms score higher in STB before, during, or after the first year of the pandemic? Methods: This preliminary study analyzed responses to a COVID-19 and mental health questionnaire obtained from a US population sample, whose data were collected between February 2021 and March 2021. We used the Mann-Whitney U test to detect differences in the medians of the total PHQ-9 scores, PHQ-9 component scores, and several STB scores between participants claiming a past clinician diagnosis of COVID-19 and those denying one, as well as between participants claiming severe COVID-19 symptoms in a close relative and those denying them. Where significant differences existed, we created linear regression models to predict the scores based on COVID-19 response as well as demographics to identify potential confounding factors in the Mann-Whitney relationships. Moreover, for STB scores, which corresponded to 5 questions asking about 3 different time intervals (i.e., past 1 year or more, past 1 month to 1 year, and past 1 month), we developed repeated-measures ANOVAs to determine whether scores tended to vary over time. Results: We found greater total depression (PHQ-9) and state anxiety (State Trait Anxiety Index) scores in those with COVID-19 history than those without (Bonferroni P = .001 and Bonferroni P = .004) despite a similar history of diagnosed depression and anxiety. Greater scores were noted for a subset of depression symptoms (PHQ-9 items) that overlapped with the symptoms of PCS (all Bonferroni Ps < .05). Moreover, we found greater overall STB scores in those with COVID-19 history, equally in time windows preceding, during, and proceeding infection (all Bonferroni Ps < .05). Conclusions: We confirm previous studies linking depression and anxiety diagnoses to COVID-19 recovery. Moreover, our findings suggest that depression diagnoses associated with COVID-19 history relate to PCS symptoms, and that STB associated with COVID-19 in some cases precede infection.}, author = {Woodward, Sean F. and Bari, Sumra and Vike, Nicole and Lalvani, Shamal and Stetsiv, Khrystyna and Kim, Byoung Woo and Stefanopoulos, Leandros and Maglaveras, Nicos and Breiter, Hans and Katsaggelos, Aggelos K.}, doi = {10.2196/36656}, issn = {2561-326X}, journal = {JMIR Formative Research}, keywords = {COVID-19,PHQ-9,Patient Health Questionnaire-9,STAI,State Trait Anxiety Index,depression,post-COVID-19 syndrome,suicidality}, month = {oct}, number = {10}, pages = {e36656}, publisher = {JMIR Publications Inc., Toronto, Canada}, title = {{Anxiety, Post–COVID-19 Syndrome-Related Depression, and Suicidal Thoughts and Behaviors in COVID-19 Survivors: Cross-sectional Study}}, url = {https://formative.jmir.org/2022/10/e36656}, volume = {6}, year = {2022} }
@article{Pablo2020, abstract = {In the last years, crowdsourcing is transforming the way classification training sets are obtained. Instead of relying on a single expert annotator, crowdsourcing shares the labelling effort among a large number of collaborators. For instance, this is being applied in the laureate laser interferometer gravitational waves observatory (LIGO), in order to detect glitches which might hinder the identification of true gravitational-waves. The crowdsourcing scenario poses new challenging difficulties, as it has to deal with different opinions from a heterogeneous group of annotators with unknown degrees of expertise. Probabilistic methods, such as Gaussian processes (GP), have proven successful in modeling this setting. However, GPs do not scale up well to large data sets, which hampers their broad adoption in real-world problems (in particular LIGO). This has led to the very recent introduction of deep learning based crowdsourcing methods, which have become the state-of-the-art for this type of problems. However, the accurate uncertainty quantification provided by GPs has been partially sacrificed. This is an important aspect for astrophysicists in LIGO, since a glitch detection system should provide very accurate probability distributions of its predictions. In this work, we first leverage a standard sparse GP approximation (SVGP) to develop a GP-based crowdsourcing method that factorizes into mini-batches. This makes it able to cope with previously-prohibitive data sets. This first approach, which we refer to as scalable variational Gaussian processes for crowdsourcing (SVGPCR), brings back GP-based methods to a state-of-the-art level, and excels at uncertainty quantification. SVGPCR is shown to outperform deep learning based methods and previous probabilistic ones when applied to the LIGO data. Its behavior and main properties are carefully analyzed in a controlled experiment based on the MNIST data set. Moreover, recent GP inference techniques are also adapted to crowdsourcing and evaluated experimentally.}, archivePrefix = {arXiv}, arxivId = {1911.01915}, author = {Morales-Alvarez, Pablo and Ruiz, Pablo and Coughlin, Scott and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1109/TPAMI.2020.3025390}, eprint = {1911.01915}, issn = {0162-8828}, journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence}, keywords = {Crowdsourcing,citizen science,deep learning,laser interferometer gravitational waves observato,scalability,sparse Gaussian processes,uncertainty quantification}, month = {mar}, number = {3}, pages = {1534--1551}, pmid = {32956038}, title = {{Scalable Variational Gaussian Processes for Crowdsourcing: Glitch Detection in LIGO}}, url = {https://ieeexplore.ieee.org/document/9201029/}, volume = {44}, year = {2022} }
@article{Fernando2022, abstract = {Stain variation between images is a main issue in the analysis of histological images. These color variations, produced by different staining protocols and scanners in each laboratory, hamper the performance of computer-aided diagnosis (CAD) systems that are usually unable to generalize to unseen color distributions. Blind color deconvolution techniques separate multi-stained images into single stained bands that can then be used to reduce the generalization error of CAD systems through stain color normalization and/or stain color augmentation. In this work, we present a Bayesian modeling and inference blind color deconvolution framework based on the K-Singular Value Decomposition algorithm. Two possible inference procedures, variational and empirical Bayes are presented. Both provide the automatic estimation of the stain color matrix, stain concentrations and all model parameters. The proposed framework is tested on stain separation, image normalization, stain color augmentation, and classification problems.}, author = {P{\'{e}}rez-Bueno, Fernando and Serra, Juan G. and Vega, Miguel and Mateos, Javier and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1016/j.compmedimag.2022.102048}, issn = {08956111}, journal = {Computerized Medical Imaging and Graphics}, keywords = {Bayesian modeling,Blind Color Deconvolution,Histological images,Stain Normalization}, month = {apr}, pages = {102048}, pmid = {35202893}, title = {{Bayesian K-SVD for H and E blind color deconvolution. Applications to stain normalization, data augmentation and cancer classification}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S0895611122000210}, volume = {97}, year = {2022} }
@article{ballester2022application, abstract = {The Tauc–Lorentz–Urbach (TLU) dispersion model allows us to build a dielectric function from only a few parameters. However, this dielectric function is non-analytic and presents some mathematical drawbacks. As a consequence of this issue, the model becomes inaccurate. In the present work, we will adopt a procedure to conveniently transform the TLU model into a self-consistent dispersion model. The transformation involves the integration of the original TLU imaginary dielectric function ϵ2 by using a Lorentzian-type function of semi-width, $\Gamma$. This novel model is analytic and obeys the other necessary mathematical requirements of the optical constants of solid-state materials. The main difference with the non-analytic TLU model occurs at values of the photon energy near or lower than that of the bandgap energy (within the Urbach absorption region). In particular, this new model allows us to reliably extend the optical characterization of amorphous-semiconductor thin films within the limit to zero photon energy. To the best of our knowledge, this is the first time that the analytic TLU model has been successfully used to accurately determine the optical constants of unhydrogenated a-Si films using only their normal-incidence transmission spectra.}, author = {Ballester, Manuel and Garc{\'{i}}a, Marcos and M{\'{a}}rquez, Almudena P. and Blanco, Eduardo and Fern{\'{a}}ndez, Susana M. and Minkov, Dorian and Katsaggelos, Aggelos K. and Cossairt, Oliver and Willomitzer, Florian and M{\'{a}}rquez, Emilio}, doi = {10.3390/coatings12101549}, issn = {2079-6412}, journal = {Coatings}, keywords = {Tauc–Lorentz model,Tauc–Lorentz–Urbach model,amorphous semiconductors,dielectric function,optical properties,thin-film characterization}, month = {oct}, number = {10}, pages = {1549}, publisher = {MDPI}, title = {{Application of the Holomorphic Tauc-Lorentz-Urbach Function to Extract the Optical Constants of Amorphous Semiconductor Thin Films}}, url = {https://www.mdpi.com/2079-6412/12/10/1549}, volume = {12}, year = {2022} }
@article{Jennifer2022, abstract = {Quantifying motion in 3D is important for studying the behavior of humans and other animals, but manual pose annotations are expensive and time-consuming to obtain. Self-supervised keypoint discovery is a promising strategy for estimating 3D poses without annotations. However, current keypoint discovery approaches commonly process single 2D views and do not operate in the 3D space. We propose a new method to perform self-supervised keypoint discovery in 3D from multi-view videos of behaving agents, without any keypoint or bounding box supervision in 2D or 3D. Our method uses an encoder-decoder architecture with a 3D volumetric heatmap, trained to reconstruct spatiotemporal differences across multiple views, in addition to joint length constraints on a learned 3D skeleton of the subject. In this way, we discover keypoints without requiring manual supervision in videos of humans and rats, demonstrating the potential of 3D keypoint discovery for studying behavior.}, archivePrefix = {arXiv}, arxivId = {2212.07401}, author = {Sun, Jennifer J. and Karashchuk, Pierre and Dravid, Amil and Ryou, Serim and Fereidooni, Sonia and Tuthill, John and Katsaggelos, Aggelos and Brunton, Bingni W. and Gkioxari, Georgia and Kennedy, Ann and Yue, Yisong and Perona, Pietro}, eprint = {2212.07401}, journal = {arXiv preprint arXiv:2212.07401}, month = {dec}, title = {{BKinD-3D: Self-Supervised 3D Keypoint Discovery from Multi-View Videos}}, url = {http://arxiv.org/abs/2212.07401}, year = {2022} }
@article{chopp2022image, abstract = {X-ray fluorescence (XRF) analysis of art objects has rapidly gained popularity since the late 2000s due to its increased accessibility to scientists. This introduced an imaging component whereby the XRF image volume provides clues as to which chemical elements are present and where they are located spatially in the object. However, as is the nature of collecting measurements, there are limitations preventing perfect acquisition; e.g, spatial resolution, signal-to-noise ratio, etc. The field of image processing, in part, aims to overcome these limitations. Image processing applications in XRF imaging are only just starting to arise due to the increased interest and availability in XRF analysis. In this article, we aim to reach readers in XRF imaging or image processing in an effort to call for further research in the field. We review the basics of XRF imaging and analysis that is tailored for those unfamiliar with this imaging modality. We then delve into various publications of image processing methods as applied to XRF data. Throughout this article, we examine (and opine on) the XRF field through a lens of the image processing field.}, author = {Chopp, Henry and McGeachy, Alicia and Alfeld, Matthias and Cossairt, Oliver and Walton, Marc and Katsaggelos, Aggelos}, doi = {10.1109/MBITS.2022.3197100}, issn = {2692-4110}, journal = {IEEE BITS the Information Theory Magazine}, number = {1}, pages = {1--12}, publisher = {IEEE}, title = {{Image Processing Perspectives of X-Ray Fluorescence Data in Cultural Heritage Sciences}}, url = {https://ieeexplore.ieee.org/document/9851850/}, volume = {2}, year = {2022} }
@article{liu2022digital, abstract = {Digital restoration is a rapidly growing methodology within the field of heritage conservation, especially for early cinematic films which have intrinsically unstable dye colourants that suffer from irreversible colour fading. Although numerous techniques to restore film digitally have emerged recently, complex degradation remains a challenging problem. This paper proposes a novel vector quantization (VQ) algorithm for restoring movie frames based on the acquisition of spectroscopic data with a custom-made push-broom VNIR hyperspectral camera (380–780 nm). The VQ algorithm utilizes what we call a multi-codebook that correlates degraded areas with corresponding non-degraded ones selected from reference frames. The spectral-codebook was compared with a professional commercially available film restoration software (DaVinci Resolve 17) tested both on RGB and on hyperspectral providing better results in terms of colour reconstruction.}, author = {Liu, L. and Catelli, E. and Katsaggelos, A. and Sciutto, G. and Mazzeo, R. and Milanic, M. and Stergar, J. and Prati, S. and Walton, M.}, doi = {10.1038/s41598-022-25248-5}, issn = {2045-2322}, journal = {Scientific Reports}, month = {dec}, number = {1}, pages = {21982}, pmid = {36539479}, publisher = {Nature Publishing Group UK London}, title = {{Digital restoration of colour cinematic films using imaging spectroscopy and machine learning}}, url = {https://www.nature.com/articles/s41598-022-25248-5}, volume = {12}, year = {2022} }
@article{dai2022adaptive, abstract = {Dense depth map capture is challenging in existing active sparse illumination based depth acquisition techniques, such as LiDAR. Various techniques have been proposed to estimate a dense depth map based on fusion of the sparse depth map measurement with the RGB image. Recent advances in hardware enable adaptive depth measurements resulting in further improvement of the dense depth map estimation. In this paper, we study the topic of estimating dense depth from depth sampling. The adaptive sparse depth sampling network is jointly trained with a fusion network of an RGB image and sparse depth, to generate optimal adaptive sampling masks. Deep learning based superpixel sampling and soft sampling approximation are applied. We show that such adaptive sampling masks can generalize well to many RGB and sparse depth fusion algorithms under a variety of sampling rates (as low as 0.0625%). The proposed adaptive sampling method is fully differentiable and flexible to be trained end-to-end with upstream perception algorithms.}, author = {Dai, Qiqin and Li, Fengqiang and Cossairt, Oliver and Katsaggelos, Aggelos K.}, doi = {10.1109/TCI.2022.3155377}, issn = {2333-9403}, journal = {IEEE Transactions on Computational Imaging}, keywords = {Adaptive sampling,Deep learning,Depth estimation,Sensor fusion}, pages = {224--235}, publisher = {IEEE}, title = {{Adaptive Illumination Based Depth Sensing Using Deep Superpixel and Soft Sampling Approximation}}, url = {https://ieeexplore.ieee.org/document/9723580/}, volume = {8}, year = {2022} }
@article{Vassilis2022, abstract = {Monitoring and treatment of severely ill COVID-19 patients in the ICU poses many challenges. The effort to understand the pathophysiology and progress of the disease requires high-quality annotated multi-parameter databases. We present CoCross, a platform that enables the monitoring and fusion of clinical information from in-ICU COVID-19 patients into an annotated database. CoCross consists of three components: (1) The CoCross4Pros native android application, a modular application, managing the interaction with portable medical devices, (2) the cloud-based data management services built-upon HL7 FHIR and ontologies, (3) the web-based application for intensivists, providing real-time review and analytics of the acquired measurements and auscultations. The platform has been successfully deployed since June 2020 in two ICUs in Greece resulting in a dynamic unified annotated database integrating clinical information with chest sounds and diagnostic imaging. Until today multisource data from 176 ICU patients were acquired and imported in the CoCross database, corresponding to a five-day average monitoring period including a dataset with 3477 distinct auscultations. The platform is well accepted and positively rated by the users regarding the overall experience.}, author = {Kilintzis, Vassilis and Beredimas, Nikolaos and Kaimakamis, Evangelos and Stefanopoulos, Leandros and Chatzis, Evangelos and Jahaj, Edison and Bitzani, Militsa and Kotanidou, Anastasia and Katsaggelos, Aggelos K. and Maglaveras, Nicos}, doi = {10.3390/healthcare10020276}, issn = {2227-9032}, journal = {Healthcare}, keywords = {Biomedical monitoring,COVID-19,Heart sounds,ICT pl,ICT platform,ICU,Lung sounds,Lung ultrasound,Research database,X-rays}, month = {jan}, number = {2}, pages = {276}, title = {{CoCross: An ICT Platform Enabling Monitoring Recording and Fusion of Clinical Information Chest Sounds and Imaging of COVID-19 ICU Patients}}, url = {https://www.mdpi.com/2227-9032/10/2/276}, volume = {10}, year = {2022} }
@article{Petmezas2022, abstract = {Background: Electrocardiogram (ECG) is one of the most common noninvasive diagnostic tools that can provide useful information regarding a patient's health status. Deep learning (DL) is an area of intense exploration that leads the way in most attempts to create powerful diagnostic models based on physiological signals. Objective: This study aimed to provide a systematic review of DL methods applied to ECG data for various clinical applications. Methods: The PubMed search engine was systematically searched by combining “deep learning” and keywords such as “ecg,” “ekg,” “electrocardiogram,” “electrocardiography,” and “electrocardiology.” Irrelevant articles were excluded from the study after screening titles and abstracts, and the remaining articles were further reviewed. The reasons for article exclusion were manuscripts written in any language other than English, absence of ECG data or DL methods involved in the study, and absence of a quantitative evaluation of the proposed approaches. Results: We identified 230 relevant articles published between January 2020 and December 2021 and grouped them into 6 distinct medical applications, namely, blood pressure estimation, cardiovascular disease diagnosis, ECG analysis, biometric recognition, sleep analysis, and other clinical analyses. We provide a complete account of the state-of-the-art DL strategies per the field of application, as well as major ECG data sources. We also present open research problems, such as the lack of attempts to address the issue of blood pressure variability in training data sets, and point out potential gaps in the design and implementation of DL models. Conclusions: We expect that this review will provide insights into state-of-the-art DL methods applied to ECG data and point to future directions for research on DL to create robust models that can assist medical experts in clinical decision-making.}, author = {Petmezas, Georgios and Stefanopoulos, Leandros and Kilintzis, Vassilis and Tzavelis, Andreas and Rogers, John A. and Katsaggelos, Aggelos K. and Maglaveras, Nicos}, doi = {10.2196/38454}, issn = {2291-9694}, journal = {JMIR Medical Informatics}, keywords = {CNN,ECG,ECG databases,LSTM,ResNet,clinical decision,convolutional neural networks,decision support,deep learning,diagnostic tools,electrocardiogram,long short-term memory,residual neural network}, month = {aug}, number = {8}, pages = {e38454}, publisher = {JMIR Publications Toronto, Canada}, title = {{State-of-the-Art Deep Learning Methods on Electrocardiogram Data: Systematic Review}}, url = {https://medinform.jmir.org/2022/8/e38454}, volume = {10}, year = {2022} }
@article{Michael2022a, abstract = {BACKGROUND AND PURPOSE: Prioritizing reading of noncontrast head CT examinations through an automated triage system may improve time to care for patients with acute neuroradiologic findings. We present a natural language-processing approach for labeling findings in noncontrast head CT reports, which permits creation of a large, labeled dataset of head CT images for development of emergent-finding detection and reading-prioritization algorithms. MATERIALS AND METHODS: In this retrospective study, 1002 clinical radiology reports from noncontrast head CTs collected between 2008 and 2013 were manually labeled across 12 common neuroradiologic finding categories. Each report was then encoded using an n-gram model of unigrams, bigrams, and trigrams. A logistic regression model was then trained to label each report for every common finding. Models were trained and assessed using a combination of L2 regularization and 5-fold cross-validation. RESULTS: Model performance was strongest for the fracture, hemorrhage, herniation, mass effect, pneumocephalus, postoperative status, and volume loss models in which the area under the receiver operating characteristic curve exceeded 0.95. Performance was relatively weaker for the edema, hydrocephalus, infarct, tumor, and white-matter disease models (area under the receiver operating characteristic curve > 0.85). Analysis of coefficients revealed finding-specific words among the top coefficients in each model. Class output probabilities were found to be a useful indicator of predictive error on individual report examples in higher-performing models. CONCLUSIONS: Combining logistic regression with n-gram encoding is a robust approach to labeling common findings in noncontrast head CT reports.}, author = {Iorga, Michael and Drakopoulos, M. and Naidech, A.M. and Katsaggelos, A.K. and Parrish, T.B. and Hill, V.B.}, doi = {10.3174/ajnr.A7500}, issn = {0195-6108}, journal = {American Journal of Neuroradiology}, month = {may}, number = {5}, pages = {721--726}, pmid = {35483905}, title = {{Labeling Noncontrast Head CT Reports for Common Findings Using Natural Language Processing}}, url = {http://www.ajnr.org/lookup/doi/10.3174/ajnr.A7500}, volume = {43}, year = {2022} }
@article{Petmezas2022a, abstract = {Respiratory diseases constitute one of the leading causes of death worldwide and directly affect the patient's quality of life. Early diagnosis and patient monitoring, which conventionally include lung auscultation, are essential for the efficient management of respiratory diseases. Manual lung sound interpretation is a subjective and time-consuming process that requires high medical expertise. The capabilities that deep learning offers could be exploited in order that robust lung sound classification models can be designed. In this paper, we propose a novel hybrid neural model that implements the focal loss (FL) function to deal with training data imbalance. Features initially extracted from short-time Fourier transform (STFT) spectrograms via a convolutional neural network (CNN) are given as input to a long short-term memory (LSTM) network that memorizes the temporal dependencies between data and classifies four types of lung sounds, including normal, crackles, wheezes, and both crackles and wheezes. The model was trained and tested on the ICBHI 2017 Respiratory Sound Database and achieved state-of-the-art results using three different data splitting strategies—namely, sensitivity 47.37%, specificity 82.46%, score 64.92% and accuracy 73.69% for the official 60/40 split, sensitivity 52.78%, specificity 84.26%, score 68.52% and accuracy 76.39% using interpatient 10-fold cross validation, and sensitivity 60.29% and accuracy 74.57% using leave-one-out cross validation.}, author = {Petmezas, Georgios and Cheimariotis, Grigorios-Aris and Stefanopoulos, Leandros and Rocha, Bruno and Paiva, Rui Pedro and Katsaggelos, Aggelos K. and Maglaveras, Nicos}, doi = {10.3390/s22031232}, issn = {1424-8220}, journal = {Sensors}, keywords = {Asthma,CNN,COPD,Crackles,Focal loss,LSTM,Lung sounds,STFT,Wheezes}, month = {feb}, number = {3}, pages = {1232}, pmid = {35161977}, publisher = {MDPI}, title = {{Automated Lung Sound Classification Using a Hybrid CNN-LSTM Network and Focal Loss Function}}, url = {https://www.mdpi.com/1424-8220/22/3/1232}, volume = {22}, year = {2022} }
@article{Emanuel2022, abstract = {Operant keypress tasks, where each action has a consequence, have been analogized to the construct of "wanting" and produce lawful relationships in humans that quantify preferences for approach and avoidance behavior. It is unknown if rating tasks without an operant framework, which can be analogized to "liking", show similar lawful relationships. We studied three independent cohorts of participants (N = 501, 506, and 4,019 participants) collected by two distinct organizations, using the same 7-point Likert scale to rate negative to positive preferences for pictures from the International Affective Picture Set. Picture ratings without an operant framework produced similar value functions, limit functions, and trade-off functions to those reported in the literature for operant keypress tasks, all with goodness of fits above 0.75. These value, limit, and trade-off functions were discrete in their mathematical formulation, recurrent across all three independent cohorts, and demonstrated scaling between individual and group curves. In all three experiments, the computation of loss aversion showed 95% confidence intervals below the value of 2, arguing against a strong overweighting of losses relative to gains, as has previously been reported for keypress tasks or games of chance with calibrated uncertainty. Graphed features from the three cohorts were similar and argue that preference assessments meet three of four criteria for lawfulness, providing a simple, short, and low-cost method for the quantitative assessment of preference without forced choice decisions, games of chance, or operant keypressing. This approach can easily be implemented on any digital device with a screen (e.g., cellphones).}, archivePrefix = {arXiv}, arxivId = {2203.06448}, author = {Azcona, Emanuel A. and Kim, Byoung-Woo and Vike, Nicole L. and Bari, Sumra and Lalvani, Shamal and Stefanopoulos, Leandros and Woodward, Sean and Block, Martin and Katsaggelos, Aggelos K. and Breiter, Hans C.}, eprint = {2203.06448}, journal = {arXiv preprint arXiv:2203.06448}, month = {mar}, title = {{Discrete, recurrent, and scalable patterns in human judgement underlie affective picture ratings}}, url = {http://arxiv.org/abs/2203.06448}, year = {2022} }
@article{BingjieJenny2022, abstract = {X-ray fluorescence spectroscopy (XRF) plays an important role for elemental analysis in a wide range of scientific fields, especially in cultural heritage.}, archivePrefix = {arXiv}, arxivId = {2207.12651}, author = {Xu, Bingjie Jenny and Wu, Yunan and Hao, Pengxiao and Vermeulen, Marc and McGeachy, Alicia and Smith, Kate and Eremin, Katherine and Rayner, Georgina and Verri, Giovanni and Willomitzer, Florian and Alfeld, Matthias and Tumblin, Jack and Katsaggelos, Aggelos and Walton, Marc}, doi = {10.1039/D2JA00246A}, eprint = {2207.12651}, issn = {0267-9477}, journal = {Journal of Analytical Atomic Spectrometry}, number = {12}, pages = {2672--2682}, title = {{Can deep learning assist automatic identification of layered pigments from XRF data?}}, url = {http://xlink.rsc.org/?DOI=D2JA00246A}, volume = {37}, year = {2022} }
@article{Xin2022, author = {Yuan, Xin and Brady, David J. and Suo, Jinli and Arguello, Henry and Rodrigues, Miguel and Katsaggelos, Aggelos K.}, doi = {10.1109/JSTSP.2022.3185190}, issn = {1932-4553}, journal = {IEEE Journal of Selected Topics in Signal Processing}, month = {jun}, number = {4}, pages = {603--607}, title = {{Editorial: Introduction to the Special Issue on Deep Learning for High-Dimensional Sensing}}, url = {https://ieeexplore.ieee.org/document/9829820/}, volume = {16}, year = {2022} }
@article{banerjee2021learning, abstract = {Roomerature semiconductor radiation detectors (RTSDs) such as CdTe are becoming popular in computed tomography (CT) imaging. These detectors are often pixelated, requiring cumbersome postinteraction 3-D event reconstruction, which can benefit from detailed material characterization at the micron level. Transport properties and material defects with respect to electrons and holes are to be characterized, which is a labor-intensive process. Current state-of-the-art characterization is done either as a whole or at most pixel-by-pixel over the detector material. In this article, we propose a novel learning-based physical model to infer material properties at the microscopic level for RTSD. Our approach uses a novel physics-inspired learning model based on physical transport of charges with trapping centers for electrons and holes in the detector. The proposed model learns these material properties from known or measured input charges to the detector along with known or measured output signals and distributed charges in the bulk of the RTSD. The actual physical detector is divided into voxels in space and takes into account different material properties (such as drift, trapping, detrapping, and recombination) in each voxel as learnable model parameters. The model is based on a physics-inspired recurrent neural network model instead of traditional convolutional or fully connected networks. The advantage of our approach is the one-to-one relationship between the actual physical parameters of the voxels and learnable weights in the model, far fewer trainable parameters compared to traditional neural network approaches and less training time. The performance of our model has been evaluated on cadmium zinc telluride (CdZnTe), with voxels of three sizes, 25, 50, and 100$\mu$ m, for single charge input as well as multiple charge inputs at different voxel positions. Our learning-based model provides material properties with higher spatial resolution and performs well in all scenarios and matches the actual physical parameters better than state-of-the-art classical approaches.}, author = {Banerjee, Srutarshi and Rodrigues, Miesher and Vija, Alexander Hans and Katsaggelos, Aggelos K.}, doi = {10.1109/TNS.2021.3130486}, issn = {0018-9499}, journal = {IEEE Transactions on Nuclear Science}, keywords = {Charge transport,Defects,Detrapping,Learning-based model,Material characterization,Room temperature semiconductor detector,Schokley-Ramo theorem,Trapping,Trapping centers}, month = {jan}, number = {1}, pages = {2--16}, publisher = {IEEE}, title = {{A Learning-Based Physical Model of Charge Transport in Room-Temperature Semiconductor Detectors}}, url = {https://ieeexplore.ieee.org/document/9625943/}, volume = {69}, year = {2022} }
@article{Aggelosd, abstract = {XRFast is a new software package written in Julia to decompose XRF imaging dataset.}, author = {Vermeulen, Marc and McGeachy, Alicia and Xu, Bingjie and Chopp, Henry and Katsaggelos, Aggelos and Meyers, Rebecca and Alfeld, Matthias and Walton, Marc}, doi = {10.1039/D2JA00114D}, issn = {0267-9477}, journal = {Journal of Analytical Atomic Spectrometry}, number = {10}, pages = {2130--2143}, title = {{XRFast a new software package for processing of MA-XRF datasets using machine learning}}, url = {https://pubs.rsc.org/en/content/articlelanding/2022/JA/D2JA00114D http://xlink.rsc.org/?DOI=D2JA00114D}, volume = {37}, year = {2022} }
@article{arief2022towards, abstract = {A robust–accurate estimation of fluid flow is the main building block of a distributed virtual flow meter. Unfortunately, a big leap in algorithm development would be required for this objective to come to fruition, mainly due to the inability of current machine learning algorithms to make predictions outside the training data distribution. To improve predictions outside the training distribution, we explore the continual learning (CL) paradigm for accurately estimating the characteristics of fluid flow in pipelines. A significant challenge facing CL is the concept of catastrophic forgetting. In this paper, we provide a novel approach for how to address the forgetting problem via compressing the distributed sensor data to increase the capacity of the CL memory bank using a compressive learning algorithm. Through extensive experiments, we show that our approach provides around 8% accuracy improvement compared to other CL algorithms when applied to a real-world distributed sensor dataset collected from an oilfield. Noticeable accuracy improvement is also achieved when using our proposed approach with the CL benchmark datasets, achieving state-of-the-art accuracies for the CIFAR-10 dataset on blurry10 and blurry30 settings of 80.83% and 88.91%, respectively.}, author = {Arief, Hasan Asy'ari and Thomas, Peter James and Constable, Kevin and Katsaggelos, Aggelos K.}, doi = {10.3390/s22249878}, issn = {1424-8220}, journal = {Sensors}, keywords = {continual learning,distributed acoustic sensing,virtual flow meter}, month = {dec}, number = {24}, pages = {9878}, pmid = {36560248}, publisher = {MDPI}, title = {{Towards Building a Distributed Virtual Flow Meter via Compressed Continual Learning}}, url = {https://www.mdpi.com/1424-8220/22/24/9878}, volume = {22}, year = {2022} }
@article{KyleAkira2022, abstract = {Binary stars undergo a variety of interactions and evolutionary phases, critical for predicting and explaining observations. Binary population synthesis with full simulation of stellar structure and evolution is computationally expensive, requiring a large number of mass-transfer sequences. The recently developed binary population synthesis code POSYDON incorporates grids of MESA binary star simulations that are interpolated to model large-scale populations of massive binaries. The traditional method of computing a high-density rectilinear grid of simulations is not scalable for higher-dimension grids, accounting for a range of metallicities, rotation, and eccentricity. We present a new active learning algorithm, psy-cris , which uses machine learning in the data-gathering process to adaptively and iteratively target simulations to run, resulting in a custom, high-performance training set. We test psy-cris on a toy problem and find the resulting training sets require fewer simulations for accurate classification and regression than either regular or randomly sampled grids. We further apply psy-cris to the target problem of building a dynamic grid of MESA simulations, and we demonstrate that, even without fine tuning, a simulation set of only ∼1/4 the size of a rectilinear grid is sufficient to achieve the same classification accuracy. We anticipate further gains when algorithmic parameters are optimized for the targeted application. We find that optimizing for classification only may lead to performance losses in regression, and vice versa. Lowering the computational cost of producing grids will enable new population synthesis codes such as POSYDON to cover more input parameters while preserving interpolation accuracies.}, archivePrefix = {arXiv}, arxivId = {2203.16683}, author = {Rocha, Kyle Akira and Andrews, Jeff J. and Berry, Christopher P. L. and Doctor, Zoheyr and Katsaggelos, Aggelos K and {Serra P{\'{e}}rez}, Juan Gabriel and Marchant, Pablo and Kalogera, Vicky and Coughlin, Scott and Bavera, Simone S. and Dotter, Aaron and Fragos, Tassos and Kovlakas, Konstantinos and Misra, Devina and Xing, Zepei and Zapartas, Emmanouil}, doi = {10.3847/1538-4357/ac8b05}, eprint = {2203.16683}, issn = {0004-637X}, journal = {The Astrophysical Journal}, month = {oct}, number = {1}, pages = {64}, title = {{Active Learning for Computationally Efficient Distribution of Binary Evolution Simulations}}, url = {https://iopscience.iop.org/article/10.3847/1538-4357/ac8b05}, volume = {938}, year = {2022} }
@article{Lionel, abstract = {Optical coherence tomography (OCT) is an optical technique which allows for volumetric visualization of the internal structures of translucent materials. Additional information can be gained by measuring the rate of signal attenuation in depth. Techniques have been developed to estimate the rate of attenuation on a voxel by voxel basis. This depth resolved attenuation analysis gives insight into tissue structure and organization in a spatially resolved way. However, the presence of speckle in the OCT measurement causes the attenuation coefficient image to contain unrealistic fluctuations and makes the reliability of these images at the voxel level poor. While the distribution of speckle in OCT images has appeared in literature, the resulting voxelwise corruption of the attenuation analysis has not. In this work, the estimated depth resolved attenuation coefficient from OCT data with speckle is shown to be approximately exponentially distributed. After this, a prior distribution for the depth resolved attenuation coefficient is derived for a simple system using statistical mechanics. Finally, given a set of depth resolved estimates which were made from OCT data in the presence of speckle, a posterior probability distribution for the true voxelwise attenuation coefficient is derived and a Bayesian voxelwise estimator for the coefficient is given. These results are demonstrated in simulation and validated experimentally.}, author = {Fiske, Lionel D. and Aalders, Maurice C. G. and Almasian, Mitra and van Leeuwen, Ton G. and Katsaggelos, Aggelos K. and Cossairt, Oliver and Faber, Dirk J.}, doi = {10.1038/s41598-021-81713-7}, issn = {2045-2322}, journal = {Scientific Reports}, month = {jan}, number = {1}, pages = {2263}, pmid = {33500435}, title = {{Bayesian analysis of depth resolved OCT attenuation coefficients}}, url = {https://www.nature.com/articles/s41598-021-81713-7}, volume = {11}, year = {2021} }
@article{Srutarshi2021, abstract = {We present a novel adaptive host-chip modular architecture for video acquisition to optimize an overall objective task constrained under a given bit rate. The chip is a high resolution imaging sensor such as gigapixel focal plane array (FPA) with low computational power deployed on the field remotely, while the host is a server with high computational power. The communication channel data bandwidth between the chip and host is constrained to accommodate transfer of all captured data from the chip. The host performs objective task specific computations and also intelligently guides the chip to optimize (compress) the data sent to host. This proposed system is modular and highly versatile in terms of flexibility in re-orienting the objective task. In this work, object tracking is the objective task. While our architecture supports any form of compression/distortion, in this paper we use quadtree (QT)-segmented video frames. We use Viterbi (Dynamic Programming) algorithm to minimize the area normalized weighted rate-distortion allocation of resources. The host receives only these degraded frames for analysis. An object detector is used to detect objects, and a Kalman Filter based tracker is used to track those objects. Evaluation of system performance is done in terms of Multiple Object Tracking Accuracy (MOTA) metric. In this proposed novel architecture, performance gains in MOTA is obtained by twice training the object detector with different system generated distortions as a novel 2-step process. Additionally, object detector is assisted by tracker to upscore the region proposals in the detector to further improve the performance.}, archivePrefix = {arXiv}, arxivId = {2102.12046}, author = {Banerjee, Srutarshi and Chopp, Henry H. and Serra, Juan G. and Yang, Hao Tian and Cossairt, Oliver and Katsaggelos, Aggelos K.}, doi = {10.1109/JSEN.2021.3081351}, eprint = {2102.12046}, issn = {1530-437X}, journal = {IEEE Sensors Journal}, keywords = {Image acquisition,Viterbi algorithm,image reconstruction,object detection,object tracker assisted detection,object tracking,optimization,video signal processing}, month = {aug}, number = {15}, pages = {17227--17243}, title = {{An Adaptive Video Acquisition Scheme for Object Tracking and Its Performance Optimization}}, url = {https://ieeexplore.ieee.org/document/9432960/}, volume = {21}, year = {2021} }
@article{Petmezas2021, abstract = {Atrial fibrillation is a heart arrhythmia strongly associated with other heart-related complications that can increase the risk of strokes and heart failure. Manual electrocardiogram (ECG) interpretation for its diagnosis is tedious, time-consuming, requires high expertise, and suffers from inter- and intra-observer variability. Deep learning techniques could be exploited in order for robust arrhythmia detection models to be designed. In this paper, we propose a novel hybrid neural model utilizing focal loss, an improved version of cross-entropy loss, to deal with training data imbalance. ECG features initially extracted via a Convolutional Neural Network (CNN) are input to a Long Short-Term Memory (LSTM) model for temporal dynamics memorization and thus, more accurate classification into the four ECG rhythm types, namely normal (N), atrial fibrillation (AFIB), atrial flutter (AFL) and AV junctional rhythm (J). The model was trained on the MIT-BIH Atrial Fibrillation Database and achieved a sensitivity of 97.87%, and specificity of 99.29% using a ten-fold cross-validation strategy. The proposed model can aid clinicians to detect common atrial fibrillation in real-time on routine screening ECG.}, author = {Petmezas, Georgios and Haris, Kostas and Stefanopoulos, Leandros and Kilintzis, Vassilis and Tzavelis, Andreas and Rogers, John A. and Katsaggelos, Aggelos K. and Maglaveras, Nicos}, doi = {10.1016/j.bspc.2020.102194}, issn = {17468094}, journal = {Biomedical Signal Processing and Control}, keywords = {CNN,LSTM,arrhythmia detection,atrial fibrillation,focal loss}, month = {jan}, pages = {102194}, publisher = {Elsevier}, title = {{Automated Atrial Fibrillation Detection using a Hybrid CNN-LSTM Network on Imbalanced ECG Datasets}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S1746809420303323}, volume = {63}, year = {2021} }
@article{Wehbe2021, abstract = {Background: There are characteristic findings of coronavirus disease 2019 (COVID-19) on chest images. An artificial intelligence (AI) algorithm to detect COVID-19 on chest radiographs might be useful for triage or infection control within a hospital setting, but prior reports have been limited by small data sets, poor data quality, or both. Purpose: To present DeepCOVID-XR, a deep learning AI algorithm to detect COVID-19 on chest radiographs, that was trained and tested on a large clinical data set. Materials and Methods: DeepCOVID-XR is an ensemble of convolutional neural networks developed to detect COVID-19 on frontal chest radiographs, with reverse-transcription polymerase chain reaction test results as the reference standard. The algorithm was trained and validated on 14 788 images (4253 positive for COVID-19) from sites across the Northwestern Memorial Health Care System from February 2020 to April 2020 and was then tested on 2214 images (1192 positive for COVID-19) from a single holdout institution. Performance of the algorithm was compared with interpretations from five experienced thoracic radiologists on 300 random test images using the McNemar test for sensitivity and specificity and the DeLong test for the area under the receiver operating characteristic curve (AUC). Results: A total of 5853 patients (mean age, 58 years 6 19 [standard deviation]; 3101 women) were evaluated across data sets. For the entire test set, accuracy of DeepCOVID-XR was 83%, with an AUC of 0.90. For 300 random test images (134 positive for COVID-19), accuracy of DeepCOVID-XR was 82%, compared with that of individual radiologists (range, 76%–81%) and the consensus of all five radiologists (81%). DeepCOVID-XR had a significantly higher sensitivity (71%) than one radiologist (60%, P , .001) and significantly higher specificity (92%) than two radiologists (75%, P , .001; 84%, P = .009). AUC of DeepCOVID-XR was 0.88 compared with the consensus AUC of 0.85 (P = .13 for comparison). With consensus interpretation as the reference standard, the AUC of DeepCOVID-XR was 0.95 (95% CI: 0.92, 0.98). Conclusion: DeepCOVID-XR, an artificial intelligence algorithm, detected coronavirus disease 2019 on chest radiographs with a performance similar to that of experienced thoracic radiologists in consensus.}, annote = {doi: 10.1148/radiol.2020203511}, author = {Wehbe, Ramsey M. and Sheng, Jiayue and Dutta, Shinjan and Chai, Siyuan and Dravid, Amil and Barutcu, Semih and Wu, Yunan and Cantrell, Donald R. and Xiao, Nicholas and Allen, Bradley D. and MacNealy, Gregory A. and Savas, Hatice and Agrawal, Rishi and Parekh, Nishant and Katsaggelos, Aggelos K.}, doi = {10.1148/radiol.2020203511}, issn = {0033-8419}, journal = {Radiology}, month = {apr}, number = {1}, pages = {E167--E176}, pmid = {33231531}, publisher = {Radiological Society of North America}, title = {{DeepCOVID-XR: An Artificial Intelligence Algorithm to Detect COVID-19 on Chest Radiographs Trained and Tested on a Large U.S. Clinical Data Set}}, url = {https://doi.org/10.1148/radiol.2020203511 http://pubs.rsna.org/doi/10.1148/radiol.2020203511}, volume = {299}, year = {2021} }
@article{besson2021geometric, abstract = {The complex relationship between the shape and function of the human brain remains elusive despite extensive studies of cortical folding over many decades. The analysis of cortical gyrification presents an opportunity to advance our knowledge about this relationship, and better understand the etiology of a variety of pathologies involving diverse degrees of cortical folding abnormalities. Hypothesis-driven surface-based approaches have been shown to be particularly efficient in their ability to accurately describe unique features of the folded sheet topology of the cortical ribbon. However, the utility of these approaches has been blunted by their reliance on manually defined features aiming to capture the relevant geometric properties of cortical folding. In this paper, we propose an entirely novel, data-driven deep-learning based method to analyze the brain's shape that eliminates this reliance on manual feature definition. This method builds on the emerging field of geometric deep-learning and uses traditional convolutional neural network architecture uniquely adapted to the surface representation of the cortical ribbon. This method is a complete departure from prior brain MRI CNN investigations, all of which have relied on three dimensional MRI data and interpreted features of the MRI signal for prediction. MRI data from 6410 healthy subjects obtained from 11 publicly available data repositories were used for analysis. Ages ranged from 6 to 89 years. Both inner and outer cortical surfaces were extracted using Freesurfer and then registered into MNI space. For purposes of method development, both a classification and regression challenge were introduced for network learning including sex and age prediction, respectively. Two independent graph convolutional neural networks (gCNNs) were trained, the first of which to predict subject's self-identified sex, the second of which to predict subject's age. Class Activation Maps (CAM) and Regression Activation Maps (RAM) were constructed respectively to map the topographic distribution of the most influential brain regions involved in the decision process for each gCNN. Using this approach, the gCNN was able to predict a subject's sex with an average accuracy of 87.99 % and achieved a Person's coefficient of correlation of 0.93 with an average absolute error 4.58 years when predicting a subject's age. We believe this shape-based convolutional classifier offers a novel, data-driven approach to define biomedically relevant features from the brain at both the population and single subject levels and therefore lays a critical foundation for future precision medicine applications.}, author = {Besson, Pierre and Parrish, Todd and Katsaggelos, Aggelos K. and Bandt, S. Kathleen}, doi = {10.1016/j.compmedimag.2021.101939}, issn = {08956111}, journal = {Computerized Medical Imaging and Graphics}, keywords = {Big data,Brain mapping,Brain shape,Geometric deep learning,Population health,Precision medicine}, month = {jul}, pages = {101939}, pmid = {34082280}, publisher = {Pergamon}, title = {{Geometric deep learning on brain shape predicts sex and age}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S0895611121000884}, volume = {91}, year = {2021} }
@article{Henry2021, abstract = {In this paper, we propose EveRestNet, a convolutional neural network designed to remove blocking artifacts in videostreams using events from neuromorphic sensors. We first degrade the video frame using a quadtree structure to produce the blocking artifacts to simulate transmitting a video under a heavily constrained bandwidth. Events from the neuromorphic sensor are also simulated, but are transmitted in full. Using the distorted frames and the event stream, EveRestNet is able to improve the image quality.}, archivePrefix = {arXiv}, arxivId = {2105.05973}, author = {Chopp, Henry H. and Banerjee, Srutarshi and Cossairt, Oliver and Katsaggelos, Aggelos K.}, eprint = {2105.05973}, journal = {arXiv preprint arXiv:2105.05973}, month = {may}, title = {{Removing Blocking Artifacts in Video Streams Using Event Cameras}}, url = {http://arxiv.org/abs/2105.05973}, year = {2021} }
@article{Siddharth2021, abstract = {The observation of gravitational waves is hindered by the presence of transient noise (glitches). We study data from the third observing run of the Advanced LIGO detectors, and identify new glitch classes: fast scattering/crown and low-frequency blips. Using training sets assembled by monitoring of the state of the detector, and by citizen-science volunteers, we update the Gravity Spy machine-learning algorithm for glitch classification. We find that fast scattering/crown, linked to ground motion at the detector sites, is especially prevalent, and identify two subclasses linked to different types of ground motion. Reclassification of data based on the updated model finds that ∼27% of all transient noise at LIGO Livingston belongs to the fast scattering class, while ∼8% belongs to the low-frequency blip class, making them the most frequent and fourth most frequent sources of transient noise at that site. Our results demonstrate both how glitch classification can reveal potential improvements to gravitational-wave detectors, and how, given an appropriate framework, citizen-science volunteers may make discoveries in large data sets.}, archivePrefix = {arXiv}, arxivId = {2103.12104}, author = {Soni, S. and Berry, C P L and Coughlin, S. B. and Harandi, M. and Jackson, C. B. and Crowston, K. and {\O}sterlund, C and Patane, O. and Katsaggelos, A. K. and Trouille, L. and Baranowski, V-G and Domainko, W. F. and Kaminski, K. and Rodriguez, M A Lobato and Marciniak, U. and Nauta, P. and Niklasch, G. and Rote, R. R. and T{\'{e}}gl{\'{a}}s, B. and Unsworth, C. and Zhang, C.}, doi = {10.1088/1361-6382/ac1ccb}, eprint = {2103.12104}, issn = {0264-9381}, journal = {Classical and Quantum Gravity}, keywords = {LIGO,machine learning,neural network,noise classification,transient noise}, month = {oct}, number = {19}, pages = {195016}, title = {{Discovering features in gravitational-wave data through detector characterization, citizen science and machine learning}}, url = {https://iopscience.iop.org/article/10.1088/1361-6382/ac1ccb}, volume = {38}, year = {2021} }
@article{Peiqi2021, abstract = {Many visual and robotics tasks in real-world scenarios rely on robust handling of high speed motion and high dynamic range (HDR) with effectively high spatial resolution and low noise. Such stringent requirements, however, cannot be directly satisfied by a single imager or imaging modality, rather by multi-modal sensors with complementary advantages. In this paper, we address high performance imaging by exploring the synergy between traditional frame-based sensors with high spatial resolution and low sensor noise, and emerging event-based sensors with high speed and high dynamic range. We introduce a novel computational framework, termed Guided Event Filtering (GEF), to process these two streams of input data and output a stream of super-resolved yet noise-reduced events. To generate high quality events, GEF first registers the captured noisy events onto the guidance image plane according to our flow model. it then performs joint image filtering that inherits the mutual structure from both inputs. Lastly, GEF re-distributes the filtered event frame in the space-time volume while preserving the statistical characteristics of the original events. When the guidance images under-perform, GEF incorporates an event self-guiding mechanism that resorts to neighbor events for guidance. We demonstrate the benefits of GEF by applying the output high quality events to existing event-based algorithms across diverse application categories, including high speed object tracking, depth estimation, high frame-rate video synthesis, and super resolution/HDR/color image restoration.}, author = {Duan, Peiqi and Wang, Zihao and Shi, Boxin and Cossairt, Oliver and Huang, Tiejun and Katsaggelos, Aggelos}, doi = {10.1109/TPAMI.2021.3113344}, issn = {0162-8828}, journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence}, keywords = {Computational hybrid cameras,event-based imaging and vision,joint filtering}, number = {11}, pages = {1--1}, pmid = {34543190}, title = {{Guided Event Filtering: Synergy between Intensity Images and Neuromorphic Events for High Performance Imaging}}, url = {https://ieeexplore.ieee.org/document/9541050/}, volume = {44}, year = {2021} }
@article{bae2019transfer, abstract = {Dementia of Alzheimer's type (DAT) is associated with devastating and irreversible cognitive decline. Predicting which patients with mild cognitive impairment (MCI) will progress to DAT is an ongoing challenge in the field. We developed a deep learning model to predict conversion from MCI to DAT. Structural magnetic resonance imaging scans were used as input to a 3-dimensional convolutional neural network. The 3-dimensional convolutional neural network was trained using transfer learning; in the source task, normal control and DAT scans were used to pretrain the model. This pretrained model was then retrained on the target task of classifying which MCI patients converted to DAT. Our model resulted in 82.4% classification accuracy at the target task, outperforming current models in the field. Next, we visualized brain regions that significantly contribute to the prediction of MCI conversion using an occlusion map approach. Contributory regions included the pons, amygdala, and hippocampus. Finally, we showed that the model's prediction value is significantly correlated with rates of change in clinical assessment scores, indicating that the model is able to predict an individual patient's future cognitive decline. This information, in conjunction with the identified anatomical features, will aid in building a personalized therapeutic strategy for individuals with MCI.}, author = {Bae, Jinhyeong and Stocks, Jane and Heywood, Ashley and Jung, Youngmoon and Jenkins, Lisanne and Hill, Virginia and Katsaggelos, Aggelos and Popuri, Karteek and Rosen, Howie and Beg, M. Faisal and Wang, Lei}, doi = {10.1016/j.neurobiolaging.2020.12.005}, issn = {01974580}, journal = {Neurobiology of Aging}, keywords = {Convolutional neural network,Dementia of Alzheimer's type,Magnetic resonance imaging,Mild cognitive impairment,Predictive modeling}, month = {mar}, pages = {53--64}, pmid = {33422894}, publisher = {Cold Spring Harbor Laboratory}, title = {{Transfer learning for predicting conversion from mild cognitive impairment to dementia of Alzheimer's type based on a three-dimensional convolutional neural network}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S0197458020304140}, volume = {99}, year = {2021} }
@article{Fernando2021, abstract = {Background and Objective:Color variations in digital histopathology severely impact the performance of computer-aided diagnosis systems. They are due to differences in the staining process and acquisition system, among other reasons. Blind color deconvolution techniques separate multi-stained images into single stained bands which, once normalized, can be used to eliminate these negative color variations and improve the performance of machine learning tasks. Methods:In this work, we decompose the observed RGB image in its hematoxylin and eosin components. We apply Bayesian modeling and inference based on the use of Super Gaussian sparse priors for each stain together with prior closeness to a given reference color-vector matrix. The hematoxylin and eosin components are then used for image normalization and classification of histological images. The proposed framework is tested on stain separation, image normalization, and cancer classification problems. The results are measured using the peak signal to noise ratio, normalized median intensity and the area under ROC curve on five different databases. Results:The obtained results show the superiority of our approach to current state-of-the-art blind color deconvolution techniques. In particular, the fidelity to the tissue improves 1,27 dB in mean PSNR. The normalized median intensity shows a good normalization quality of the proposed approach on the tested datasets. Finally, in cancer classification experiments the area under the ROC curve improves from 0.9491 to 0.9656 and from 0.9279 to 0.9541 on Camelyon-16 and Camelyon-17, respectively, when the original and processed images are used. Furthermore, these figures of merits are better than those obtained by the methods compared with. Conclusions:The proposed framework for blind color deconvolution, normalization and classification of images guarantees fidelity to the tissue structure and can be used both for normalization and classification. In addition, color deconvolution enables the use of the optical density space for classification, which improves the classification performance.}, author = {P{\'{e}}rez-Bueno, Fernando and Vega, Miguel and Sales, Mar{\'{i}}a A. and Aneiros-Fern{\'{a}}ndez, Jos{\'{e}} and Naranjo, Valery and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1016/j.cmpb.2021.106453}, issn = {01692607}, journal = {Computer Methods and Programs in Biomedicine}, keywords = {Blind color deconvolution,Histopathological images,Image normalization,Super Gaussian,Variational bayes}, month = {nov}, pages = {106453}, pmid = {34649072}, title = {{Blind color deconvolution, normalization, and classification of histological images using general super Gaussian priors and Bayesian inference}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S0169260721005277}, volume = {211}, year = {2021} }
@article{cheimariotis2021automatic, abstract = {Intravascular Optical Coherence Tomography (IVOCT) images provide important insight into every aspect of atherosclerosis. Specifically, the extent of plaque and its type, which are indicative of the patient's condition, are better assessed by OCT images in comparison to other in vivo modalities. A large amount of imaging data per patient require automatic methods for rapid results. An effective step towards automatic plaque detection and plaque characterization is axial lines (A-lines) based classification into normal and various plaque types. In this work, a novel automatic method for A-line classification is proposed. The method employed convolutional neural networks (CNNs) for classification in its core and comprised the following pre-processing steps: arterial wall segmentation and an OCT-specific (depth-resolved) transformation and a post-processing step based on the majority of classifications. The important step was the OCT-specific transformation, which was based on the estimation of the attenuation coefficient in every pixel of the OCT image. The dataset used for training and testing consisted of 183 images from 33 patients. In these images, four different plaque types were delineated. The method was evaluated by cross-validation. The mean values of accuracy, sensitivity and specificity were 74.73%, 87.78%, and 61.45%, respectively, when classifying into plaque and normal A-lines. When plaque A-lines were classified into fibrolipidic and fibrocalcific, the overall accuracy was 83.47% for A-lines of OCT-specific transformed images and 74.94% for A-lines of original images. This large improvement in accuracy indicates the advantage of using attenuation coefficients when characterizing plaque types. The proposed automatic deep-learning pipeline constitutes a positive contribution to the accurate classification of A-lines in intravascular OCT images.}, author = {Cheimariotis, Grigorios-Aris and Riga, Maria and Haris, Kostas and Toutouzas, Konstantinos and Katsaggelos, Aggelos K. and Maglaveras, Nicos}, doi = {10.3390/app11167412}, issn = {2076-3417}, journal = {Applied Sciences}, keywords = {Atheromatic plaque,CNN,Classification,Deep learning,Intravascular optical coherence tomography}, month = {aug}, number = {16}, pages = {7412}, publisher = {MDPI}, title = {{Automatic Classification of A-Lines in Intravascular OCT Images Using Deep Learning and Estimation of Attenuation Coefficients}}, url = {https://www.mdpi.com/2076-3417/11/16/7412}, volume = {11}, year = {2021} }
@article{Srutarshi2021a, abstract = {We present a novel adaptive multi-modal intensity-event algorithm to optimize an overall objective of object tracking under bit rate constraints for a host-chip architecture. The chip is a computationally resource constrained device acquiring high resolution intensity frames and events, while the host is capable of performing computationally expensive tasks. We develop a joint intensity-neuromorphic event rate-distortion compression framework with a quadtree (QT) based compression of intensity and events scheme. The data acquisition on the chip is driven by the presence of objects of interest in the scene as detected by an object detector. The most informative intensity and event data are communicated to the host under rate constraints, so that the best possible tracking performance is obtained. The detection and tracking of objects in the scene are done on the distorted data at the host. Intensity and events are jointly used in a fusion framework to enhance the quality of the distorted images, so as to improve the object detection and tracking performance. The performance assessment of the overall system is done in terms of the multiple object tracking accuracy (MOTA) score. Compared to using intensity modality only, there is an improvement in MOTA using both these modalities in different scenarios.}, archivePrefix = {arXiv}, arxivId = {2105.14164}, author = {Banerjee, Srutarshi and Chopp, Henry H and Zhang, Jianping and Wang, Zihao W and Cossairt, Oliver and Katsaggelos, Aggelos}, eprint = {2105.14164}, isbn = {2105.14164v1}, journal = {arXiv preprint arXiv:2105.14164}, keywords = {Compressed domain object detection and tracking,Dynamic Program-ming,Index Terms-Joint Intensity-Event Imaging System,Joint Intensity-Event Rate Distortion Optimization}, month = {may}, title = {{A Joint Intensity-Neuromorphic Event Imaging System for Resource Constrained Devices}}, url = {http://arxiv.org/abs/2105.14164}, year = {2021} }
@article{Daming2021, abstract = {Highly accelerated real-time cine MRI using compressed sensing (CS) is a promising approach to achieve high spatio-temporal resolution and clinically acceptable image quality in patients with arrhythmia and/or dyspnea. However, its lengthy image reconstruction time may hinder its clinical translation. The purpose of this study was to develop a neural network for reconstruction of non-Cartesian real-time cine MRI k-space data faster (<1 min per slice with 80 frames) than graphics processing unit (GPU)-accelerated CS reconstruction, without significant loss in image quality or accuracy in left ventricular (LV) functional parameters. We introduce a perceptual complex neural network (PCNN) that trains on complex-valued MRI signal and incorporates a perceptual loss term to suppress incoherent image details. This PCNN was trained and tested with multi-slice, multi-phase, cine images from 40 patients (20 for training, 20 for testing), where the zero-filled images were used as input and the corresponding CS reconstructed images were used as practical ground truth. The resulting images were compared using quantitative metrics (structural similarity index (SSIM) and normalized root mean square error (NRMSE)) and visual scores (conspicuity, temporal fidelity, artifacts, and noise scores), individually graded on a five-point scale (1, worst; 3, acceptable; 5, best), and LV ejection fraction (LVEF). The mean processing time per slice with 80 frames for PCNN was 23.7 ± 1.9 s for pre-processing (Step 1, same as CS) and 0.822 ± 0.004 s for dealiasing (Step 2, 166 times faster than CS). Our PCNN produced higher data fidelity metrics (SSIM = 0.88 ± 0.02, NRMSE = 0.014 ± 0.004) compared with CS. While all the visual scores were significantly different (P < 0.05), the median scores were all 4.0 or higher for both CS and PCNN. LVEFs measured from CS and PCNN were strongly correlated (R2 = 0.92) and in good agreement (mean difference = −1.4% [2.3% of mean]; limit of agreement = 10.6% [17.6% of mean]). The proposed PCNN is capable of rapid reconstruction (25 s per slice with 80 frames) of non-Cartesian real-time cine MRI k-space data, without significant loss in image quality or accuracy in LV functional parameters.}, author = {Shen, Daming and Ghosh, Sushobhan and Haji‐Valizadeh, Hassan and Pathrose, Ashitha and Schiffers, Florian and Lee, Daniel C. and Freed, Benjamin H. and Markl, Michael and Cossairt, Oliver S. and Katsaggelos, Aggelos K. and Kim, Daniel}, doi = {10.1002/nbm.4405}, issn = {0952-3480}, journal = {NMR in Biomedicine}, keywords = {compressed sensing (CS),convolutional neural network (CNN),deep learning (DL),perceptual complex neural network (PCNN),perceptual loss,real-time cine MRI}, month = {jan}, number = {1}, pages = {e4405}, pmid = {32875668}, title = {{Rapid reconstruction of highly undersampled, non‐Cartesian real‐time cine k ‐space data using a perceptual complex neural network (PCNN)}}, url = {https://onlinelibrary.wiley.com/doi/10.1002/nbm.4405}, volume = {34}, year = {2021} }
@article{Emanuel2021, abstract = {Several patterns of atrophy have been identified and strongly related to Alzheimer's disease (AD) pathology and its progression. Morphological changes in brain shape have been identified up to ten years before clinical diagnoses of AD, making its early detection more relevant. We propose novel geometric deep learning frameworks for the analysis of brain shape in the context of neurodegeneration caused by AD. Our deep neural networks learn low-dimensional shape descriptors of multiple neuroanatomical structures, instead of handcrafted features for each structure. A discriminative network using spiral convolution on 3D meshes is constructed for the in-vivo binary classification of AD from healthy controls (HCs) using a fast and efficient "spiral" convolution operator on 3D triangular mesh surfaces of human brain subcortical structures extracted from T1-weighted magnetic resonance imaging (MRI). Our network architecture consists of modular learning blocks using residual connections to improve overall classi-fier performance. In this work: (1) a discriminative network is used to analyze the efficacy of disease classification using input data from multiple brain structures and compared to using a single hemisphere or a single structure. It also outperforms prior work using spectral graph convolution on the same the same tasks, as well as alternative methods that operate on intermediate point cloud representations of 3D shapes. (2) Additionally, visual interpretations for regions on the surface of brain structures that are associated to true positive AD predictions are generated and fall in accordance with the current reports on the structural localization of pathological changes associated to AD. (3) A conditional generative network is also implemented to analyze the effects of phenotypic priors given to the model (i.e. AD diagnosis) in generating subcortical structures. The generated surface meshes by our model indicate learned morphological differences in the presence of AD that agrees with the current literature on patterns of atrophy associated to the disease. In particular, our inference results demonstrate an overall reduction in subcortical mesh volume and surface area in the presence of AD, especially in the hippocampus. The low-dimensional shape descriptors obtained by our generative model are also evaluated in our discriminative baseline comparisons versus our discriminative network and the alternative shape-based approaches.}, author = {Azcona, Emanuel A and Besson, Pierre and Wu, Yunan and Kurani, Ajay S and {Kathleen Bandt}, S and Parrish, Todd B and Katsaggelos, Aggelos K}, doi = {https://doi.org/10.1101/2021.04.15.440008}, journal = {bioRxiv}, keywords = {geometric deep learning,graph convolutional networks,neuroscience,shape analysis}, pages = {2004--2021 , publisher = Cold Spring Harbor Laborat}, title = {{Analyzing Brain Morphology in Alzheimer's Disease Using Discriminative and Generative Spiral Networks}}, url = {https://doi.org/10.1101/2021.04.15.440008}, year = {2021} }
@article{Xin2021, abstract = {Capturing high-dimensional (HD) data is a long-term challenge in signal processing and related fields. Snapshot compressive imaging (SCI) uses a 2D detector to capture HD (≥3D) data in a snapshot measurement. Via novel optical designs, the 2D detector samples the HD data in a compressive manner; following this, algorithms are employed to reconstruct the desired HD data cube. SCI has been used in hyperspectral imaging, video, holography, tomography, focal depth imaging, polarization imaging, microscopy, and so on. Although the hardware has been investigated for more than a decade, the theoretical guarantees have only recently been derived. Inspired by deep learning, various deep neural networks have also been developed to reconstruct the HD data cube in spectral SCI and video SCI. This article reviews recent advances in SCI hardware, theory, and algorithms, including both optimizationbased and deep learning-based algorithms. Diverse applications and the outlook for SCI are also discussed.}, author = {Yuan, Xin and Brady, David J. and Katsaggelos, Aggelos K.}, doi = {10.1109/MSP.2020.3023869}, issn = {1053-5888}, journal = {IEEE Signal Processing Magazine}, month = {mar}, number = {2}, pages = {65--88}, title = {{Snapshot Compressive Imaging: Theory, Algorithms, and Applications}}, url = {https://ieeexplore.ieee.org/document/9363502/}, volume = {38}, year = {2021} }
@article{Santiago2021a, abstract = {Wetlands serve many important ecosystem services, yet the United States lacks up-to-date, high-resolution wetland inventories. New, automated techniques for developing wetland segmentation maps from high-resolution aerial imagery can improve our understanding of the location and amount of wetlands. We assembled training and testing data sets (patch sizes of 28 × 28 m2 and 56 × 56 m2) of high-resolution aerial imagery of wetlands using Illinois Natural History Survey wetland location data and National Agricultural Imagery Project data. Each patch was labeled as wetland or non-wetland. To augment these data sets with additional information, we incorporated digital surface and digital terrain models and topographic wetness index data in the same two patch sizes. Subsequently, we evaluated convolutional neural network (CNN) and Gaussian process-based machine learning methods to produce wetland segmentation maps. We developed the best performing method into a new CNN algorithm, WetSegNet. It exhibited an area under the curve of 98% when used with 56 × 56 m2 patch sizes. WetSegNet developed reliable wetland segmentation maps in test cases in which wetlands would have gone undetected using only the National Land Cover Database. The development of WetSegNet exemplifies the types of data sets and methods that are needed to accelerate the use of high-resolution aerial imagery towards an improved understanding of wetlands. This algorithm could be used by state and federal agencies or other groups to identify wetlands with higher accuracy and at a finer scale than previously possible.}, author = {L{\'{o}}pez-Tapia, Santiago and Ruiz, Pablo and Smith, Mitchell and Matthews, Jeffrey and Zercher, Bradley and Sydorenko, Liliana and Varia, Neelanshi and Jin, Yuanzhe and Wang, Minzi and Dunn, Jennifer B. and Katsaggelos, Aggelos K.}, doi = {10.1016/j.jag.2021.102581}, issn = {15698432}, journal = {International Journal of Applied Earth Observation and Geoinformation}, keywords = {High-resolution aerial imagery,Machine learning,Neural networks,Segmentation,Wetland}, month = {dec}, pages = {102581}, title = {{Machine learning with high-resolution aerial imagery and data fusion to improve and automate the detection of wetlands}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S0303243421002889}, volume = {105}, year = {2021} }
@article{Emeline2020, abstract = {A new portable macro X-ray fluorescence scanner has been specifically designed for in situ, real-time elemental mapping of large painted surfaces. This system allows scanning 80 × 80 × 20 cm3 along the X, Z, and Y directions, respectively, with adaptive beam size at the energy of the Rh Ka-line. The detection system consists of a 50 mm2 active area detector coupled to a CUBE pre-amplifier and to the DANTE digital pulse processor (DPP) with adaptive shaping time. The system is controlled with a custom software including a graphical user interface (GUI) programmed in Python for real-time control of the stage, DPP, and camera of the scanner. This system allows considering new ways of sampling the object surface than the usual raster scanning in serpentine as well as a live elaboration of X-ray data; technical details and performances of the scanner are presented in this paper together with an example of its application to investigate painted surface, illustrating the value of the developed instrument.}, author = {Pouyet, Emeline and Barbi, Nicholas and Chopp, Henry and Healy, Owen and Katsaggelos, Aggelos and Moak, Sophia and Mott, Rick and Vermeulen, Marc and Walton, Marc}, doi = {10.1002/xrs.3173}, issn = {0049-8246}, journal = {X-Ray Spectrometry}, month = {aug}, number = {4}, pages = {263--271}, title = {{Development of a highly mobile and versatile large MA‐XRF scanner for in situ analyses of painted work of arts}}, url = {https://onlinelibrary.wiley.com/doi/10.1002/xrs.3173}, volume = {50}, year = {2021} }
@article{Sidi2021, abstract = {We apply reinforcement learning to video compressive sensing to adapt the compression ratio. Specifically, video snapshot compressive imaging (SCI), which captures high-speed video using a low-speed camera is considered in this work, in which multiple (B) video frames can be reconstructed from a snapshot measurement. One research gap in previous studies is how to adapt B in the video SCI system for different scenes. In this paper, we fill this gap utilizing reinforcement learning (RL). An RL model, as well as various convolutional neural networks for reconstruction, are learned to achieve adaptive sensing of video SCI systems. Furthermore, the performance of an object detection network using directly the video SCI measurements without reconstruction is also used to perform RL-based adaptive video compressive sensing. Our proposed adaptive SCI method can thus be implemented in low cost and real time. Our work takes the technology one step further towards real applications of video SCI.}, archivePrefix = {arXiv}, arxivId = {2105.08205}, author = {Lu, Sidi and Yuan, Xin and Katsaggelos, Aggelos K and Shi, Weisong}, eprint = {2105.08205}, journal = {arXiv preprint arXiv:2105.08205}, month = {may}, title = {{Reinforcement Learning for Adaptive Video Compressive Sensing}}, url = {http://arxiv.org/abs/2105.08205}, year = {2021} }
@article{Miguel2021, abstract = {The volume of labeled data is often the primary determinant of success in developing machine learning algorithms. This has increased interest in methods for leveraging crowds to scale data labeling efforts, and methods to learn from noisy crowd-sourced labels. The need to scale labeling is acute but particularly challenging in medical applications like pathology, due to the expertise required to generate quality labels and the limited availability of qualified experts. In this paper we investigate the application of Scalable Variational Gaussian Processes for Crowdsourcing (SVGPCR) in digital pathology. We compare SVGPCR with other crowdsourcing methods using a large multi-rater dataset where pathologists, pathology residents, and medical students annotated tissue regions breast cancer. Our study shows that SVGPCR is competitive with equivalent methods trained using gold-standard pathologist generated labels, and that SVGPCR meets or exceeds the performance of other crowdsourcing methods based on deep learning. We also show how SVGPCR can effectively learn the class-conditional reliabilities of individual annotators and demonstrate that Gaussian-process classifiers have comparable performance to similar deep learning methods. These results suggest that SVGPCR can meaningfully engage non-experts in pathology labeling tasks, and that the class-conditional reliabilities estimated by SVGPCR may assist in matching annotators to tasks where they perform well.}, author = {L{\'{o}}pez-P{\'{e}}rez, Miguel and Amgad, Mohamed and Morales-{\'{A}}lvarez, Pablo and Ruiz, Pablo and Cooper, Lee A. D. and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1038/s41598-021-90821-3}, issn = {2045-2322}, journal = {Scientific Reports}, month = {jun}, number = {1}, pages = {11612}, pmid = {34078955}, title = {{Learning from crowds in digital pathology using scalable variational Gaussian processes}}, url = {https://www.nature.com/articles/s41598-021-90821-3}, volume = {11}, year = {2021} }
@article{barutcu2021limited, abstract = {Computed tomography is a well-established x-ray imaging technique to reconstruct the three-dimensional structure of objects. It has been used extensively in a variety of fields, from diagnostic imaging to materials and biological sciences. One major challenge in some applications, such as in electron or x-ray tomography systems, is that the projections cannot be gathered over all the angles due to the sample holder setup or shape of the sample. This results in an ill-posed problem called the limited angle reconstruction problem. Typical image reconstruction in this setup leads to distortion and artifacts, thereby hindering a quantitative evaluation of the results. To address this challenge, we use a generative model to effectively constrain the solution of a physics-based approach. Our approach is self-training that can iteratively learn the nonlinear mapping from partial projections to the scanned object. Because our approach combines the data likelihood and image prior terms into a single deep network, it is computationally tractable and improves performance through an end-to-end training. We also complement our approach with total-variation regularization to handle high-frequency noise in reconstructions and implement a solver based on alternating direction method of multipliers. We present numerical results for various degrees of missing angle range and noise levels, which demonstrate the effectiveness of the proposed approach.}, author = {Barutcu, Semih and Aslan, Selin and Katsaggelos, Aggelos K. and G{\"{u}}rsoy, Doğa}, doi = {10.1038/s41598-021-97226-2}, issn = {2045-2322}, journal = {Scientific Reports}, month = {sep}, number = {1}, pages = {17740}, pmid = {34489500}, publisher = {Nature Publishing Group UK London}, title = {{Limited-angle computed tomography with deep image and physics priors}}, url = {https://www.nature.com/articles/s41598-021-97226-2}, volume = {11}, year = {2021} }
@article{KyungPyo2021, abstract = {Objective. To accelerate compressed sensing (CS) reconstruction of subsampled radial k-space data using a geometrically-derived density compensation function (gDCF) without significant loss in image quality. Approach. We developed a theoretical framework to calculate a gDCF based on Nyquist distance along the radial and circumferential directions of a discrete polar coordinate system. Our gDCF was compared against standard DCF (e.g. ramp filter) and another commonly used DCF (modified Shepp-Logan (SL) filter). The resulting image quality produced by each DCF was quantified using normalized root-mean-square-error (NRMSE), blur metric (1 = blurriest; 0 = sharpest), and structural similarity index (SSIM; 1 = perfect match; 0 = no match) compared with the reference. For filtered backprojection (FBP) of phantom data obtained at the Nyquist sampling rate, Cartesian k-space sampling was used as the reference. For CS reconstruction of subsampled cardiac magnetic resonance imaging datasets (real-time cardiac cine data with 11 projections per frame, n = 20 patients; cardiac perfusion data with 30 projections per frame, n = 19 patients), CS reconstruction without DCF was used as the reference. Main results. The NRMSE, SSIM, and blur metrics of the phantom data were good for all DCFs, confirming that our gDCF produces uniform densities at the upper limit (Nyquist). For CS reconstruction of subsampled real-time cine and cardiac perfusion datasets, the image quality metrics (SSIM, NRMSE) were significantly (p < 0.05) higher for our gDCF than other DCFs, and the reconstruction time was significantly (p < 0.05) faster for our gDCF (reference) than no DCF (11.9%-52.9% slower), standard DCF (23.9%-57.6% slower), and modified SL filter (13.5%-34.8% slower). Significance. The proposed gDCF accelerates CS reconstruction of subsampled radial k-space data without significant loss in image quality compared with no DCF as the reference.}, author = {Hong, KyungPyo and Schiffers, Florian and DiCarlo, Amanda L. and Rigsby, Cynthia K. and Haji-Valizadeh, Hassan and Lee, Daniel C. and Markl, Michael and Katsaggelos, Aggelos K. and Kim, Daniel}, doi = {10.1088/1361-6560/ac2c9d}, issn = {0031-9155}, journal = {Physics in Medicine & Biology}, keywords = {Compressed sensing,Density compensation,Filtered backprojection,Image reconstruction,MRI,Radial k-space sampling}, month = {nov}, number = {21}, pages = {21NT01}, title = {{Accelerating compressed sensing reconstruction of subsampled radial k-space data using geometrically-derived density compensation}}, url = {https://iopscience.iop.org/article/10.1088/1361-6560/ac2c9d}, volume = {66}, year = {2021} }
@article{Santiago2021, abstract = {In recent years, deep learning-based models have gained momentum in imaging problems such as image and video super-resolution, image restoration or inpainting. The analytical approaches that have traditionally been used to solve image inverse problems have started to be replaced by deep learning ones, being outperformed in terms of efficacy and efficiency in many applications. However, deep learning-based models lack the adaptability of analytical models, thus making them unsuitable for dealing simultaneously with different forward image formation models. In contrast to analytical methods, deep learning models typically do not use domain knowledge and rely on learning the solution to the inverse problem from large data sets. This is making them susceptible to errors caused by the presence of degradations not seen during training. Hybrid models combining analytical and deep learning approaches have been introduced to solve such generalization issues while retaining the efficacy of deep learning models. In this work, we review deep learning and hybrid methods for solving imaging inverse problems, focusing on image and video super-resolution and image restoration. Furthermore, we discuss open problems in this area that would be of critical importance in the future, the challenges of applying deep learning models to solve them, and how future research could address them.}, author = {L{\'{o}}pez-Tapia, Santiago and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1016/j.dsp.2021.103285}, issn = {10512004}, journal = {Digital Signal Processing}, keywords = {Convolutional neural network,Deep learning,Inverse imaging problems,Video super-resolution}, month = {dec}, pages = {103285}, title = {{Deep learning approaches to inverse problems in imaging: Past, present and future}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S1051200421003249}, volume = {119}, year = {2021} }
@article{Amil2021, author = {Amil, Dravid and Aggelos, K Katsaggelos}, title = {{Visual explanations for convolutional neural networks via latent traversal}}, year = {2021} }
@article{Kevin2019, abstract = {We present the design of a citizen science system that uses machine learning to guide the presentation of image classification tasks to newcomers to help them more quickly learn how to do the task while still contributing to the work of the project. A Bayesian model for tracking volunteer learning for training with tasks with uncertain outcomes is presented and fit to data from 12,986 volunteer contributors. The model can be used both to estimate the ability of volunteers and to decide the classification of an image. A simulation of the model applied to volunteer promotion and image retirement suggests that the model requires fewer classifications than the current system.}, author = {Crowston, Kevin and Osterlund, Carsten and Lee, Tae Kyoung and Jackson, Corey and Harandi, Mahboobeh and Allen, Sarah and Bahaadini, Sara and Coughlin, Scott and Katsaggelos, Aggelos K. and Larson, Shane L. and Rohani, Neda and Smith, Joshua R. and Trouille, Laura and Zevin, Michael}, doi = {10.1109/TLT.2019.2936480}, issn = {1939-1382}, journal = {IEEE Transactions on Learning Technologies}, keywords = {Citizen science,machine learning,training}, month = {jan}, number = {1}, pages = {123--134}, title = {{Knowledge Tracing to Model Learning in Online Citizen Science Projects}}, url = {https://ieeexplore.ieee.org/document/8812979/}, volume = {13}, year = {2020} }
@article{Kuan2020, abstract = {Light field microscopy (LFM) is an emerging technology for high-speed wide-field 3D imaging by capturing 4D light field of 3D volumes. However, its 3D imaging capability comes at a cost of lateral resolution. In addition, the lateral resolution is not uniform across depth in the light field dconvolution reconstructions. To address these problems, here, we propose a snapshot multifocal light field microscopy (MFLFM) imaging method. The underlying concept of the MFLFM is to collect multiple focal shifted light fields simultaneously. We show that by focal stacking those focal shifted light fields, the depth-of-field (DOF) of the LFM can be further improved but without sacrificing the lateral resolution. Also, if all differently focused light fields are utilized together in the deconvolution, the MFLFM could achieve a high and uniform lateral resolution within a larger DOF. We present a house-built MFLFM system by placing a diffractive optical element at the Fourier plane of a conventional LFM. The optical performance of the MFLFM are analyzed and given. Both simulations and proof-of-principle experimental results are provided to demonstrate the effectiveness and benefits of the MFLFM. We believe that the proposed snapshot MFLFM has potential to enable high-speed and high resolution 3D imaging applications.}, author = {He, Kuan and Wang, Xiaolei and Wang, Zihao W. and Yi, Hannah and Scherer, Norbert F. and Katsaggelos, Aggelos K. and Cossairt, Oliver}, doi = {10.1364/OE.390719}, issn = {1094-4087}, journal = {Optics Express}, month = {apr}, number = {8}, pages = {12108}, pmid = {32403711}, title = {{Snapshot multifocal light field microscopy}}, url = {https://opg.optica.org/abstract.cfm?URI=oe-28-8-12108}, volume = {28}, year = {2020} }
@article{Yunan2020, abstract = {Brain structure is tightly coupled with brain functions, but it remains unclear how cognition is related to brain morphology, and what is consistent across neurodevelopment. In this work, we developed graph convolutional neural networks (gCNNs) to predict Fluid Intelligence (Gf) from shapes of cortical ribbons and subcortical structures. T1-weighted MRIs from two independent cohorts, the Human Connectome Project (HCP; age: 28.81±3.70) and the Adolescent Brain Cognitive Development Study (ABCD; age: 9.93±0.62) were independently analyzed. Cortical and subcortical surfaces were extracted and modeled as surface meshes. Three gCNNs were trained and evaluated using six-fold nested cross-validation. Overall, combining cortical and subcortical surfaces yielded the best predictions on both HCP (R=0.454) and ABCD datasets (R=0.314), and outperformed the current literature. Across both datasets, the morphometry of the amygdala and hippocampus, along with temporal, parietal and cingulate cortex consistently drove the prediction of Gf, suggesting a novel reframing of the morphometry underlying Gf.. CC-BY 4.0 International license perpetuity. It is made available under a preprint (which was not certified by peer review) is the author/funder, who has granted bioRxiv a license to display the preprint in The copyright holder for this this version posted October 15, 2020. ; https://doi.}, author = {Wu, Yunan and Besson, Pierre and Azcona, Emanuel A and Bandt, S Kathleen and Parrish, Todd B and Breiter, Hans C and Katsaggelos, Aggelos K}, doi = {10.1101/2020.10.14.331199}, journal = {bioRxiv}, pages = {2020.10.14.331199}, title = {{Novel age-dependent cortico-subcortical morphologic interactions predict fluid intelligence: A multi-cohort geometric deep learning study Authors}}, url = {https://doi.org/10.1101/2020.10.14.331199}, year = {2020} }
@article{Alexis2020, abstract = {3D shape reconstruction is a primary component of augmented/virtual reality. Despite being highly advanced, existing solutions based on RGB, RGB-D and Lidar sensors are power and data intensive, which introduces challenges for deployment in edge devices. We approach 3D reconstruction with an event camera, a sensor with significantly lower power, latency and data expense while enabling high dynamic range. While previous event-based 3D reconstruction methods are primarily based on stereo vision, we cast the problem as multi-view shape from silhouette using a monocular event camera. The output from a moving event camera is a sparse point set of space-time gradients, largely sketching scene/object edges and contours. We first introduce an event-to-silhouette (E2S) neural network module to transform a stack of event frames to the corresponding silhouettes, with additional neural branches for camera pose regression. Second, we introduce E3D, which employs a 3D differentiable renderer (PyTorch3D) to enforce cross-view 3D mesh consistency and fine-tune the E2S and pose network. Lastly, we introduce a 3D-to-events simulation pipeline and apply it to publicly available object datasets and generate synthetic event/silhouette training pairs for supervised learning.}, archivePrefix = {arXiv}, arxivId = {2012.05214}, author = {Baudron, Alexis and Wang, Zihao W. and Cossairt, Oliver and Katsaggelos, Aggelos K.}, eprint = {2012.05214}, journal = {arXiv preprint arXiv:2012.05214}, month = {dec}, title = {{E3D: Event-Based 3D Shape Reconstruction}}, url = {http://arxiv.org/abs/2012.05214}, year = {2020} }
@article{Florian2020, abstract = {We introduce a system that exploits the screen and front-facing camera of a mobile device to perform three-dimensional deflectometry-based surface measurements. In contrast to current mobile deflectometry systems, our method can capture surfaces with large normal variation and wide field of view (FoV). We achieve this by applying automated multi-view panoramic stitching algorithms to produce a large FoV normal map from a hand-guided capture process without the need for external tracking systems, like robot arms or fiducials. The presented work enables 3D surface measurements of specular objects 'in the wild' with a system accessible to users with little to no technical imaging experience. We demonstrate high-quality 3D surface measurements without the need for a calibration procedure. We provide experimental results with our prototype Deflectometry system and discuss applications for computer vision tasks such as object detection and recognition.}, author = {Willomitzer, Florian and Yeh, Chia-Kai and Gupta, Vikas and Spies, William and Schiffers, Florian and Katsaggelos, Aggelos and Walton, Marc and Cossairt, Oliver}, doi = {10.1364/OE.383475}, issn = {1094-4087}, journal = {Optics Express}, month = {mar}, number = {7}, pages = {9027}, pmid = {32225516}, title = {{Hand-guided qualitative deflectometry with a mobile device}}, url = {https://opg.optica.org/abstract.cfm?URI=oe-28-7-9027}, volume = {28}, year = {2020} }
@article{Srutarshi2020, abstract = {With several advantages over conventional RGB cameras, event cameras have provided new opportunities for tackling visual tasks under challenging scenarios with fast motion, high dynamic range, and/or power constraint. Yet unlike image/video compression, the performance of event compression algorithm is far from satisfying and practical. The main challenge for compressing events is the unique event data form, i.e., a stream of asynchronously fired event tuples each encoding the 2D spatial location, timestamp, and polarity (denoting an increase or decrease in brightness). Since events only encode temporal variations, they lack spatial structure which is crucial for compression. To address this problem, we propose a novel event compression algorithm based on a quad tree (QT) segmentation map derived from the adjacent intensity images. The QT informs 2D spatial priority within the 3D space-time volume. In the event encoding step, events are first aggregated over time to form polarity-based event histograms. The histograms are then variably sampled via Poisson Disk Sampling prioritized by the QT based segmentation map. Next, differential encoding and run length encoding are employed for encoding the spatial and polarity information of the sampled events, respectively, followed by Huffman encoding to produce the final encoded events. Our Poisson Disk Sampling based Lossy Event Compression (PDS-LEC) algorithm performs rate-distortion based optimal allocation. On average, our algorithm achieves greater than 6x compression compared to the state of the art.}, archivePrefix = {arXiv}, arxivId = {2005.00974}, author = {Banerjee, Srutarshi and Wang, Zihao W. and Chopp, Henry H. and Cossairt, Oliver and Katsaggelos, Aggelos}, eprint = {2005.00974}, journal = {arXiv}, keywords = {Event cameras,Event-based vision,Image and video compression}, month = {may}, title = {{Lossy Event Compression based on Image-derived Quad Trees and Poisson Disk Sampling}}, url = {http://arxiv.org/abs/2005.00974}, year = {2020} }
@article{Florian2020a, abstract = {Imaging through scattering media finds applications in diverse fields from biomedicine to autonomous driving. However, interpreting the resulting images is difficult due to blur caused by the scattering of photons within the medium. Transient information, captured with fast temporal sensors, can be used to significantly improve the quality of images acquired in scattering conditions. Photon scattering, within a highly scattering media, is well modeled by the diffusion approximation of the Radiative Transport Equation (RTE). Its solution is easily derived which can be interpreted as a Spatio-Temporal Point Spread Function (ST-PSF). In this paper, we first discuss the properties of the ST-PSF and subsequently use this knowledge to simulate transient imaging through highly scattering media. We then propose a framework to invert the forward model, which assumes Poisson noise, to recover a noise-free, unblurred image by solving an optimization problem.}, author = {Schiffers, Florian and Fiske, Lionel and Ruiz, Pablo and Katsaggelos, Aggelos K. and Cossairt, Oliver}, doi = {10.2352/ISSN.2470-1173.2020.14.COIMG-306}, issn = {2470-1173}, journal = {Electronic Imaging}, month = {jan}, number = {14}, pages = {306--1--306--6}, title = {{Imaging through Scattering Media with a Learning Based Prior}}, url = {https://library.imaging.org/ei/articles/32/14/art00012}, volume = {32}, year = {2020} }
@article{Perez-Bueno2020, abstract = {In digital histopathological image analysis, two conflicting objectives are often pursued: closeness to the original tissue and high classification performance. The former objective tries to recover images (stains) that are as close as possible to the ones obtained by staining the tissue with a single dye. The latter objective requires images that allow the extraction of better features for an improved classification, even if their appearance is not close to single stained tissues. In this paper we propose a framework that achieves both objectives depending on the number of stains used to mathematically decompose the scanned image. The proposed framework uses a total variation prior for each stain together with the similarity to a given reference color-vector matrix. Variational inference and an evidence lower bound are utilized to automatically estimate all the latent variables and model parameters. The proposed methodology is tested on real images and compared to classical and state-of-the-art methods for histopathological blind image color deconvolution and prostate cancer classification.}, author = {P{\'{e}}rez-Bueno, Fernando and L{\'{o}}pez-P{\'{e}}rez, Miguel and Vega, Miguel and Mateos, Javier and Naranjo, Valery and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1016/j.dsp.2020.102727}, issn = {10512004}, journal = {Digital Signal Processing}, keywords = {Blind color deconvolution,Histopathological images,Prostate cancer,Variational Bayes}, month = {jun}, pages = {102727}, title = {{A TV-based image processing framework for blind color deconvolution and classification of histological images}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S1051200420300725}, volume = {101}, year = {2020} }
@article{Hassan2020, abstract = {Purpose: To implement an integrated reconstruction pipeline including a graphics processing unit (GPU)–based convolutional neural network (CNN) architecture and test whether it reconstructs four-dimensional non-Cartesian, non–contrast material–enhanced MR angiographic k-space data faster than a central processing unit (CPU)–based compressed sensing (CS) reconstruction pipeline, without significant losses in data fidelity, summed visual score (SVS), or arterial vessel–diameter measurements. Materials and Methods: Raw k-space data of 24 patients (18 men and six women; mean age, 56.8 years 6 11.8 [standard deviation]) suspected of having thoracic aortic disease were used to evaluate the proposed reconstruction pipeline derived from an open-source threedimensional CNN. For training, 4800 zero-filled images and the corresponding CS-reconstructed images from 10 patients were used as input-output pairs. For testing, 6720 zero-filled images from 14 different patients were used as inputs to a trained CNN. Metrics for evaluating the agreement between the CNN and CS images included reconstruction times, structural similarity index (SSIM) and normalized root-mean-square error (NRMSE), SVS (3 = nondiagnostic, 9 = clinically acceptable, 15 = excellent), and vessel diameters. Results: The mean reconstruction time was 65 times and 69 times shorter for the CPU-based and GPU-based CNN pipelines (216.6 seconds 6 40.5 and 204.9 seconds 6 40.5), respectively, than for CS (14 152.3 seconds 6 1708.6) (P, .001). Compared with CS as practical ground truth, CNNs produced high data fidelity (SSIM = 0.94 6 0.02, NRMSE = 2.8% 6 0.4) and not significantly different (P = .25) SVS and aortic diameters, except at one out of seven locations, where the percentage difference was only 3% (ie, clinically irrelevant). Conclusion: The proposed integrated reconstruction pipeline including a CNN architecture is capable of rapidly reconstructing timeresolved volumetric cardiovascular MRI k-space data, without a significant loss in data quality, thereby supporting clinical translation of said non–contrast-enhanced MR angiograms.}, author = {Haji-Valizadeh, Hassan and Shen, Daming and Avery, Ryan J. and Serhal, Ali M. and Schiffers, Florian A. and Katsaggelos, Aggelos K. and Cossairt, Oliver S. and Kim, Daniel}, doi = {10.1148/ryct.2020190205}, issn = {2638-6135}, journal = {Radiology: Cardiothoracic Imaging}, month = {jun}, number = {3}, pages = {e190205}, title = {{Rapid Reconstruction of Four-dimensional MR Angiography of the Thoracic Aorta Using a Convolutional Neural Network}}, url = {http://pubs.rsna.org/doi/10.1148/ryct.2020190205}, volume = {2}, year = {2020} }
@article{Arun2020, abstract = {In this paper, we present a temporal capsule network architecture to encode motion in videos as an instantiation parameter. The extracted motion is used to perform motion-compensated error concealment. We modify the original architecture and use a carefully curated dataset to enable the training of capsules spatially and temporally. First, we add the temporal dimension by taking co-located “patches” from three consecutive frames obtained from standard video sequences to form input data “cubes.” Second, the network is designed with an initial feature extraction layer that operates on all three dimensions to generate spatiotemporal features. Additionally, we implement the PrimaryCaps module with a recurrent layer, instead of a conventional convolutional layer, to extract short-term motion-related temporal dependencies and encode them as activation vectors in the capsule output. Finally, the capsule output is combined with the most-recent past frame and passed through a fully connected reconstruction network to perform motion-compensated error concealment. We study the effectiveness of temporal capsules by comparing the proposed model with architectures that do not include capsules. Although the quality of the reconstruction shows room for improvement, we successfully demonstrate that capsules-based architectures can be designed to operate in the temporal dimension to encode motion-related attributes as instantiation parameters. The accuracy of motion estimation is evaluated by comparing both the reconstructed frame outputs and the corresponding optical flow estimates with ground truth data.}, author = {Sankisa, Arun and Punjabi, Arjun and Katsaggelos, Aggelos K.}, doi = {10.1007/s11760-020-01671-x}, issn = {1863-1703}, journal = {Signal, Image and Video Processing}, keywords = {Capsule networks,Conv3D,ConvLSTM,Error concealment,Motion estimation}, month = {oct}, number = {7}, pages = {1369--1377}, title = {{Temporal capsule networks for video motion estimation and error concealment}}, url = {http://link.springer.com/10.1007/s11760-020-01671-x}, volume = {14}, year = {2020} }
@article{Natalia2019, abstract = {Most whole-slide histological images are stained with two or more chemical dyes. Slide stain separation or color deconvolution is a crucial step within the digital pathology workflow. In this paper, the blind color deconvolution problem is formulated within the Bayesian framework. Starting from a multi-stained histological image, our model takes into account both spatial relations among the concentration image pixels and similarity between a given reference color-vector matrix and the estimated one. Using Variational Bayes inference, three efficient new blind color deconvolution methods are proposed which provide automated procedures to estimate all the model parameters in the problem. A comparison with classical and current state-of-the-art color deconvolution algorithms using real images has been carried out demonstrating the superiority of the proposed approach.}, author = {Hidalgo-Gavira, Natalia and Mateos, Javier and Vega, Miguel and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1109/TIP.2019.2946442}, issn = {1057-7149}, journal = {IEEE Transactions on Image Processing}, keywords = {Bayesian modeling and inference,Blind color deconvolution,histopathological images,variational Bayes}, number = {1}, pages = {2026--2036}, pmid = {31634128}, title = {{Variational Bayesian Blind Color Deconvolution of Histopathological Images}}, url = {https://ieeexplore.ieee.org/document/8870230/}, volume = {29}, year = {2020} }
@article{Fernando2020b, abstract = {Pansharpening is a technique that fuses a low spatial resolution multispectral image and a high spatial resolution panchromatic one to obtain a multispectral image with the spatial resolution of the latter while preserving the spectral information of the multispectral image. In this paper we propose a variational Bayesian methodology for pansharpening. The proposed methodology uses the sensor characteristics to model the observation process and Super-Gaussian sparse image priors on the expected characteristics of the pansharpened image. The pansharpened image, as well as all model and variational parameters, are estimated within the proposed methodology. Using real and synthetic data, the quality of the pansharpened images is assessed both visually and quantitatively and compared with other pansharpening methods. Theoretical and experimental results demonstrate the effectiveness, efficiency, and flexibility of the proposed formulation.}, author = {P{\'{e}}rez-Bueno, Fernando and Vega, Miguel and Mateos, Javier and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.3390/s20185308}, issn = {1424-8220}, journal = {Sensors}, keywords = {Image fusion,Pansharpening,Super-Gaussians,Variational Bayesian}, month = {sep}, number = {18}, pages = {5308}, pmid = {32948056}, title = {{Variational Bayesian Pansharpening with Super-Gaussian Sparse Image Priors}}, url = {https://www.mdpi.com/1424-8220/20/18/5308}, volume = {20}, year = {2020} }
@article{Arjun2020, abstract = {Capsule networks are a recently developed class of neural networks that potentially address some of the deficiencies with traditional convolutional neural networks. By replacing the standard scalar activations with vectors, and by connecting the artificial neurons in a new way, capsule networks aim to be the next great development for computer vision applications. However, in order to determine whether these networks truly operate differently than traditional networks, one must look at the differences in the capsule features. To this end, we perform several analyses with the purpose of elucidating capsule features and determining whether they perform as described in the initial publication. First, we perform a deep visualization analysis to visually compare capsule features and convolutional neural network features. Then, we look at the ability for capsule features to encode information across the vector components and address what changes in the capsule architecture provides the most benefit. Finally, we look at how well the capsule features are able to encode instantiation parameters of class objects via visual transformations.}, archivePrefix = {arXiv}, arxivId = {2001.10964}, author = {Punjabi, Arjun and Schmid, Jonas and Katsaggelos, Aggelos K.}, eprint = {2001.10964}, journal = {arXiv preprint arXiv:2001.10964}, month = {jan}, title = {{Examining the Benefits of Capsule Neural Networks}}, url = {http://arxiv.org/abs/2001.10964}, year = {2020} }
@article{bae2020relating, author = {Bae, Jinhyeong and Stocks, Jane and Heywood, Ashley and Jung, Youngmoon and Katsaggelos, Aggelos and Jenkins, Lisanne M and Karteek, Popuri and Beg, Mirza Faisal and Wang, Lei}, doi = {10.1002/alz.043538}, institution = {ALZ}, issn = {1552-5260}, journal = {Alzheimer's & Dementia}, month = {dec}, number = {S5}, title = {{Relating occlusion maps obtained through deep learning to functional impairment in dementia of Alzheimer's type}}, url = {https://onlinelibrary.wiley.com/doi/10.1002/alz.043538}, volume = {16}, year = {2020} }
@article{Santiago2020, abstract = {The popularity of high and ultra-high definition displays has led to the need for methods to improve the quality of videos already obtained at much lower resolutions. A large amount of current CNN-based Video Super-Resolution methods are designed and trained to handle a specific degradation operator (e.g., bicubic downsampling) and are not robust to mismatch between training and testing degradation models. This causes their performance to deteriorate in real-life applications. Furthermore, many of them use the Mean-Squared-Error as the only loss during learning, causing the resulting images to be too smooth. In this work we propose a new Convolutional Neural Network for video super resolution which is robust to multiple degradation models. During training, which is performed on a large dataset of scenes with slow and fast motions, it uses the pseudo-inverse image formation model as part of the network architecture in conjunction with perceptual losses and a smoothness constraint that eliminates the artifacts originating from these perceptual losses. The experimental validation shows that our approach outperforms current state-of-the-art methods and is robust to multiple degradations.}, archivePrefix = {arXiv}, arxivId = {1907.01399}, author = {L{\'{o}}pez-Tapia, Santiago and Lucas, Alice and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1016/j.dsp.2020.102801}, eprint = {1907.01399}, issn = {10512004}, journal = {Digital Signal Processing}, keywords = {Convolutional neuronal networks,Generative adversarial networks,Perceptual loss functions,Super-resolution,Video}, month = {sep}, pages = {102801}, title = {{A single video super-resolution GAN for multiple downsampling operators based on pseudo-inverse image formation models}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S1051200420301469}, volume = {104}, year = {2020} }
@article{Corey2020, abstract = {Existing literature points to scaffolded training as an effective yet resource-intensive approach to help newcomers learn and stay motivated. Experts need to select relevant learning materials and continuously assess learners' progress. Peer production communities such as Wikipedia and Open Source Software Development projects face the additional problem of turning volunteers into productive participants as soon as possible. To address these challenges, we designed and tested a training regime combining scaffolded instruction and machine learning to select learning materials and gradually introduces new materials to individuals as their competences improve. We evaluated the training regime on 386 participants that contribute to Gravity Spy, an online citizen science project where people are asked to categorize glitches to assist scientists in the search for gravitational waves. Volunteers were assigned to one of two conditions; (1) a machine learning guided training (MLGT) system that continuously assesses volunteers skill level and adjusts the learning materials or (2) an unscaffolded training program where all learning materials were administered at once. Our analysis revealed that volunteers in the MLGT condition were more accurate on the categorization task (an average accuracy of 90% vs. 54%), executed more tasks (an average of 228 vs. 121 tasks), and were retained for a longer period (an average of 2.5 vs. 2 sessions) than volunteers in the unscaffolded training. The results suggest that MLGT is an effective pedagogical approach for training volunteers in categorization tasks and increases volunteers' motivation.}, author = {Jackson, Corey and {\O}sterlund, Carsten and Crowston, Kevin and Harandi, Mahboobeh and Allen, Sarah and Bahaadini, Sara and Coughlin, Scotty and Kalogera, Vicky and Katsaggelos, Aggelos and Larson, Shane and Rohani, Neda and Smith, Joshua and Trouille, Laura and Zevin, Michael}, doi = {10.1016/j.chb.2019.106198}, issn = {07475632}, journal = {Computers in Human Behavior}, keywords = {Citizen science,Experiment,Learning,Online communities,Scaffolding,Training,User studies,Zooniverse}, month = {apr}, pages = {106198}, title = {{Teaching citizen scientists to categorize glitches using machine learning guided training}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S0747563219304182}, volume = {105}, year = {2020} }
@article{Qiqin2019, abstract = {This paper presents an adaptive image sampling algorithm based on Deep Learning (DL). It consists of an adaptive sampling mask generation network which is jointly trained with an image inpainting network. The sampling rate is controlled by the mask generation network, and a binarization strategy is investigated to make the sampling mask binary. In addition to the image sampling and reconstruction process, we show how it can be extended and used to speed up raster scanning such as the X-Ray fluorescence (XRF) image scanning process. Recently XRF laboratory-based systems have evolved into lightweight and portable instruments thanks to technological advancements in both X-Ray generation and detection. However, the scanning time of an XRF image is usually long due to the long exposure requirements (e.g., 100\; $\mu$ s-1 ms per point). We propose an XRF image inpainting approach to address the long scanning times, thus speeding up the scanning process, while being able to reconstruct a high quality XRF image. The proposed adaptive image sampling algorithm is applied to the RGB image of the scanning target to generate the sampling mask. The XRF scanner is then driven according to the sampling mask to scan a subset of the total image pixels. Finally, we inpaint the scanned XRF image by fusing the RGB image to reconstruct the full scan XRF image. The experiments show that the proposed adaptive sampling algorithm is able to effectively sample the image and achieve a better reconstruction accuracy than that of existing methods.}, archivePrefix = {arXiv}, arxivId = {1812.10836}, author = {Dai, Qiqin and Chopp, Henry and Pouyet, Emeline and Cossairt, Oliver and Walton, Marc and Katsaggelos, Aggelos K.}, doi = {10.1109/TMM.2019.2958760}, eprint = {1812.10836}, issn = {1520-9210}, journal = {IEEE Transactions on Multimedia}, keywords = {Adaptive sampling,X-Ray fluorescence,convolutional neural network,inpainting}, month = {oct}, number = {10}, pages = {2564--2578}, title = {{Adaptive Image Sampling Using Deep Learning and Its Application on X-Ray Fluorescence Image Reconstruction}}, url = {https://ieeexplore.ieee.org/document/8930037/}, volume = {22}, year = {2020} }
@article{iliadis2020deepbinarymask, abstract = {In this paper, we propose an encoder-decoder neural network model referred to as DeepBinaryMask for video compressive sensing. In video compressive sensing one frame is acquired using a set of coded masks (sensing matrix) from which a number of video frames, equal to the number of coded masks, is reconstructed. The proposed framework is an end-to-end model where the sensing matrix is trained along with the video reconstruction. The encoder maps a video block to compressive measurements by learning the binary elements of the sensing matrix. The decoder is trained to map the measurements from a video patch back to a video block via several hidden layers of a Multi-Layer Perceptron network. The predicted video blocks are stacked together to recover the unknown video sequence. The reconstruction performance is found to improve when using the trained sensing mask from the network as compared to other mask designs such as random, across a wide variety of compressive sensing reconstruction algorithms. Finally, our analysis and discussion offers insights into understanding the characteristics of the trained mask designs that lead to the improved reconstruction quality.}, archivePrefix = {arXiv}, arxivId = {1607.03343}, author = {Iliadis, Michael and Spinoulas, Leonidas and Katsaggelos, Aggelos K.}, doi = {10.1016/j.dsp.2019.102591}, eprint = {1607.03343}, issn = {10512004}, journal = {Digital Signal Processing}, keywords = {Binary mask,Compressive sensing,Deep learning,Mask optimization,Video reconstruction}, month = {jan}, pages = {102591}, title = {{DeepBinaryMask: Learning a binary mask for video compressive sensing}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S1051200419301459}, volume = {96}, year = {2020} }
@article{Emily2020, abstract = {Abstract Background Memory complaints are widespread among the elderly and aging is a major risk factor for Alzheimer's disease (AD), leading to the impression that gradual loss of memory ability is a nearly universal consequence of getting old. Our longitudinal studies of SuperAgers, 80+ year-olds with episodic memory performance that remains in the range that is at least normal for 50-60 year-olds suggests an alternative aging trajectory is possible. This session will highlight some of the emerging biologic features of the SuperAgers. Method Participants include SuperAgers and cognitively average 80+ year-old cognitively average normal controls. Data from detailed neuropsychological assessments, quantitative neuroimaging measurements (MR and amyloid PET), genetic features and neuropathologic findings will be reported. Result Initial evidence suggest SuperAgers tend to show mismatch between chronologic and biologic age, including maintenance of cortical but not necessarily hippocampal volume, a tendency to resist significant amyloid PET retention, an abundance of anterior cingulate Von Economo neurons, and some with resistance to cortical Alzheimer's pathology. Conclusion These studies contribute to our understanding mechanisms of resilience and resistance in cognitive aging and may help isolate factors that are potentially important for promoting successful cognitive aging and avoiding age-related brain diseases such as AD.}, author = {Rogalski, Emily J and Sridhar, Jaiashre and Martersteck, Adam and Makowski‐Woidan, Beth and Engelmeyer, Janessa and Parrish, Todd and Besson, Pierre and Cobia, Derin and Paxton, Holly and Weintraub, Sandra and Katsaggelos, Aggelos and Bandt, Katie and Bigio, Eileen H and Geula, Changiz and Mesulam, Marsel}, doi = {10.1002/alz.037932}, issn = {1552-5260}, journal = {Alzheimer's & Dementia}, month = {dec}, number = {S10}, pages = {e037932}, title = {{SuperAging: A model for studying mechanisms of resilience and resistance}}, url = {https://onlinelibrary.wiley.com/doi/10.1002/alz.037932}, volume = {16}, year = {2020} }
@article{Haoyu2020, abstract = {Computed tomography is widely used to examine internal structures in a non-destructive manner. To obtain high-quality reconstructions, one typically has to acquire a densely sampled trajectory to avoid angular undersampling. However, many scenarios require a sparse-view measurement leading to streak-artifacts if unaccounted for. Current methods do not make full use of the domain-specific information, and hence fail to provide reliable reconstructions for highly undersampled data. We present a novel framework for sparse-view tomography by decoupling the reconstruction into two steps: First, we overcome its ill-posedness using a super-resolution network, SIN, trained on the sparse projections. The intermediate result allows for a closed-form tomographic reconstruction with preserved details and highly reduced streak-artifacts. Second, a refinement network, PRN, trained on the reconstructions reduces any remaining artifacts. We further propose a light-weight variant of the perceptual-loss that enhances domain-specific information, boosting restoration accuracy. Our experiments demonstrate an improvement over current solutions by 4 dB.}, archivePrefix = {arXiv}, arxivId = {2012.04743}, author = {Wei, Haoyu and Schiffers, Florian and W{\"{u}}rfl, Tobias and Shen, Daming and Kim, Daniel and Katsaggelos, Aggelos K. and Cossairt, Oliver}, eprint = {2012.04743}, journal = {arXiv preprint arXiv:2012.04743}, month = {dec}, title = {{2-Step Sparse-View CT Reconstruction with a Domain-Specific Perceptual Network}}, url = {http://arxiv.org/abs/2012.04743}, year = {2020} }
@article{Arjun2019, abstract = {Automated methods for Alzheimer's disease (AD) classification have the potential for great clinical benefits and may provide insight for combating the disease. Machine learning, and more specifically deep neural networks, have been shown to have great efficacy in this domain. These algorithms often use neurological imaging data such as MRI and FDG PET, but a comprehensive and balanced comparison of the MRI and amyloid PET modalities has not been performed. In order to accurately determine the relative strength of each imaging variant, this work performs a comparison study in the context of Alzheimer's dementia classification using the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset with identical neural network architectures. Furthermore, this work analyzes the benefits of using both modalities in a fusion setting and discusses how these data types may be leveraged in future AD studies using deep learning.}, archivePrefix = {arXiv}, arxivId = {1811.05105}, author = {Punjabi, Arjun and Martersteck, Adam and Wang, Yanran and Parrish, Todd B. and Katsaggelos, Aggelos K.}, doi = {10.1371/journal.pone.0225759}, editor = {Ginsberg, Stephen D}, eprint = {1811.05105}, issn = {1932-6203}, journal = {PLOS ONE}, month = {dec}, number = {12}, pages = {e0225759}, pmid = {31805160}, title = {{Neuroimaging modality fusion in Alzheimer's classification using convolutional neural networks}}, url = {https://dx.plos.org/10.1371/journal.pone.0225759}, volume = {14}, year = {2019} }
@article{AliBahrami2019, abstract = {Objective: The aim of this study is to develop an automated classification algorithm for polysomnography (PSG) recordings to detect non-apneic and non-hypopneic arousals. Our particular focus is on detecting the respiratory effort-related arousals (RERAs) which are very subtle respiratory events that do not meet the criteria for apnea or hypopnea, and are more challenging to detect. Methods: The proposed algorithm is based on a bidirectional long short-term memory (BiLSTM) classifier and 465 multi-domain features, extracted from multimodal clinical time series. The features consist of a set of physiology-inspired features (n = 75), obtained by multiple steps of feature selection and expert analysis, and a set of physiology-agnostic features (n = 390), derived from scattering transform. Results: The proposed algorithm is validated on the 2018 PhysioNet challenge dataset. The overall performance in terms of the area under the precision-recall curve (AUPRC) is 0.50 on the hidden test dataset. This result is tied for the second-best score during the follow-up and official phases of the 2018 PhysioNet challenge. Conclusions: The results demonstrate that it is possible to automatically detect subtle non-apneic/non-hypopneic arousal events from PSG recordings. Significance: Automatic detection of subtle respiratory events such as RERAs together with other non-apneic/non-hypopneic arousals will allow detailed annotations of large PSG databases. This contributes to a better retrospective analysis of sleep data, which may also improve the quality of treatment.}, archivePrefix = {arXiv}, arxivId = {1909.02971}, author = {Rad, Ali Bahrami and Zabihi, Morteza and Zhao, Zheng and Gabbouj, Moncef and Katsaggelos, Aggelos K. and S{\"{a}}rkk{\"{a}}, Simo}, eprint = {1909.02971}, journal = {arXiv e-prints}, month = {sep}, pages = {arXiv----1909}, title = {{Automated Polysomnography Analysis for Detection of Non-Apneic and Non-Hypopneic Arousals using Feature Engineering and a Bidirectional LSTM Network}}, url = {http://arxiv.org/abs/1909.02971}, year = {2019} }
@article{coughlin2019classifying, abstract = {The observation of gravitational waves from compact binary coalescences by LIGO and Virgo has begun a new era in astronomy. A critical challenge in making detections is determining whether loud transient features in the data are caused by gravitational waves or by instrumental or environmental sources. The citizen-science project Gravity Spy has been demonstrated as an efficient infrastructure for classifying known types of noise transients (glitches) through a combination of data analysis performed by both citizen volunteers and machine learning. We present the next iteration of this project, using similarity indices to empower citizen scientists to create large data sets of unknown transients, which can then be used to facilitate supervised machine-learning characterization. This new evolution aims to alleviate a persistent challenge that plagues both citizen-science and instrumental detector work: the ability to build large samples of relatively rare events. Using two families of transient noise that appeared unexpectedly during LIGO's second observing run, we demonstrate the impact that the similarity indices could have had on finding these new glitch types in the Gravity Spy program.}, archivePrefix = {arXiv}, arxivId = {1903.04058}, author = {Coughlin, S. and Bahaadini, S. and Rohani, N. and Zevin, M. and Patane, O. and Harandi, M. and Jackson, C. and Noroozi, V. and Allen, S. and Areeda, J. and Coughlin, M. and Ruiz, P. and Berry, C. P. L. and Crowston, K. and Katsaggelos, A. K. and Lundgren, A. and {\O}sterlund, C. and Smith, J. R. and Trouille, L. and Kalogera, V.}, doi = {10.1103/PhysRevD.99.082002}, eprint = {1903.04058}, issn = {2470-0010}, journal = {Physical Review D}, month = {apr}, number = {8}, pages = {082002}, publisher = {American Physical Society}, title = {{Classifying the unknown: Discovering novel gravitational-wave detector glitches using similarity learning}}, url = {https://link.aps.org/doi/10.1103/PhysRevD.99.082002}, volume = {99}, year = {2019} }
@article{Alice2019a, abstract = {While Convolutional Neural Networks (CNNs) trained for image and video super-resolution (SR) regularly achieve new state-of-the-art performance, they also suffer from significant drawbacks. One of their limitations is their lack of robustness to unseen image formation models during training. Other limitations include the generation of artifacts and hallucinated content when training Generative Adversarial Networks (GANs) for SR. While the Deep Learning literature focuses on presenting new training schemes and settings to resolve these various issues, we show that one can avoid training and correct for SR results with a fully self-supervised fine-tuning approach. More specifically, at test time, given an image and its known image formation model, we fine-tune the parameters of the trained network and iteratively update them using a data fidelity loss. We apply our fine-tuning algorithm on multiple image and video SR CNNs and show that it can successfully correct for a sub-optimal SR solution by entirely relying on internal learning at test time. We apply our method on the problem of fine-tuning for unseen image formation models and on removal of artifacts introduced by GANs.}, archivePrefix = {arXiv}, arxivId = {https://arxiv.org/abs/1912.12879v3}, author = {Lucas, Alice and Lopez-Tapia, Santiago and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {https://doi.org/10.48550/arXiv.1912.12879}, eprint = {/arxiv.org/abs/1912.12879v3}, journal = {arXiv preprint arXiv:1912.12879}, keywords = {Computer Science - Machine Learning,Electrical Engineering and Systems Science - Image,Statistics - Machine Learning}, month = {dec}, pages = {1--15}, primaryClass = {https:}, title = {{Self-supervised Fine-tuning for Correcting Super-Resolution Convolutional Neural Networks}}, url = {http://arxiv.org/abs/1912.12879}, year = {2019} }
@article{Alice2019c, abstract = {Video super-resolution (VSR) has become one of the most critical problems in video processing. In the deep learning literature, recent works have shown the benefits of using adversarial-based and perceptual losses to improve the performance on various image restoration tasks; however, these have yet to be applied for video super-resolution. In this paper, we propose a generative adversarial network (GAN)-based formulation for VSR. We introduce a new generator network optimized for the VSR problem, named VSRResNet, along with new discriminator architecture to properly guide VSRResNet during the GAN training. We further enhance our VSR GAN formulation with two regularizers, a distance loss in feature-space and pixel-space, to obtain our final VSRResFeatGAN model. We show that pre-training our generator with the mean-squared-error loss only quantitatively surpasses the current state-of-the-art VSR models. Finally, we employ the PercepDist metric to compare the state-of-the-art VSR models. We show that this metric more accurately evaluates the perceptual quality of SR solutions obtained from neural networks, compared with the commonly used PSNR/SSIM metrics. Finally, we show that our proposed model, the VSRResFeatGAN model, outperforms the current state-of-the-art SR models, both quantitatively and qualitatively.}, archivePrefix = {arXiv}, arxivId = {1806.05764}, author = {Lucas, Alice and Lopez-Tapia, Santiago and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1109/TIP.2019.2895768}, eprint = {1806.05764}, issn = {1057-7149}, journal = {IEEE Transactions on Image Processing}, keywords = {Artificial neural networks,image generation,image resolution,video signal processing}, month = {jul}, number = {7}, pages = {3312--3327}, pmid = {30714918}, title = {{Generative Adversarial Networks and Perceptual Losses for Video Super-Resolution}}, url = {https://ieeexplore.ieee.org/document/8629024/}, volume = {28}, year = {2019} }
@article{Arun2019, abstract = {A novel optical flow prediction model using an adaptable deep neural network architecture for blind and non-blind error concealment of videos degraded by transmission loss is presented. The two-stream network model is trained by separating the horizontal and vertical motion fields which are passed through two similar parallel pipelines that include traditional convolutional (Conv) and convolutional long short-term memory (ConvLSTM) layers. The ConvLSTM layers extract temporally correlated motion information while the Conv layers correlate motion spatially. The optical flows used as input to the two-pipeline prediction network are obtained through a flow generation network that can be easily interchanged, increasing the adaptability of the overall end-to-end architecture. The performance of the proposed model is evaluated using real-world packet loss scenarios. Standard video quality metrics are used to compare frames reconstructed using predicted optical flows with those reconstructed using “ground-truth” flows obtained directly from the generator.}, author = {Sankisa, Arun and Punjabi, Arjun and Katsaggelos, Aggelos K.}, doi = {10.4018/IJMDEM.2019070102}, isbn = {978-1-4799-7061-2}, issn = {1947-8534}, journal = {International Journal of Multimedia Data Engineering and Management}, keywords = {CNN,ConvLSTM,Deep Neural Networks,Optical flow,Video Error Concealment}, month = {jul}, number = {3}, pages = {27--46}, publisher = {IEEE}, title = {{Optical Flow Prediction for Blind and Non-Blind Video Error Concealment Using Deep Neural Networks}}, url = {https://ieeexplore.ieee.org/document/8451090/ http://services.igi-global.com/resolvedoi/resolve.aspx?doi=10.4018/IJMDEM.2019070102}, volume = {10}, year = {2019} }
@article{Pablo2019, abstract = {Over the last few years, multiply-annotated data has become a very popular source of information. Online platforms such as Amazon Mechanical Turk have revolutionized the labelling process needed for any classification task, sharing the effort between a number of annotators (instead of the classical single expert). This crowdsourcing approach has introduced new challenging problems, such as handling disagreements on the annotated samples or combining the unknown expertise of the annotators. Probabilistic methods, such as Gaussian Processes (GP), have proven successful to model this new crowdsourcing scenario. However, GPs do not scale up well with the training set size, which makes them prohibitive for medium-to-large datasets (beyond 10K training instances). This constitutes a serious limitation for current real-world applications. In this work, we introduce two scalable and efficient GP-based crowdsourcing methods that allow for processing previously-prohibitive datasets. The first one is an efficient and fast approximation to GP with squared exponential (SE) kernel. The second allows for learning a more flexible kernel at the expense of a heavier training (but still scalable to large datasets). Since the latter is not a GP-SE approximation, it can be also considered as a whole new scalable and efficient crowdsourcing method, useful for any dataset size. Both methods use Fourier features and variational inference, can predict the class of new samples, and estimate the expertise of the involved annotators. A complete experimentation compares them with state-of-the-art probabilistic approaches in synthetic and real crowdsourcing datasets of different sizes. They stand out as the best performing approach for large scale problems. Moreover, the second method is competitive with the current state-of-the-art for small datasets.}, author = {Morales-{\'{A}}lvarez, Pablo and Ruiz, Pablo and Santos-Rodr{\'{i}}guez, Ra{\'{u}}l and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1016/j.inffus.2018.12.008}, issn = {15662535}, journal = {Information Fusion}, keywords = {Bayesian modelling,Classification,Fourier features,Gaussian processes,Scalable crowdsourcing,Variational inference}, month = {dec}, pages = {110--127}, title = {{Scalable and efficient learning from crowds with Gaussian processes}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S1566253518304664}, volume = {52}, year = {2019} }
@article{Alice2019, abstract = {Somatosensation is composed of two distinct modalities: touch, arising from sensors in the skin, and proprioception, resulting primarily from sensors in the muscles, combined with these same cutaneous sensors. In contrast to the wealth of information about touch, we know quite less about the nature of the signals giving rise to proprioception at the cortical level. Likewise, while there is considerable interest in developing encoding models of touch-related neurons for application to brain machine interfaces, much less emphasis has been placed on an analogous proprioceptive interface. Here we investigate the use of Artificial Neural Networks (ANNs) to model the relationship between the firing rates of single neurons in area 2, a largely proprioceptive region of somatosensory cortex (S1) and several types of kinematic variables related to arm movement. To gain a better understanding of how these kinematic variables interact to create the proprioceptive responses recorded in our datasets, we train ANNs under different conditions, each involving a different set of input and output variables. We explore the kinematic variables that provide the best network performance, and find that the addition of information about joint angles and/or muscle lengths significantly improves the prediction of neural firing rates. Our results thus provide new insight regarding the complex representations of the limb motion in S1: that the firing rates of neurons in area 2 may be more closely related to the activity of peripheral sensors than it is to extrinsic hand position. In addition, we conduct numerical experiments to determine the sensitivity of ANN models to various choices of training design and hyper-parameters. Our results provide a baseline and new tools for future research that utilizes machine learning to better describe and understand the activity of neurons in S1.}, author = {Lucas, Alice and Tomlinson, Tucker and Rohani, Neda and Chowdhury, Raeed and Solla, Sara A. and Katsaggelos, Aggelos K. and Miller, Lee E.}, doi = {10.3389/fnsys.2019.00013}, issn = {1662-5137}, journal = {Frontiers in Systems Neuroscience}, keywords = {Artificial neural networks,Limb-state encoding,Monkey,Reaching,Single neurons,Somatosensory cortex}, month = {mar}, pages = {13 , publisher = Frontiers Media SA}, title = {{Neural Networks for Modeling Neural Spiking in S1 Cortex}}, url = {https://www.frontiersin.org/article/10.3389/fnsys.2019.00013/full}, volume = {13}, year = {2019} }
@article{Pablo2019a, abstract = {Historical paper often contains features embedded in its structure that are invisible under standard viewing conditions. These features (watermarks, laid lines, and chain lines) can provide valuable information about a sheet's provenance. Standard methods of reproducing watermarks, such as beta-radiography and low-voltage x-rays, are costly and time intensive, and therefore inaccessible to many institutions or individuals. In this work we introduce an inexpensive prototype whose elements are a light table and a consumer-grade photographic camera. For a given document we acquire an image with light emitted by a light table passing through the document and two images of the front and the back side with ambient light. The images are then processed to suppress the printed elements and isolate the watermark. The proposed method is capable of recovering images of watermarks similar to the ones obtained with standard methods while being a non-destructive, rapid, easy to operate, and inexpensive method.}, author = {Ruiz, Pablo and Dill, Olivia and Raju, Goutam and Cossairt, Oliver and Walton, Marc and Katsaggelos, Aggelos K.}, doi = {10.1016/j.daach.2019.e00121}, issn = {22120548}, journal = {Digital Applications in Archaeology and Cultural Heritage}, keywords = {Image processing,Registration,Scattering,Visible light,Watermark extraction}, month = {dec}, pages = {e00121}, title = {{Visible transmission imaging of watermarks by suppression of occluding text or drawings}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S221205481830047X}, volume = {15}, year = {2019} }
@article{Juan2019, abstract = {Most state-of-the-art blind image deconvolution methods rely on the Bayesian paradigm to model the deblurring problem and estimate both the blur kernel and latent image. It is customary to model the image in the filter space, where it is supposed to be sparse, and utilize convenient priors to account for this sparsity. In this paper, we propose the use of the spike-and-slab prior together with an efficient variational Expectation Maximization (EM) inference scheme to estimate the blur in the image. The spike-and-slab prior, which constitutes the gold standard in sparse machine learning, selectively shrinks irrelevant variables while mildly regularizing the relevant ones. The proposed variational Expectation Maximization algorithm is more efficient than usual Markov Chain Monte Carlo (MCMC) inference and, also, proves to be more accurate than the standard mean-field variational approximation. Additionally, all the prior model parameters are estimated by the proposed scheme. After blur estimation, a non-blind restoration method is used to obtain the actual estimation of the sharp image. We investigate the behavior of the prior in the experimental section together with a series of experiments with synthetically generated and real blurred images that validate the method's performance in comparison with state-of-the-art blind deconvolution techniques.}, author = {Serra, Juan G. and Mateos, Javier and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1016/j.dsp.2019.01.004}, issn = {10512004}, journal = {Digital Signal Processing}, keywords = {Blind image deconvolution,Blur estimation,Spike and slab,Variational inference}, month = {may}, pages = {116--129}, title = {{Variational EM method for blur estimation using the spike-and-slab image prior}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S1051200418306109}, volume = {88}, year = {2019} }
@article{Neda2015, abstract = {This paper proposes a new model for multi-sensory data classification. To tackle this problem, probabilistic modeling and variational Bayesian inference are used. A Gaussian Process (GP) classifier is built upon the introduced modeling. Its posterior distribution is approximated using variational Bayesian inference. Finally, labels of test samples are predicted employing this classifier. Very importantly, and in contrast to alternative approaches, the proposed method does not discard samples with missing features and utilizes all available information for training. Furthermore, to take into account that the quality of the information provided by each sensor may differ (some modalities/sensors may provide more reliable/distinctive information than others), we introduce two versions of the algorithm. In the first one, the parameters modeling each sensor performance are shared while in the second one, each sensor parameters are estimated independently. Synthetic and real datasets are utilized to examine the validity of the proposed models. The results obtained for binary classification problems justify their use and confirm their superiority over existing fusion architectures.}, author = {Rohani, Neda and Ruiz, Pablo and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1016/j.patrec.2018.08.035}, issn = {01678655}, journal = {Pattern Recognition Letters}, keywords = {Fusion,Gaussian process,Kernel,Posterior probability,Variational inference}, month = {dec}, pages = {80--87}, title = {{Variational Gaussian process for multisensor classification problems}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S0167865518305427}, volume = {116}, year = {2018} }
@article{Salvador2018, abstract = {Digital Forensics encompasses the recovery and investigation of data, images, and recordings found in digital devices in order to provide evidence in the court of law. This paper is devoted to the assessment of digital evidence which requires not only an understanding of the scientific technique that leads to improved quality of surveillance video recordings, but also of the legal principles behind it. Emphasis is given on the special treatment of image processing in terms of its handling and explanation that would be acceptable in a court of law. In this context, we propose a variational Bayesian approach to multiple-image super-resolution based on Super-Gaussian prior models that automatically enhances the quality of outdoor video recordings and estimates all the model parameters while preserving the authenticity, credibility and reliability of video data as digital evidence. The proposed methodology is validated both quantitatively and visually on synthetic videos generated from single images and real-life videos and applied to a real-life case of damages and stealing in a private property.}, author = {Villena, Salvador and Vega, Miguel and Mateos, Javier and Rosenberg, Duska and Murtagh, Fionn and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1016/j.compind.2018.02.004}, issn = {01663615}, journal = {Computers in Industry}, keywords = {Legal aspects,Outdoor surveillance,Super-resolution,Usability}, month = {jun}, pages = {34--47}, title = {{Image super-resolution for outdoor digital forensics. Usability and legal aspects}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S0166361517306358}, volume = {98}, year = {2018} }
@article{Xiang2018a, abstract = {Volumetric biological imaging often involves compromising high temporal resolution at the expense of high spatial resolution when popular scanning methods are used to capture 3D information. We introduce an integrated experimental and image reconstruction method for capturing dynamic 3D fluorescent extended objects as a series of synchronously measured 3D snapshots taken at the frame rate of the imaging camera. We employ multifocal microscopy (MFM) to simultaneously image at 25 focal planes and process this depth-encoded image to recover the 3D structure of extended objects, such as bacteria, using a sparsity-based reconstruction approach. The combined experimental and computational method produces image quality similar to confocal microscopy in a fraction of the acquisition time. In addition, our computational image reconstruction approach allows a simplified MFM optical design by correcting aberrations using the measured response to point sources. This "compressive" MFM acquisition and reconstruction method, where an image volume with roughly 8 million voxels is recovered from a single 1-megapixel captured image, enables straightforward study of dynamic processes in 3D, and as a simultaneous snapshot advances the state of the art in dynamic 3D microscopy.}, archivePrefix = {arXiv}, arxivId = {1802.01565}, author = {Huang, Xiang and Selewa, Alan and Wang, Xiaolei and Daddysman, Matthew K. and Gdor, Itay and Wilton, Rosemarie and Kemner, Kenneth M. and Yoo, Seunghwan and Katsaggelos, Aggelos K. and He, Kuan and Cossairt, Oliver and Ferrier, Nicola J. and Hereld, Mark and Scherer, Norbert F.}, eprint = {1802.01565}, journal = {arXiv preprint arXiv:1802.01565}, month = {feb}, title = {{3D Snapshot Microscopy of Extended Objects}}, url = {http://arxiv.org/abs/1802.01565}, year = {2018} }
@article{Michael2018, abstract = {In this work we present a deep learning framework for video compressive sensing. The proposed formulation enables recovery of video frames in a few seconds at significantly improved reconstruction quality compared to previous approaches. Our investigation starts by learning a linear mapping between video sequences and corresponding measured frames which turns out to provide promising results. We then extend the linear formulation to deep fully-connected networks and explore the performance gains using deeper architectures. Our analysis is always driven by the applicability of the proposed framework on existing compressive video architectures. Extensive simulations on several video sequences document the superiority of our approach both quantitatively and qualitatively. Finally, our analysis offers insights into understanding how dataset sizes and number of layers affect reconstruction performance while raising a few points for future investigation.}, archivePrefix = {arXiv}, arxivId = {1603.04930}, author = {Iliadis, Michael and Spinoulas, Leonidas and Katsaggelos, Aggelos K.}, doi = {10.1016/j.dsp.2017.09.010}, eprint = {1603.04930}, issn = {10512004}, journal = {Digital Signal Processing}, keywords = {Deep neural networks,Fully-connected networks,Video compressive sensing}, month = {jan}, pages = {9--18}, title = {{Deep fully-connected networks for video compressive sensing}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S1051200417302130}, volume = {72}, year = {2018} }
@article{Neda2018a, abstract = {Nonlinear unmixing of hyperspectral reflectance data is one of the key problems in quantitative imaging of painted works of art. The approach presented is to interrogate a hyperspectral image cube by first decomposing it into a set of reflectance curves representing pure basis pigments and second to estimate the scattering and absorption coefficients of each pigment in a given pixel to produce estimates of the component fractions. This two-step algorithm uses a deep neural network to qualitatively identify the constituent pigments in any unknown spectrum and, based on the pigment(s) present and Kubelka–Munk theory to estimate the pigment concentration on a per-pixel basis. Using hyperspectral data acquired on a set of mock-up paintings and a well-characterized illuminated folio from the 15th century, the performance of the proposed algorithm is demonstrated for pigment recognition and quantitative estimation of concentration.}, author = {Rohani, Neda and Pouyet, Emeline and Walton, Marc and Cossairt, Oliver and Katsaggelos, Aggelos K.}, doi = {10.1002/anie.201805135}, issn = {14337851}, journal = {Angewandte Chemie International Edition}, keywords = {deep neural network classification,heritage science,nonlinear unmixing Kubelka–Munk theory,visible hyperspectral imaging}, month = {aug}, number = {34}, pages = {10910--10914}, pmid = {29940088}, title = {{Nonlinear Unmixing of Hyperspectral Datasets for the Study of Painted Works of Art}}, url = {https://onlinelibrary.wiley.com/doi/10.1002/anie.201805135}, volume = {57}, year = {2018} }
@article{Emeline2018, abstract = {Visible hyperspectral imaging (HSI) is a fast and non-invasive imaging method that has been adapted by the field of conservation science to study painted surfaces. By collecting reflectance spectra from a 2D surface, the resulting 3D hyperspectral data cube contains millions of recorded spectra. While processing such large amounts of spectra poses an analytical and computational challenge, it also opens new opportunities to apply powerful methods of multivariate analysis for data evaluation. With the intent of expanding current data treatment of hyperspectral datasets, an innovative approach for data reduction and visualization is presented in this article. It uses a statistical embedding method known as t-distributed stochastic neighbor embedding (t-SNE) to provide a non-linear representation of spectral features in a lower 2D space. The efficiency of the proposed method for painted surfaces from cultural heritage is established through the study of laboratory prepared paint mock-ups, and medieval French illuminated manuscript.}, author = {Pouyet, Emeline and Rohani, Neda and Katsaggelos, Aggelos K. and Cossairt, Oliver and Walton, Marc}, doi = {10.1515/pac-2017-0907}, issn = {1365-3075}, journal = {Pure and Applied Chemistry}, keywords = {ChemCultHerit,Data reduction and visualization,Illuminated manuscript,Multivariate analysis,T-distributed stochastic neighbor embedding,Visible hyperspectral imaging}, month = {feb}, number = {3}, pages = {493--506}, title = {{Innovative data reduction and visualization strategy for hyperspectral imaging datasets using t-SNE approach}}, url = {https://www.degruyter.com/document/doi/10.1515/pac-2017-0907/html}, volume = {90}, year = {2018} }
@article{Kuan2018, abstract = {Despite recent advances, high performance single-shot 3D microscopy remains an elusive task. By introducing designed diffractive optical elements (DOEs), one is capable of converting a microscope into a 3D "kaleidoscope", in which case the snapshot image consists of an array of tiles and each tile focuses on different depths. However, the acquired multifocal microscopic (MFM) image suffers from multiple sources of degradation, which prevents MFM from further applications. We propose a unifying computational framework which simplifies the imaging system and achieves 3D reconstruction via computation. Our optical configuration omits chromatic correction grating and redesigns the multifocal grating to enlarge the tracking area. Our proposed setup features only one single grating in addition to a regular microscope. The aberration correction, along with Poisson and background denoising, are incorporated in our deconvolution-based fully-automated algorithm, which requires no empirical parameter-tuning. In experiments, we achieve the spatial resolutions of $0.35$um (lateral) and $0.5$um (axial), which are comparable to the resolution that can be achieved with confocal deconvolution microscopy. We demonstrate a 3D video of moving bacteria recorded at $25$ frames per second using our proposed computational multifocal microscopy technique.}, archivePrefix = {arXiv}, arxivId = {1809.01239}, author = {He, Kuan and Wang, Zihao and Huang, Xiang and Wang, Xiaolei and Yoo, Seunghwan and Ruiz, Pablo and Gdor, Itay and Selewa, Alan and Ferrier, Nicola J. and Scherer, Norbert and Hereld, Mark and Katsaggelos, Aggelos K. and Cossairt, Oliver}, doi = {10.1364/BOE.9.006477}, eprint = {1809.01239}, issn = {2156-7085}, journal = {Biomedical Optics Express}, month = {dec}, number = {12}, pages = {6477}, title = {{Computational multifocal microscopy}}, url = {https://opg.optica.org/abstract.cfm?URI=boe-9-12-6477}, volume = {9}, year = {2018} }
@article{Danielle2018, abstract = {Microscopy and Microanalysis Volume 24 supplement s1: proceedings of microscopy & microanalysis 2018}, author = {Duggins, Danielle and Li, Fengqiang and Aalders, Maurice and Cossairt, Oliver and Katsaggelos, Aggelos and Walton, Marc}, doi = {10.1017/S1431927618011194}, issn = {1431-9276}, journal = {Microscopy and Microanalysis}, month = {aug}, number = {S1}, pages = {2142--2143}, title = {{A Novel OCT Design for Cultural Heritage Applications}}, url = {https://academic.oup.com/mam/article/24/S1/2142/6945740}, volume = {24}, year = {2018} }
@article{Alice2018, abstract = {Traditionally, analytical methods have been used to solve imaging problems such as image restoration, inpainting, and superresolution (SR). In recent years, the fields of machine and deep learning have gained a lot of momentum in solving such imaging problems, often surpassing the performance provided by analytical approaches. Unlike analytical methods for which the problem is explicitly defined and domain-knowledge carefully engineered into the solution, deep neural networks (DNNs) do not benefit from such prior knowledge and instead make use of large data sets to learn the unknown solution to the inverse problem. In this article, we review deep-learning techniques for solving such inverse problems in imaging. More specifically, we review the popular neural network architectures used for imaging tasks, offering some insight as to how these deep-learning tools can solve the inverse problem. Furthermore, we address some fundamental questions, such as how deeplearning and analytical methods can be combined to provide better solutions to the inverse problem in addition to providing a discussion on the current limitations and future directions of the use of deep learning for solving inverse problem in imaging.}, author = {Lucas, Alice and Iliadis, Michael and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1109/MSP.2017.2760358}, issn = {1053-5888}, journal = {IEEE Signal Processing Magazine}, month = {jan}, number = {1}, pages = {20--36}, title = {{Using Deep Neural Networks for Inverse Problems in Imaging: Beyond Analytical Methods}}, url = {http://ieeexplore.ieee.org/document/8253590/}, volume = {35}, year = {2018} }
@article{Itay2018, abstract = {Accurate and rapid particle tracking is essential for addressing many research problems in single molecule and cellular biophysics and colloidal soft condensed matter physics. We developed a novel three-dimensional interferometric fluorescent particle tracking approach that does not require any sample scanning. By periodically shifting the interferometer phase, the information stored in the interference pattern of the emitted light allows localizing particles positions with nanometer resolution. This tracking protocol was demonstrated by measuring a known trajectory of a fluorescent bead with sub-5 nm axial localization error at 5 Hz. The interferometric microscopy was used to track the RecA protein in Bacillus subtilis bacteria to demonstrate its compatibility with biological systems.}, author = {Gdor, Itay and Wang, Xiaolei and Daddysman, Matthew and Yifat, Yuval and Wilton, Rosemarie and Hereld, Mark and Noirot-Gros, Marie-Fran{\c{c}}oise and Scherer, Norbert F.}, doi = {10.1364/OL.43.002819}, issn = {0146-9592}, journal = {Optics Letters}, month = {jun}, number = {12}, pages = {2819}, pmid = {29905697}, title = {{Particle tracking by repetitive phase-shift interferometric super resolution microscopy}}, url = {https://opg.optica.org/abstract.cfm?URI=ol-43-12-2819}, volume = {43}, year = {2018} }
@article{bahaadini2018machine, abstract = {The detection of gravitational waves with ground-based laser-interferometric detectors requires sensitivity to changes in distance much smaller than the diameter of atomic nuclei. Though sophisticated machinery and techniques have been developed over the past few decades to isolate such instruments from non-astrophysical noise, the detectors are still susceptible to instrumental and environmental noise transients known as “glitches,” which hinder searches for transient gravitational waves. The Gravity Spy project is an effort to comprehensively classify the glitches that afflict gravitational wave detectors into morphological families by combining the strengths of machine learning algorithms and citizen scientists. This paper presents the initial Gravity Spy dataset used for citizen scientist and machine learning classification – a static, accessible, documented dataset for testing machine learning supervised classification. Previous versions of this dataset used in [8, 53] did not include all current classes and also for some of the classes, some samples were pruned and added. This set consists of time–frequency images of LIGO glitches and their associated metadata. These glitches are organized by time–frequency morphology into 22 classes for which descriptions and representative images are presented. Results from the application of state-of-the-art supervised classification methods to this dataset are presented in order to provide baselines for future glitch classification work. Standard splitting for training, validation, and testing sets are also presented to facilitate the comparison between different machine learning methods. The baseline methods are selected from both traditional and more recent deep learning approaches. An ensemble framework is developed that demonstrates that combining various classifiers can yield a more accurate model for classification. The ensemble classifier, trained with the standard training set, achieves 98.21% accuracy on the standard test set.}, author = {Bahaadini, S. and Noroozi, V. and Rohani, N. and Coughlin, S. and Zevin, M. and Smith, J.R. and Kalogera, V. and Katsaggelos, A.}, doi = {10.1016/j.ins.2018.02.068}, issn = {00200255}, journal = {Information Sciences}, keywords = {Classification,Dataset,Deep learning,Gravity Spy,Machine learning,aLIGO}, month = {may}, pages = {172--186}, publisher = {Elsevier}, title = {{Machine learning for Gravity Spy: Glitch classification and dataset}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S0020025518301634}, volume = {444}, year = {2018} }
@article{Kuan2018a, abstract = {Realizing both high temporal and spatial resolution across a large volume is a key challenge for 3D fluorescent imaging. Towards achieving this objective, we introduce an interferometric multifocus microscopy (iMFM) system, a combination of multifocus microscopy (MFM) with two opposing objective lenses. We show that the proposed iMFM is capable of simultaneously producing multiple focal plane interferometry that provides axial super-resolution and hence isotropic 3D resolution with a single exposure. We design and simulate the iMFM microscope by employing two special diffractive optical elements. The point spread function of this new iMFM microscope is simulated and the image formation model is given. For reconstruction, we use the Richardson-Lucy deconvolution algorithm with total variation regularization for 3D extended object recovery, and a maximum likelihood estimator (MLE) for single molecule tracking. A method for determining an initial axial position of the molecule is also proposed to improve the convergence of the MLE. We demonstrate both theoretically and numerically that isotropic 3D nanoscopic localization accuracy is achievable with an axial imaging range of 2um when tracking a fluorescent molecule in three dimensions and that the diffraction limited axial resolution can be improved by 3–4 times in the single shot wide-field 3D extended object recovery. We believe that iMFM will be a useful tool in 3D dynamic event imaging that requires both high temporal and spatial resolution.}, author = {He, Kuan and Huang, Xiang and Wang, Xiaolei and Yoo, Seunghwan and Ruiz, Pablo and Gdor, Itay and Ferrier, Nicola J. and Scherer, Norbert and Hereld, Mark and Katsaggelos, Aggelos K. and Cossairt, Oliver}, doi = {10.1364/OE.26.027381}, issn = {1094-4087}, journal = {Optics Express}, month = {oct}, number = {21}, pages = {27381}, pmid = {30469808}, title = {{Design and simulation of a snapshot multi-focal interferometric microscope}}, url = {https://opg.optica.org/abstract.cfm?URI=oe-26-21-27381}, volume = {26}, year = {2018} }
@article{AliBahrami2018, abstract = {Aim An automatic resuscitation rhythm annotator (ARA) would facilitate and enhance retrospective analysis of resuscitation data, contributing to a better understanding of the interplay between therapy and patient response. The objective of this study was to define, implement, and demonstrate an ARA architecture for complete resuscitation episodes, including chest compression pauses (CC-pauses) and chest compression intervals (CC-intervals). Methods We analyzed 126.5 h of ECG and accelerometer-based chest-compression depth data from 281 out-of-hospital cardiac arrest (OHCA) patients. Data were annotated by expert reviewers into asystole (AS), pulseless electrical activity (PEA), pulse-generating rhythm (PR), ventricular fibrillation (VF), and ventricular tachycardia (VT). Clinical pulse annotations were based on patient-charts and impedance measurements. An ARA was developed for CC-pauses, and was used in combination with a chest compression artefact removal filter during CC-intervals. The performance of the ARA was assessed in terms of the unweighted mean of sensitivities (UMS). Results The UMS of the ARA were 75.0% during CC-pauses and 52.5% during CC-intervals, 55-points and 32.5-points over a random guess (20% for five categories). Filtering increased the UMS during CC-intervals by 5.2-points. Sensitivities for AS, PEA, PR, VF, and VT were 66.8%, 55.8%, 86.5%, 82.1% and 83.8% during CC-pauses; and 51.1%, 34.1%, 58.7%, 86.4%, and 32.1% during CC-intervals. Conclusions A general ARA architecture was defined and demonstrated on a comprehensive OHCA dataset. Results showed that semi-automatic resuscitation rhythm annotation, which may involve further revision/correction by clinicians for quality assurance, is feasible. The performance (UMS) dropped significantly during CC-intervals and sensitivity was lowest for PEA.}, author = {Rad, Ali Bahrami and Eftest{\o}l, Trygve and Irusta, Unai and Kval{\o}y, Jan Terje and Wik, Lars and Kramer-Johansen, Jo and Katsaggelos, Aggelos K. and Engan, Kjersti}, doi = {10.1016/j.resuscitation.2017.11.035}, issn = {03009572}, journal = {Resuscitation}, keywords = {Automatic resuscitation rhythm annotator,Cardiac arrest,Cardiac rhythm classification,Cardiopulmonary resuscitation}, month = {jan}, pages = {6--12}, pmid = {29122647}, title = {{An automatic system for the comprehensive retrospective analysis of cardiac rhythms in resuscitation episodes}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S0300957217307177}, volume = {122}, year = {2018} }
@article{Nima2017b, abstract = {Artificial intelligence is revolutionizing our lives at an ever increasing pace. At the heart of this revolution is the recent advancements in deep neural networks (DNN), learning to perform sophisticated, high-level tasks. However, training DNNs requires massive amounts of data and is very computationally intensive. Gaining analytical understanding of the solutions found by DNNs can help us devise more efficient training algorithms, replacing the commonly used mthod of stochastic gradient descent (SGD). We analyze the dynamics of SGD and show that, indeed, direct computation of the solutions is possible in many cases. We show that a high performing setup used in DNNs introduces a separation of time-scales in the training dynamics, allowing SGD to train layers from the lowest (closest to input) to the highest. We then show that for each layer, the distribution of solutions found by SGD can be estimated using a class-based principal component analysis (PCA) of the layer's input. This finding allows us to forgo SGD entirely and directly derive the DNN parameters using this class-based PCA, which can be well estimated using significantly less data than SGD. We implement these results on image datasets MNIST, CIFAR10 and CIFAR100 and find that, in fact, layers derived using our class-based PCA perform comparable or superior to neural networks of the same size and architecture trained using SGD. We also confirm that the class-based PCA often converges using a fraction of the data required for SGD. Thus, using our method training time can be reduced both by requiring less training data than SGD, and by eliminating layers in the costly backpropagation step of the training.}, archivePrefix = {arXiv}, arxivId = {1703.04757}, author = {Dehmamy, Nima and Rohani, Neda and Katsaggelos, Aggelos and Nima, Dehmamy and Neda, Rohani and Aggelos, Katsaggelos}, eprint = {1703.04757}, journal = {arXiv preprint arXiv:1703.04757}, keywords = {neural networks}, month = {mar}, title = {{Separation of time scales and direct computation of weights in deep neural networks}}, url = {http://arxiv.org/abs/1703.04757}, volume = {1703}, year = {2017} }
@article{AliBahrami2017, abstract = {Objective: There is a need to monitor the heart rhythm in resuscitation to improve treatment quality. Resuscitation rhythms are categorized into: ventricular tachycardia (VT), ventricular fibrillation (VF), pulseless electrical activity (PEA), asystole (AS), and pulse-generating rhythm (PR). Manual annotation of rhythms is time-consuming and infeasible for large datasets. Our objective was to develop ECG-based algorithms for the retrospective and automatic classification of resuscitation cardiac rhythms. Methods: The dataset consisted of 1631 3-s ECG segments with clinical rhythm annotations, obtained from 298 out-of-hospital cardiac arrest patients. In total, 47 wavelet- and time-domain-based features were computed from the ECG. Features were selected using a wrapper-based feature selection architecture. Classifiers based on Bayesian decision theory, k-nearest neighbor, k-local hyperplane distance nearest neighbor, artificial neural network (ANN), and ensemble of decision trees were studied. Results: The best results were obtained for ANN classifier with Bayesian regularization backpropagation training algorithm with 14 features, which forms the proposed algorithm. The overall accuracy for the proposed algorithm was 78.5%. The sensitivities (and positive-predictive-values) for AS, PEA, PR, VF, and VT were 88.7% (91.0%), 68.9% (70.4%), 65.9% (69.0%), 86.2% (83.8%), and 78.8% (72.9%), respectively. Conclusions: The results demonstrate that it is possible to classify resuscitation cardiac rhythms automatically, but the accuracy for the organized rhythms (PEA and PR) is low. Significance: We have made an important step toward making classification of resuscitation rhythms more efficient in the sense of minimal feedback from human experts.}, author = {Rad, Ali Bahrami and Eftestol, Trygve and Engan, Kjersti and Irusta, Unai and Kvaloy, Jan Terje and Kramer-Johansen, Jo and Wik, Lars and Katsaggelos, Aggelos K.}, doi = {10.1109/TBME.2017.2688380}, issn = {0018-9294}, journal = {IEEE Transactions on Biomedical Engineering}, keywords = {Cardiac arrest,cardiac rhythm classification,cardiopulmonary resuscitation,feature extraction/selection,nested cross-validation}, month = {oct}, number = {10}, pages = {2411--2418}, pmid = {28371771}, title = {{ECG-Based Classification of Resuscitation Cardiac Rhythms for Retrospective Data Analysis}}, url = {http://ieeexplore.ieee.org/document/7890478/}, volume = {64}, year = {2017} }
@article{pouyet2017revealing, abstract = {Reading the content of hidden texts from ancient manuscripts has become an increasingly important endeavor thanks to the variety of non-destructive analytical tools and image processing routines available for this task. In this study, portable macro X-Ray Fluorescence (MA-XRF-tube), Visible Hyperspectral Imaging (HSI) together with Synchrotron based macro X-Ray Fluorescence (MA-XRF-SR) are combined with signal processing methods to reveal the biography of a degraded manuscript recycled as binding material for a 16th century printed edition of Hesiod's Works and Days. The analytical techniques allow visualizing the hidden text, revealing passages from the Institutes Justinian, a 6th century A.D codification of the Roman Law, with further marginal comments on medieval Canon Law. In addition, the identification of the materials (e.g. pigments, inks) part of the original manuscript together with their sequence of use are revealed: i) the preparation of the parchment using a Ca-based preparation layer, ii) drawing of ruled guide lines, using a Pb-based pen or ink, iii) writing of the main text using a rich Fe-gall ink with modulating color pigments (Hg-, Cu- and Pb- based) and iv) addition of two types of comments to the main text, one of the ink used for the comments being a Fe-gall ink rich in Cu.}, author = {Pouyet, E. and Devine, S. and Grafakos, T. and Kieckhefer, R. and Salvant, J. and Smieska, L. and Woll, A. and Katsaggelos, A. and Cossairt, O. and Walton, M.}, doi = {10.1016/j.aca.2017.06.016}, issn = {00032670}, journal = {Analytica Chimica Acta}, keywords = {Data fusion,Hidden manuscript,Hyperspectral,Inverse learning,Synchrotron,X-Ray Fluorescence}, month = {aug}, pages = {20--30}, pmid = {28734360}, publisher = {Elsevier}, title = {{Revealing the biography of a hidden medieval manuscript using synchrotron and conventional imaging techniques}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S0003267017307201}, volume = {982}, year = {2017} }
@article{Matthew2017a, abstract = {The image processing technique known as super-resolution (SR), which attempts to increase the effective pixel sampling density of a digital imager, has gained rapid popularity over the last decade. The majority of literature focuses on its ability to provide results that are visually pleasing to a human observer. In this paper, we instead examine the ability of SR to improve the resolution-critical capability of an imaging system to perform a classification task from a remote location, specifically from an airborne camera. In order to focus the scope of the study, we address and quantify results for the narrow case of text classification. However, we expect the results generalize to a large set of related, remote classification tasks. We generate theoretical results through simulation, which are corroborated by experiments with a camera mounted on a DJI Phantom 3 quadcopter.}, author = {Woods, Matthew and Katsaggelos, Aggelos}, doi = {10.1364/JOSAA.34.000203}, issn = {1084-7529}, journal = {Journal of the Optical Society of America A}, month = {feb}, number = {2}, pages = {203}, pmid = {28157846}, title = {{Remote classification from an airborne camera using image super-resolution}}, url = {https://opg.optica.org/abstract.cfm?URI=josaa-34-2-203}, volume = {34}, year = {2017} }
@article{Huyen2017, abstract = {Objectives Newborn deaths are reported to be caused mainly by birth asphyxia. Information learned from ventilation and other treatment could help increase survival rate of newborns in need of resuscitation. Characteristics of manual bag-mask ventilation have been studied in our previous works. However, other resuscitation activities could have important impacts as well. This paper illustrates the classification of several predefined resuscitation activities using information from acceleration and ECG signal. Methods Time and frequency domain features were extracted from the acceleration and ECG signals. A 2-stage classifier was trained on data of manually annotated activities by observing videos of 30 resuscitation babies. Leave-one-out cross validation was used: for each fold, the classifier was trained on activities of 29 patients and tested on activities of 1 patient. Results The average accuracy of the classification of activities is 79%. Conclusions The performance of the classification algorithms indicates that it is possible to use ECG and acceleration signals to automatically derive useful information regarding resuscitation activities.}, author = {Vu, Huyen and Engan, Kjersti and Eftest{\o}l, Trygve and Katsaggelos, Aggelos and Jatosh, Samwel and Kusulla, Simeon and Mduma, Estomih and Kidanto, Hussein and Ersdal, Hege}, doi = {10.1016/j.bspc.2017.03.004}, issn = {17468094}, journal = {Biomedical Signal Processing and Control}, keywords = {Acceleration signal,Birth asphyxia,Decision tree,ECG signal,Linear discriminant analysis,Newborns,Short time energy,Wavelet packet decomposition}, month = {jul}, pages = {20--26}, title = {{Automatic classification of resuscitation activities on birth-asphyxiated newborns using acceleration and ECG signals}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S174680941730054X}, volume = {36}, year = {2017} }
@article{Xu2017, abstract = {Expectation Maximization (EM) based inference has already proven to be a very powerful tool to solve blind image deconvolution (BID) problems. Unfortunately, three important problems still impede the application of EM in BID: the undesirable saddle points and local minima caused by highly nonconvex priors, the instability around zero of some of the most interesting sparsity promoting priors, and the intrinsic high computational cost of the corresponding BID algorithm. In this paper we first show how Super Gaussian priors can be made numerically tractable around zero by introducing the family of Huber Super Gaussian priors and then present a fast EM based blind deconvolution method formulated in the image space. In the proposed computational approach, image and kernel estimation are performed by using the Alternating Direction Method of Multipliers (ADMM), which allows to exploit the advantages of FFT computation. For highly nonconvex priors, we propose a Smooth ADMM (SADMM) approach to avoid poor BID estimates. Extensive experiments demonstrate that the proposed method significantly outperforms state-of-the-art BID methods in terms of quality of the reconstructions and speed.}, author = {Zhou, Xu and Vega, Miguel and Zhou, Fugen and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1016/j.dsp.2016.08.008}, issn = {10512004}, journal = {Digital Signal Processing}, keywords = {Blind deconvolution,Image deblurring,Image restoration,Variational Bayesian}, month = {jan}, pages = {122--133}, title = {{Fast Bayesian blind deconvolution with Huber Super Gaussian priors}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S1051200416301245}, volume = {60}, year = {2017} }
@article{kemner2017integrated, author = {Kemner, K. M. and Hereld, M. and Scherer, N. and Selewa, A. and Wang, X. and Gdor, I. and Daddysman, M. and Jureller, J. and Huynh, T. and Cossairt, O. and Katsaggelos, A. and He, K. and Yoo, S. and Matsuda, N. and Glick, B. and Riviere, P. La and Austin, J. and Day, K. and Chandler, T. and Papanikou, S. and Ferrier, N. and Sholto-Douglas, D. and Gursoy, D. and Antipova, O. and Soriano, C. and O'Brien, S. and Wilton, R. and Ahrendt, A. and Asplund, M. and Zerbs, S. and Noirot, P. and Atkins, C. and Babnigg, G. and Johnson, J. and Shinde, S. and Korajczyk, P. and Noirot, M. F.}, doi = {10.1017/S1431927617002380}, issn = {1431-9276}, journal = {Microscopy and Microanalysis}, month = {jul}, number = {S1}, pages = {340--341}, publisher = {Cambridge University Press}, title = {{Integrated Dynamic 3D Imaging of Microbial Processes and Communities in Rhizosphere Environments: The Argonne Small Worlds Project}}, url = {https://academic.oup.com/mam/article/23/S1/340/6944835}, volume = {23}, year = {2017} }
@article{Marc2014, author = {Walton, Marc and Pastorelli, Gianluca and Pouyet, Emeline and Katsaggelos, Aggelos and Cossairt, Oliver and Dai, Qiqin}, doi = {10.1107/S2053273317089823}, issn = {2053-2733}, journal = {Acta Crystallographica Section A Foundations and Advances}, month = {dec}, number = {a2}, pages = {C591--C591}, title = {{Getting more for less: adaptive X-ray fluorescence sampling for imaging}}, url = {http://scripts.iucr.org/cgi-bin/paper?S2053273317089823}, volume = {73}, year = {2017} }
@article{Reza2017, abstract = {Sparse coding of images is traditionally done by cutting them into small patches and representing each patch individually over some dictionary given a pre-determined number of nonzero coefficients to use for each patch. In lack of a way to effectively distribute a total number (or global budget) of nonzero coefficients across all patches, current sparse recovery algorithms distribute the global budget equally across all patches despite the wide range of differences in structural complexity among them. In this work we propose a new framework for joint sparse representation and recovery of all image patches simultaneously. We also present two novel global hard thresholding algorithms, based on the notion of variable splitting, for solving the joint sparse model. Experimentation using both synthetic and real data shows effectiveness of the proposed framework for sparse image representation and denoising tasks. Additionally, time complexity analysis of the proposed algorithms indicate high scalability of both algorithms, making them favorable to use on large megapixel images.}, archivePrefix = {arXiv}, arxivId = {1705.09816}, author = {Borhani, Reza and Watt, Jeremy and Katsaggelos, Aggelos}, eprint = {1705.09816}, journal = {arXiv preprint arXiv:1705.09816}, month = {may}, title = {{Global hard thresholding algorithms for joint sparse image representation and denoising}}, url = {http://arxiv.org/abs/1705.09816}, year = {2017} }
@article{Qiqin2016, abstract = {In this paper, we propose two multiple-frame super-resolution (SR) algorithms based on dictionary learning (DL) and motion estimation. First, we adopt the use of video bilevel DL, which has been used for single-frame SR. It is extended to multiple frames by using motion estimation with sub-pixel accuracy. We propose a batch and a temporally recursive multi-frame SR algorithm, which improves over single-frame SR. Finally, we propose a novel DL algorithm utilizing consecutive video frames, rather than still images or individual video frames, which further improves the performance of the video SR algorithms. Extensive experimental comparisons with the state-of-the-art SR algorithms verify the effectiveness of our proposed multiple-frame video SR approach.}, author = {Dai, Qiqin and Yoo, Seunghwan and Kappeler, Armin and Katsaggelos, Aggelos K.}, doi = {10.1109/TIP.2016.2631339}, issn = {1057-7149}, journal = {IEEE Transactions on Image Processing}, keywords = {Video super-resolution,dictionary learning,motion estimation,optical flow,sparse coding}, month = {feb}, number = {2}, pages = {765--781}, pmid = {27893388}, title = {{Sparse Representation-Based Multiple Frame Video Super-Resolution}}, url = {http://ieeexplore.ieee.org/document/7752984/}, volume = {26}, year = {2017} }
@article{Michael2017a, abstract = {In this paper, we propose an iterative method to address the face identification problem with block occlusions. Our approach utilizes a robust representation based on two characteristics in order to model contiguous errors (e.g., block occlusion) effectively. The first fits to the errors a distribution described by a tailored loss function. The second describes the error image as having a specific structure (resulting in low-rank in comparison with image size). We will show that this joint characterization is effective for describing errors with spatial continuity. Our approach is computationally efficient due to the utilization of the alternating direction method of multipliers. A special case of our fast iterative algorithm leads to the robust representation method, which is normally used to handle non-contiguous errors (e.g., pixel corruption). Extensive results on representative face databases (in constrained and unconstrained environments) document the effectiveness of our method over existing robust representation methods with respect to both identification rates and computational time.}, archivePrefix = {arXiv}, arxivId = {1605.02266}, author = {Iliadis, Michael and Wang, Haohong and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1109/TIP.2017.2675206}, eprint = {1605.02266}, issn = {1057-7149}, journal = {IEEE Transactions on Image Processing}, keywords = {Face identification,Iterative reweighted coding,Low-rank estimation,Robust representation}, month = {may}, number = {5}, pages = {2203--2218}, pmid = {28252401}, title = {{Robust and Low-Rank Representation for Fast Face Identification With Occlusions}}, url = {http://ieeexplore.ieee.org/document/7864430/}, volume = {26}, year = {2017} }
@article{Qiqin2017, abstract = {X-Ray fluorescence (XRF) scanning of works of art is becoming an increasing popular non-destructive analytical method. The high quality XRF spectra is necessary to obtain significant information on both major and minor elements used for characterization and provenance analysis. However, there is a trade-off between the spatial resolution of an XRF scan and the Signal-to-Noise Ratio (SNR) of each pixel's spectrum, due to the limited scanning time. In this project, we propose an XRF image super-resolution method to address this trade-off, thus obtaining a high spatial resolution XRF scan with high SNR. We fuse a low resolution XRF image and a conventional RGB highresolution image into a product of both high spatial and high spectral resolution XRF image. There is no guarantee of a one to one mapping between XRF spectrum and RGB color since, for instance, paintings with hidden layers cannot be detected in visible but can in X-ray wavelengths. We separate the XRF image into the visible and non-visible components. The spatial resolution of the visible component is increased utilizing the high-resolution RGB image while the spatial resolution of the non-visible component is increased using a total variation superresolution method. Finally, the visible and non-visible components are combined to obtain the final result.}, author = {Dai, Qiqin and Pouyet, Emeline and Cossairt, Oliver and Walton, Marc and Katsaggelos, Aggelos K.}, doi = {10.1109/TCI.2017.2703987}, issn = {2333-9403}, journal = {IEEE Transactions on Computational Imaging}, month = {sep}, number = {3}, pages = {432--444}, title = {{Spatial-Spectral Representation for X-Ray Fluorescence Image Super-Resolution}}, url = {http://ieeexplore.ieee.org/document/7927468/}, volume = {3}, year = {2017} }
@article{Juan2017a, abstract = {Recent work in signal processing in general and image processing in particular deals with sparse representation related problems. Two such problems are of paramount importance: an overriding need for designing a well-suited overcomplete dictionary containing a redundant set of atoms-i.e., basis signals-and how to find a sparse representation of a given signal with respect to the chosen dictionary. Dictionary learning techniques, among which we find the popular K-singular value decomposition algorithm, tackle these problems by adapting a dictionary to a set of training data. A common drawback of such techniques is the need for parameter-tuning. In order to overcome this limitation, we propose a fullyautomated Bayesian method that considers the uncertainty of the estimates and produces a sparse representation of the data without prior information on the number of non-zeros in each representation vector. We follow a Bayesian approach that uses a three-tiered hierarchical prior to enforce sparsity on the representations and develop an efficient variational inference framework that reduces computational complexity. Furthermore, we describe a greedy approach that speeds up the whole process. Finally, we present experimental results that show superior performance on two different applications with real images: denoising and inpainting.}, author = {Serra, Juan G. and Testa, Matteo and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1109/TIP.2017.2681436}, issn = {1057-7149}, journal = {IEEE Transactions on Image Processing}, keywords = {Bayesian modeling,Denoising,Dictionary learning,Inpainting,Sparse representation,Variational inference,k-SVD}, month = {jul}, number = {7}, pages = {3344--3359}, pmid = {28362587}, title = {{Bayesian K-SVD Using Fast Variational Inference}}, url = {http://ieeexplore.ieee.org/document/7875464/}, volume = {26}, year = {2017} }
@article{Gursoy2017, abstract = {As x-ray and electron tomography is pushed further into the nanoscale, the limitations of rotation stages become more apparent, leading to challenges in the alignment of the acquired projection images. Here we present an approach for rapid post-acquisition alignment of these projections to obtain high quality three-dimensional images. Our approach is based on a joint estimation of alignment errors, and the object, using an iterative refinement procedure. With simulated data where we know the alignment error of each projection image, our approach shows a residual alignment error that is a factor of a thousand smaller, and it reaches the same error level in the reconstructed image in less than half the number of iterations. We then show its application to experimental data in x-ray and electron nanotomography.}, author = {Gursoy, Doga and Hong, Young P. and He, Kuan and Hujsak, Karl and Yoo, Seunghwan and Chen, Si and Li, Yue and Ge, Mingyuan and Miller, Lisa M. and Chu, Yong S. and {De Andrade}, Vincent and He, Kai and Cossairt, Oliver and Katsaggelos, Aggelos K. and Jacobsen, Chris}, doi = {10.1038/s41598-017-12141-9}, issn = {2045-2322}, journal = {Scientific Reports}, month = {sep}, number = {1}, pages = {11818}, pmid = {28924196}, title = {{Rapid alignment of nanotomography data using joint iterative reconstruction and reprojection}}, url = {https://www.nature.com/articles/s41598-017-12141-9}, volume = {7}, year = {2017} }
@article{Michael2017, abstract = {With the first direct detection of gravitational waves, the advanced laser interferometer gravitational-wave observatory (LIGO) has initiated a new field of astronomy by providing an alternative means of sensing the universe. The extreme sensitivity required to make such detections is achieved through exquisite isolation of all sensitive components of LIGO from non-gravitational-wave disturbances. Nonetheless, LIGO is still susceptible to a variety of instrumental and environmental sources of noise that contaminate the data. Of particular concern are noise features known as glitches, which are transient and non-Gaussian in their nature, and occur at a high enough rate so that accidental coincidence between the two LIGO detectors is non-negligible. Glitches come in a wide range of time-frequency-amplitude morphologies, with new morphologies appearing as the detector evolves. Since they can obscure or mimic true gravitational-wave signals, a robust characterization of glitches is paramount in the effort to achieve the gravitational-wave detection rates that are predicted by the design sensitivity of LIGO. This proves a daunting task for members of the LIGO Scientific Collaboration alone due to the sheer amount of data. In this paper we describe an innovative project that combines crowdsourcing with machine learning to aid in the challenging task of categorizing all of the glitches recorded by the LIGO detectors. Through the Zooniverse platform, we engage and recruit volunteers from the public to categorize images of time-frequency representations of glitches into pre-identified morphological classes and to discover new classes that appear as the detectors evolve. In addition, machine learning algorithms are used to categorize images after being trained on human-classified examples of the morphological classes. Leveraging the strengths of both classification methods, we create a combined method with the aim of improving the efficiency and accuracy of each individual classifier. The resulting classification and characterization should help LIGO scientists to identify causes of glitches and subsequently eliminate them from the data or the detector entirely, thereby improving the rate and accuracy of gravitational-wave observations. We demonstrate these methods using a small subset of data from LIGO's first observing run.}, archivePrefix = {arXiv}, arxivId = {1611.04596}, author = {Zevin, M. and Coughlin, S. and Bahaadini, S. and Besler, E. and Rohani, N. and Allen, S. and Cabero, M. and Crowston, K. and Katsaggelos, A. K. and Larson, S. L. and Lee, T. K. and Lintott, C. and Littenberg, T. B. and Lundgren, A. and {\O}sterlund, C and Smith, J. R. and Trouille, L. and Kalogera, V.}, doi = {10.1088/1361-6382/aa5cea}, eprint = {1611.04596}, issn = {0264-9381}, journal = {Classical and Quantum Gravity}, keywords = {LIGO,citizen science,detector characterization,gravitational waves,machine learning}, month = {mar}, number = {6}, pages = {064003}, title = {{Gravity Spy: integrating advanced LIGO detector characterization, machine learning, and citizen science}}, url = {https://iopscience.iop.org/article/10.1088/1361-6382/aa5cea}, volume = {34}, year = {2017} }
@article{Evaggelia2017, abstract = {Performance guarantees for recovery algorithms employed in sparse representations, and compressed sensing highlights the importance of incoherence. Optimal bounds of incoherence are attained by equiangular unit norm tight frames (ETFs). Although ETFs are important in many applications, they do not exist for all dimensions, while their construction has been proven extremely difficult. In this paper, we construct frames that are close to ETFs. According to results from frame and graph theory, the existence of an ETF depends on the existence of its signature matrix, that is, a symmetric matrix with certain structure and spectrum consisting of two distinct eigenvalues. We view the construction of a signature matrix as an inverse eigenvalue problem and propose a method that produces frames of any dimensions that are close to ETFs. Due to the achieved equiangularity property, the so obtained frames can be employed as spreading sequences in synchronous code-division multiple access (s-CDMA) systems, besides compressed sensing.}, author = {Tsiligianni, Evaggelia and Kondi, Lisimachos P. and Katsaggelos, Aggelos K.}, doi = {10.1186/s13634-017-0501-0}, issn = {1687-6180}, journal = {EURASIP Journal on Advances in Signal Processing}, keywords = {Compressed sensing,Equiangular unit norm tight frames,Signature matrix,Spreading sequences}, month = {dec}, number = {1}, pages = {66}, title = {{Approximate equiangular tight frames for compressed sensing and CDMA applications}}, url = {https://asp-eurasipjournals.springeropen.com/articles/10.1186/s13634-017-0501-0}, volume = {2017}, year = {2017} }
@article{Zihao2017a, abstract = {Compressed sensing has been discussed separately in spatial and temporal domains. Compressive holography has been introduced as a method that allows 3D tomographic reconstruction at different depths from a single 2D image. Coded exposure is a temporal compressed sensing method for high speed video acquisition. In this work, we combine compressive holography and coded exposure techniques and extend the discussion to 4D reconstruction in space and time from one coded captured image. In our prototype, digital in-line holography was used for imaging macroscopic, fast moving objects. The pixel-wise temporal modulation was implemented by a digital micromirror device. In this paper we demonstrate $10\times$ temporal super resolution with multiple depths recovery from a single image. Two examples are presented for the purpose of recording subtle vibrations and tracking small particles within 5 ms.}, archivePrefix = {arXiv}, arxivId = {1610.09013}, author = {Wang, Zihao and Spinoulas, Leonidas and He, Kuan and Tian, Lei and Cossairt, Oliver and Katsaggelos, Aggelos K. and Chen, Huaijin}, doi = {10.1364/OE.25.000250}, eprint = {1610.09013}, issn = {1094-4087}, journal = {Optics Express}, month = {jan}, number = {1}, pages = {250}, pmid = {28085818}, title = {{Compressive holographic video}}, url = {https://opg.optica.org/abstract.cfm?URI=oe-25-1-250}, volume = {25}, year = {2017} }
@article{Pablo2016, abstract = {Sequence labeling aims at assigning a label to every sample of a signal (or pixel of an image) while considering the sequentiality (or vicinity) of the samples. To perform this task, many works in the literature first filter and then label the data. Unfortunately, the filtering, which is performed independently from the labeling, is far from optimal and frequently makes the latter task harder. In this paper, a novel approach that trains a Gaussian process classifier and estimates the coefficients of an optimal filter jointly is presented. The new approach, based on Bayesian modeling and alternating direction method of multipliers (ADMMs) optimization, performs both tasks simultaneously. All unknowns are treated as stochastic variables, which are estimated using variational inference and filtering and labeling are linked with the use of ADMM. In the experimental section, synthetic and real experiments are presented to compare the proposed method with other existing approaches.}, author = {Ruiz, Pablo and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1109/TIP.2016.2558472}, issn = {1057-7149}, journal = {IEEE Transactions on Image Processing}, keywords = {ADMM,Bayesian Modeling,Classification,Filtering,Gaussian Processes,Variational Inference}, month = {jul}, number = {7}, pages = {3059--3072}, title = {{Joint Data Filtering and Labeling Using Gaussian Processes and Alternating Direction Method of Multipliers}}, url = {http://ieeexplore.ieee.org/document/7460233/}, volume = {25}, year = {2016} }
@article{Reza2016, abstract = {Symmetric Nonnegative Matrix Factorization (SNMF) models arise naturally as simple reformulations of many standard clustering algorithms including the popular spectral clustering method. Recent work has demonstrated that an elementary instance of SNMF provides superior clustering quality compared to many classic clustering algorithms on a variety of synthetic and real world data sets. In this work, we present novel reformulations of this instance of SNMF based on the notion of variable splitting and produce two fast and effective algorithms for its optimization using i) the provably convergent Accelerated Proximal Gradient (APG) procedure and ii) a heuristic version of the Alternating Direction Method of Multipliers (ADMM) framework. Our two algorithms present an interesting tradeoff between computational speed and mathematical convergence guarantee: while the former method is provably convergent it is considerably slower than the latter approach, for which we also provide significant but less stringent mathematical proof regarding its convergence. Through extensive experiments we show not only that the efficacy of these approaches is equal to that of the state of the art SNMF algorithm, but also that the latter of our algorithms is extremely fast being one to two orders of magnitude faster in terms of total computation time than the state of the art approach, outperforming even spectral clustering in terms of computation time on large data sets.}, archivePrefix = {arXiv}, arxivId = {1609.05342}, author = {Borhani, Reza and Watt, Jeremy and Katsaggelos, Aggelos}, eprint = {1609.05342}, journal = {arXiv preprint arXiv:1609.05342}, month = {sep}, title = {{Fast and Effective Algorithms for Symmetric Nonnegative Matrix Factorization}}, url = {http://arxiv.org/abs/1609.05342}, year = {2016} }
@article{alsaafin2016compressive, abstract = {In this work we propose a novel framework to obtain high resolution images from compressed sensing imaging systems capturing multiple low resolution images of the same scene. The proposed approach of Compressed Sensing Super Resolution (CSSR), combines existing compressed sensing reconstruction algorithms with a low-resolution to high-resolution approach based on the use of a super Gaussian regularization term. The reconstruction alternates between compressed sensing reconstruction and super resolution reconstruction, including registration parameter estimation. The image estimation subproblem is solved using majorization-minimization while the compressed sensing reconstruction becomes an l1-minimization subject to a quadratic constraint. The performed experiments on grayscale and synthetically compressed real millimeter wave images, demonstrate the capability of the proposed framework to provide very good quality super resolved images from multiple low resolution compressed acquisitions.}, author = {AlSaafin, Wael and Villena, Salvador and Vega, Miguel and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1016/j.dsp.2015.12.005}, issn = {10512004}, journal = {Digital Signal Processing}, keywords = {Compressed sensing,Image reconstruction,Passive millimeter wave images,Super resolution}, month = {mar}, pages = {180--190}, publisher = {Academic Press}, title = {{Compressive sensing super resolution from multiple observations with application to passive millimeter wave images}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S1051200415003607}, volume = {50}, year = {2016} }
@article{Armin2016, abstract = {Convolutional neural networks (CNN) are a special type of deep neural networks (DNN). They have so far been successfully applied to image super-resolution (SR) as well as other image restoration tasks. In this paper, we consider the problem of video super-resolution. We propose a CNN that is trained on both the spatial and the temporal dimensions of videos to enhance their spatial resolution. Consecutive frames are motion compensated and used as input to a CNN that provides super-resolved video frames as output. We investigate different options of combining the video frames within one CNN architecture. While large image databases are available to train deep neural networks, it is more challenging to create a large video database of sufficient quality to train neural nets for video restoration. We show that by using images to pretrain our model, a relatively small video database is sufficient for the training of our model to achieve and even improve upon the current state-of-the-art. We compare our proposed approach to current video as well as image SR algorithms.}, author = {Kappeler, Armin and Yoo, Seunghwan and Dai, Qiqin and Katsaggelos, Aggelos K.}, doi = {10.1109/TCI.2016.2532323}, issn = {2333-9403}, journal = {IEEE Transactions on Computational Imaging}, keywords = {Convolutional Neural Networks,Deep Learning,Deep Neural Networks,Video Super-Resolution}, month = {jun}, number = {2}, pages = {109--122}, title = {{Video Super-Resolution With Convolutional Neural Networks}}, url = {http://ieeexplore.ieee.org/document/7444187/}, volume = {2}, year = {2016} }
@article{Morteza2015, abstract = {In this paper, the performance of the phase space representation in interpreting the underlying dynamics of epileptic seizures is investigated and a novel patient-specific seizure detection approach is proposed based on the dynamics of EEG signals. To accomplish this, the trajectories of seizure and nonseizure segments are reconstructed in a high dimensional space using time-delay embedding method. Afterwards, Principal Component Analysis (PCA) was used in order to reduce the dimension of the reconstructed phase spaces. The geometry of the trajectories in the lower dimensions is then characterized using Poincar{\'{e}} section and seven features were extracted from the obtained intersection sequence. Once the features are formed, they are fed into a two-layer classification scheme, comprising the Linear Discriminant Analysis (LDA) and Naive Bayesian classifiers. The performance of the proposed method is then evaluated over the CHB-MIT benchmark database and the proposed approach achieved 88.27% sensitivity and 93.21% specificity on average with 25% training data. Finally, we perform comparative performance evaluations against the state-of-the-art methods in this domain which demonstrate the superiority of the proposed method.}, author = {Zabihi, Morteza and Kiranyaz, Serkan and Rad, Ali Bahrami and Katsaggelos, Aggelos K. and Gabbouj, Moncef and Ince, Turker}, doi = {10.1109/TNSRE.2015.2505238}, issn = {1534-4320}, journal = {IEEE Transactions on Neural Systems and Rehabilitation Engineering}, keywords = {Dynamics,Poincar{\'{e}} section,electroencephalography (EEG),phase space,seizure detection,two-layer classifier topology}, month = {mar}, number = {3}, pages = {386--398}, pmid = {26701865}, title = {{Analysis of High-Dimensional Phase Space via Poincar{\'{e}} Section for Patient-Specific Seizure Detection}}, url = {https://ieeexplore.ieee.org/document/7360936/}, volume = {24}, year = {2016} }
@article{AliBahrami2016, abstract = {Aim: Resuscitation guidelines recommend different treatments depending on the patient's cardiac rhythm. Rhythm interpretation is a key tool to retrospectively evaluate and improve the quality of treatment. Manual rhythm annotation is time consuming and an obstacle for handling large resuscitation datasets efficiently. The objective of this study was to develop a system for automatic rhythm interpretation by using signal processing and machine learning algorithms. Methods: Data from 302 out of hospital cardiac arrest patients were used. In total 1669 3-second artifact free ECG segments with clinical rhythm annotations were extracted. The proposed algorithms combine 32 features obtained from both wavelet- and time-domain representations of the ECG, followed by a feature selection procedure based on the wrapper method in a nested cross-validation architecture. Linear and quadratic discriminant analyses (LDA and QDA) were used to automatically classify the segments into one of five rhythm types: ventricular tachycardia (VT), ventricular fibrillation (VF), pulseless electrical activity (PEA), asystole (AS), and pulse generating rhythms (PR). Results: The overall accuracy for the best algorithm was 68%. VT, VF, and AS are recognized with sensitivities of 71%, 75%, and 79%, respectively. Sensitivities for PEA and PR were 55% and 56%, respectively, which reflects the difficulty of identifying pulse using only the ECG. Conclusions: An ECG based automatic rhythm interpreter for resuscitation has been demonstrated. The interpreter handles VT, VF and AS well, while PEA and PR discrimination poses a more difficult problem.}, author = {Rad, Ali Bahrami and Engan, Kjersti and Katsaggelos, Aggelos K. and Kval{\o}y, Jan Terje and Wik, Lars and Kramer-Johansen, Jo and Irusta, Unai and Eftest{\o}l, Trygve}, doi = {10.1016/j.resuscitation.2016.01.015}, issn = {03009572}, journal = {Resuscitation}, keywords = {Cardiac rhythm interpretation,Cardiopulmonary resuscitation,Classification,Feature extraction,Feature selection}, month = {may}, pages = {44--50}, pmid = {26891862}, title = {{Automatic cardiac rhythm interpretation during resuscitation}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S0300957216000411}, volume = {102}, year = {2016} }
@article{Xiang2016, abstract = {Because art is inherently visual, the use of imaging has long been an important way to understand its structure, form, and history. Recently, new ways of engaging with objects from our shared cultural heritage are possible with advances in computation and imaging that allow scientists to analyze art noninvasively, historians to pose new social questions about the art, and the public to explore and interact with art in ways never before possible. There is a rich history in applying image processing techniques to conventional photographic images of works of art, many of which have been highlighted in previous special issues of IEEE Signal Processing Magazine (e.g., the 2008 and 2015 July issues). Building on these contributions, this article comprises a survey of techniques where computation is central to the image acquisition process. Known as computational imaging, the methods being pioneered in this field are increasingly relevant to cultural heritage applications because they leverage advances in image processing, acquisition, and display technologies that make scientific data readily comprehensible to a broad cohort of nontechnical researchers interested in understanding the visual content of art. Presently, only a small research community undertakes computational imaging of cultural heritage. Here we aim to introduce this growing new field to a larger research community by discussing: 1) the historic background of imaging of art, 2) the burgeoning present day community of researchers interested in computational imaging in the arts, and finally, 3) our vision for the future of this new field.}, author = {Huang, Xiang and Uffelman, Erich and Cossairt, Oliver and Walton, Marc and Katsaggelos, Aggelos K.}, doi = {10.1109/MSP.2016.2581847}, issn = {1053-5888}, journal = {IEEE Signal Processing Magazine}, month = {sep}, number = {5}, pages = {130--138}, title = {{Computational Imaging for Cultural Heritage: Recent developments in spectral imaging, 3-D surface measurement, image relighting, and X-ray mapping}}, url = {http://ieeexplore.ieee.org/document/7560020/}, volume = {33}, year = {2016} }
@article{Roman2015, abstract = {We present a prototype compressive video camera that encodes scene movement using a translated binary photomask in the optical path. The encoded recording can then be used to reconstruct multiple output frames from each captured image, effectively synthesizing high speed video. The use of a printed binary mask allows reconstruction at higher spatial resolutions than has been previously demonstrated. In addition, we improve upon previous work by investigating tradeoffs in mask design and reconstruction algorithm selection. We identify a mask design that consistently provides the best performance across multiple reconstruction strategies in simulation, and verify it with our prototype hardware. Finally, we compare reconstruction algorithms and identify the best choice in terms of balancing reconstruction quality and speed.}, author = {Koller, Roman and Schmid, Lukas and Matsuda, Nathan and Niederberger, Thomas and Spinoulas, Leonidas and Cossairt, Oliver and Schuster, Guido and Katsaggelos, Aggelos K.}, doi = {10.1364/OE.23.015992}, issn = {1094-4087}, journal = {Optics Express}, month = {jun}, number = {12}, pages = {15992}, title = {{High spatio-temporal resolution video with compressed sensing}}, url = {https://opg.optica.org/abstract.cfm?URI=oe-23-12-15992}, volume = {23}, year = {2015} }
@article{Evaggelia2015, abstract = {Performance guarantees for the algorithms deployed to solve underdetermined linear systems with sparse solutions are based on the assumption that the involved system matrix has the form of an incoherent unit norm tight frame. Learned dictionaries, which are popular in sparse representations, often do not meet the necessary conditions for signal recovery. In compressed sensing (CS), recovery rates have been improved substantially with optimized projections; however, these techniques do not produce binary matrices, which are more suitable for hardware implementation. In this paper, we consider an underdetermined linear system with sparse solutions and propose a preconditioning technique that yields a system matrix having the properties of an incoherent unit norm tight frame. While existing work in preconditioning concerns greedy algorithms, the proposed technique is based on recent theoretical results for standard numerical solvers such as BP and OMP. Our simulations show that the proposed preconditioning improves the recovery rates both in sparse representations and CS; the results for CS are comparable to optimized projections.}, author = {Tsiligianni, Evaggelia and Kondi, Lisimachos P. and Katsaggelos, Aggelos K.}, doi = {10.1109/LSP.2015.2392000}, issn = {1070-9908}, journal = {IEEE Signal Processing Letters}, keywords = {Compressed sensing,incoherent unit norm tight frames,preconditioning,sparse representations}, month = {sep}, number = {9}, pages = {1239--1243}, title = {{Preconditioning for Underdetermined Linear Systems with Sparse Solutions}}, url = {http://ieeexplore.ieee.org/document/7008458/}, volume = {22}, year = {2015} }
@article{chen2015robust, abstract = {In this paper, we consider the problem of recovering jointly sparse vectors from underdetermined measurements that are corrupted by both additive noise and outliers. This can be viewed as the robust extension of the Multiple Measurement Vector (MMV) problem. To solve this problem, we propose two general approaches. As a benchmark, the first approach preprocesses the input for outlier removal and then employs state-of-the-art technologies for signal recovery. The second approach, as the main contribution of this paper, is based on formulation of an innovative regularized fitting problem. By solving the regularized fitting problem, we jointly remove outliers and recover the sparse vectors. Furthermore, by exploiting temporal smoothness among the sparse vectors, we improve noise robustness of the proposed approach and avoid the problem of over-fitting. Extensive numerical results are provided to illustrate the excellent performance of the proposed approach.}, author = {Chen, Zhaofu and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1109/TSP.2015.2403277}, issn = {1053-587X}, journal = {IEEE Transactions on Signal Processing}, keywords = {Signal reconstruction,iterative methods,optimization}, month = {apr}, number = {7}, pages = {1779--1791}, publisher = {IEEE}, title = {{Robust Recovery of Temporally Smooth Signals From Under-Determined Multiple Measurements}}, url = {http://ieeexplore.ieee.org/document/7041206/}, volume = {63}, year = {2015} }
@article{Xu2015, abstract = {Blind image deconvolution involves two key objectives: 1) latent image and 2) blur estimation. For latent image estimation, we propose a fast deconvolution algorithm, which uses an image prior of nondimensional Gaussianity measure to enforce sparsity and an undetermined boundary condition methodology to reduce boundary artifacts. For blur estimation, a linear inverse problem with normalization and nonnegative constraints must be solved. However, the normalization constraint is ignored in many blind image deblurring methods, mainly because it makes the problem less tractable. In this paper, we show that the normalization constraint can be very naturally incorporated into the estimation process by using a Dirichlet distribution to approximate the posterior distribution of the blur. Making use of variational Dirichlet approximation, we provide a blur posterior approximation that considers the uncertainty of the estimate and removes noise in the estimated kernel. Experiments with synthetic and real data demonstrate that the proposed method is very competitive to the state-of-the-art blind image restoration methods.}, author = {Zhou, Xu and Mateos, Javier and Zhou, Fugen and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1109/TIP.2015.2478407}, issn = {1057-7149}, journal = {IEEE Transactions on Image Processing}, keywords = {Blind deconvolution,Dirichlet distribution,constrained optimization,image deblurring,inverse problem,point spread function,variational distribution approximations}, month = {dec}, number = {12}, pages = {5127--5139}, title = {{Variational Dirichlet Blur Kernel Estimation}}, url = {http://ieeexplore.ieee.org/document/7265038/}, volume = {24}, year = {2015} }
@article{Aggelos2015, abstract = {In this paper, we review recent results on audiovisual (AV) fusion. We also discuss some of the challenges and report on approaches to address them. One important issue in AV fusion is how the modalities interact and influence each other. This review will address this question in the context of AV speech processing, and especially speech recognition, where one of the issues is that the modalities both interact but also sometimes appear to desynchronize from each other. An additional issue that sometimes arises is that one of the modalities may be missing at test time, although it is available at training time; for example, it may be possible to collect AV training data while only having access to audio at test time. We will review approaches to address this issue from the area of multiview learning, where the goal is to learn a model or representation for each of the modalities separately while taking advantage of the rich multimodal training data. In addition to multiview learning, we also discuss the recent application of deep learning (DL) toward AV fusion. We finally draw conclusions and offer our assessment of the future in the area of AV fusion.}, author = {Katsaggelos, Aggelos K. and Bahaadini, Sara and Molina, Rafael}, doi = {10.1109/JPROC.2015.2459017}, issn = {0018-9219}, journal = {Proceedings of the IEEE}, keywords = {Audiovisual (AV) fusion,deep learning (DL),machine learning,multimodal analysis,multiview learning,stream asynchrony}, month = {sep}, number = {9}, pages = {1635--1653}, title = {{Audiovisual Fusion: Challenges and New Approaches}}, url = {http://ieeexplore.ieee.org/document/7194741/}, volume = {103}, year = {2015} }
@article{Nicolas2015, abstract = {Yan is an ETS-domain transcription factor responsible for maintaining Drosophila eye cells in a multipotent state. Yan is at the core of a regulatory network that determines the time and place in which cells transit from multipotency to one of several differentiated lineages. Using a fluorescent reporter for Yan expression, we observed a biphasic distribution of Yan in multipotent cells, with a rapid inductive phase and slow decay phase. Transitions to various differentiated states occurred over the course of this dynamic process, suggesting that Yan expression level does not strongly determine cell potential. Consistent with this conclusion, perturbing Yan expression by varying gene dosage had no effect on cell fate transitions. However, we observed that as cells transited to differentiation, Yan expression became highly heterogeneous and this heterogeneity was transient. Signals received via the EGF Receptor were necessary for the transience in Yan noise since genetic loss caused sustained noise. Since these signals are essential for eye cells to differentiate, we suggest that dynamic heterogeneity of Yan is a necessary element of the transition process, and cell states are stabilized through noise reduction.}, author = {Pel{\'{a}}ez, Nicol{\'{a}}s and Gavalda-Miralles, Arnau and Wang, Bao and Navarro, Heliodoro Tejedor and Gudjonson, Herman and Rebay, Ilaria and Dinner, Aaron R. and Katsaggelos, Aggelos K. and Amaral, Lu{\'{i}}s A.N. and Carthew, Richard W.}, doi = {10.7554/eLife.08924}, issn = {2050-084X}, journal = {eLife}, month = {nov}, number = {NOVEMBER2015}, pmid = {26583752}, title = {{Dynamics and heterogeneity of a fate determinant during transition towards cell differentiation}}, url = {https://elifesciences.org/articles/08924}, volume = {4}, year = {2015} }
@article{LasyaPriya2015, abstract = {Introduction: Patients surviving myocardial infarction (MI) can be divided into high and low arrhythmic risk groups. Distinguishing between these two groups is of crucial importance since the high-risk group has been shown to benefit from implantable cardioverter defibrillator insertion; a costly surgical procedure with potential complications and no proven advantages for the low-risk group. Currently, markers such as left ventricular ejection fraction and myocardial scar size are used to evaluate arrhythmic risk. Methods: In this paper, we propose quantitative discriminative features extracted from late gadolinium enhanced cardiac magnetic resonance images of post-MI patients, to distinguish between 20 high-risk and 34 low-risk patients. These features include size, location, and textural information concerning the scarred myocardium. To evaluate the discriminative power of the proposed features, we used several built-in classification schemes from matrix laboratory (MATLAB) and Waikato environment for knowledge analysis (WEKA) software, including k-nearest neighbor (k-NN), support vector machine (SVM), decision tree, and random forest. Results: In Experiment 1, the leave-one-out cross-validation scheme is implemented in MATLAB to classify high- and low-risk groups with a classification accuracy of 94.44%, and an AUC of 0.965 for a feature combination that captures size, location and heterogeneity of the scar. In Experiment 2 with the help of WEKA, nested cross-validation is performed with k-NN, SVM, adjusting decision tree and random forest classifiers to differentiate high-risk and low-risk patients. SVM classifier provided average accuracy of 92.6%, and AUC of 0.921 for a feature combination capturing location and heterogeneity of the scar. Experiment 1 and Experiment 2 show that textural features from the scar are important for classification and that localization features provide an additional benefit. Conclusion: These promising results suggest that the discriminative features introduced in this paper can be used by medical professionals, or in automatic decision support systems, along with the recognized risk markers, to improve arrhythmic risk stratification in post-MI patients.}, author = {Kotu, Lasya Priya and Engan, Kjersti and Borhani, Reza and Katsaggelos, Aggelos K. and {\O}rn, Stein and Woie, Leik and Eftest{\o}l, Trygve}, doi = {10.1016/j.artmed.2015.06.001}, issn = {09333657}, journal = {Artificial Intelligence in Medicine}, keywords = {Cardiac magnetic resonance image,High and low arrhythmic risk,K-Nearest neighbor classifier,Local binary pattern,Sobel filter,Support vector machine classifier}, month = {jul}, number = {3}, pages = {205--215}, pmid = {26239472}, title = {{Cardiac magnetic resonance image-based classification of the risk of arrhythmias in post-myocardial infarction patients}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S0933365715000809}, volume = {64}, year = {2015} }
@article{Matthew2015, abstract = {The image processing technique known as superresolution (SR) has the potential to allow engineers to specify lower resolution and, therefore, less expensive cameras for a given task by enhancing the base camera's resolution. This is especially true in the remote detection and classification of objects in the environment, such as aircraft or human faces. Performing each of these tasks requires a minimum image “sharpness” which is quantified by a maximum resolvable spatial frequency, which is, in turn, a function of the camera optics, pixel sampling density, and signal-to-noise ratio. Much of the existing SR literature focuses on SR performance metrics for candidate algorithms, such as perceived image quality or peak SNR. These metrics can be misleading because they also credit deblurring and/or denoising in addition to true SR. In this paper, we propose a new, task-based metric where the performance of an SR algorithm is, instead, directly tied to the probability of successfully detecting critical spatial frequencies within the scene.}, author = {Woods, Matthew and Katsaggelos, Aggelos K.}, doi = {10.1364/JOSAA.32.002002}, issn = {1084-7529}, journal = {Journal of the Optical Society of America A}, month = {nov}, number = {11}, pages = {2002}, title = {{Spatial-frequency-based metric for image superresolution}}, url = {https://opg.optica.org/abstract.cfm?URI=josaa-32-11-2002}, volume = {32}, year = {2015} }
@article{Bruno2013, abstract = {In this paper we provide a review of the recent literature on Bayesian Blind Image Deconvolution (BID) methods. We believe that two events have marked the recent history of BID: the predominance of Variational Bayes (VB) inference as a tool to solve BID problems and the increasing interest of the computer vision community in solving BID problems. VB inference in combination with recent image models like the ones based on Super Gaussian (SG) and Scale Mixture of Gaussians (SMG) representations have led to the use of very general and powerful tools to provide clear images from blurry observations. In the provided review emphasis is paid on VB inference and the use of SG and SMG models with coverage of recent advances in sampling methods. We also provide examples of current state of the art BID methods and discuss problems that very likely will mark the near future of BID.}, author = {Ruiz, Pablo and Zhou, Xu and Mateos, Javier and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1016/j.dsp.2015.04.012}, isbn = {9780992862602 22195491 , issue = 10}, issn = {10512004}, journal = {Digital Signal Processing}, keywords = {Bayesian modeling,Blind deconvolution,Image deblurring,Image restoration,Variational Bayesian}, month = {dec}, pages = {116--127}, title = {{Variational Bayesian Blind Image Deconvolution: A review}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S105120041500144X}, volume = {47}, year = {2015} }
@article{Pablo2013a, abstract = {In recent years, kernel methods, in particular support vector machines (SVMs), have been successfully introduced to remote sensing image classification. Their properties make them appropriate for dealing with a high number of image features and a low number of available labeled spectra. The introduction of alternative approaches based on (parametric) Bayesian inference has been quite scarce in the more recent years. Assuming a particular prior data distribution may lead to poor results in remote sensing problems because of the specificities and complexity of the data. In this context, the emerging field of nonparametric Bayesian methods constitutes a proper theoretical framework to tackle the remote sensing image classification problem. This paper exploits the Bayesian modeling and inference paradigm to tackle the problem of kernel-based remote sensing image classification. This Bayesian methodology is appropriate for both finite- and infinite-dimensional feature spaces. The particular problem of active learning is addressed by proposing an incremental/active learning approach based on three different approaches: 1) the maximum differential of entropies; 2) the minimum distance to decision boundary; and 3) the minimum normalized distance. Parameters are estimated by using the evidence Bayesian approach, the kernel trick, and the marginal distribution of the observations instead of the posterior distribution of the adaptive parameters. This approach allows us to deal with infinite-dimensional feature spaces. The proposed approach is tested on the challenging problem of urban monitoring from multispectral and synthetic aperture radar data and in multiclass land cover classification of hyperspectral images, in both purely supervised and active learning settings. Similar results are obtained when compared to SVMs in the supervised mode, with the advantage of providing posterior estimates for classification and automatic parameter learning. Comparison with random sampling as well as standard active learning methods such as margin sampling and entropy-query-by-bagging reveals a systematic overall accuracy gain and faster convergence with the number of queries. {\textcopyright} 2013 IEEE.}, author = {Ruiz, Pablo and Mateos, Javier and Camps-Valls, Gustavo and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1109/TGRS.2013.2258468}, issn = {0196-2892}, journal = {IEEE Transactions on Geoscience and Remote Sensing}, keywords = {Bayesian inference,Incremental/active learning,Multispectral image segmentation,Supervised classification}, month = {apr}, number = {4}, pages = {2186--2196}, title = {{Bayesian Active Remote Sensing Image Classification}}, url = {http://ieeexplore.ieee.org/document/6521357/}, volume = {52}, year = {2014} }
@article{Lei2014, abstract = {Our work addresses the problem of analyzing and understanding dynamic video scenes. A two-level motion pattern mining approach is proposed. At the first level, activities are modeled as distributions over patch-based features, including spatial location, moving direction, and speed. At the second level, traffic states are modeled as distributions over activities. Both patterns are shared among video clips. Compared to other works, one advantage of our method is that moving speed is considered to describe visual word. The other advantage is that traffic states are detected and assigned to every video frame. These enable finer semantic interpretation, more precise video segmentation, and anomaly detection. Specifically, every video frame is labeled by a certain traffic state, and the video is segmented frame by frame accordingly. Moving pixels in each frame, which do not belong to any activity or cannot exist in the corresponding traffic state, are detected as anomalies. We have successfully tested our approach on some challenging traffic surveillance sequences containing both pedestrian and vehicle motions. {\textcopyright} 2000-2011 IEEE.}, author = {Song, Lei and Jiang, Fan and Shi, Zhongke and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1109/TITS.2014.2299403}, issn = {1524-9050}, journal = {IEEE Transactions on Intelligent Transportation Systems}, keywords = {Anomaly detection,Latent Dirichlet Allocation (LDA),motion pattern analysis,video segmentation,visual surveillance}, month = {jun}, number = {3}, pages = {1273--1285}, title = {{Toward Dynamic Scene Understanding by Hierarchical Motion Pattern Mining}}, url = {https://ieeexplore.ieee.org/document/6746216/}, volume = {15}, year = {2014} }
@article{chen2014variational, abstract = {In this paper we present an introduction to Variational Bayesian (VB) methods in the context of probabilistic graphical models, and discuss their application in multimedia related problems. VB is a family of deterministic probability distribution approximation procedures that offer distinct advantages over alternative approaches based on stochastic sampling and those providing only point estimates. VB inference is flexible to be applied in different practical problems, yet is broad enough to subsume as its special cases several alternative inference approaches including Maximum A Posteriori (MAP) and the Expectation-Maximization (EM) algorithm. In this paper we also show the connections between VB and other posterior approximation methods such as the marginalization-based Loopy Belief Propagation (LBP) and the Expectation Propagation (EP) algorithms. Specifically, both VB and EP are variational methods that minimize functionals based on the Kullback-Leibler (KL) divergence. LBP, traditionally developed using graphical models, can also be viewed as a VB inference procedure. We present several multimedia related applications illustrating the use and effectiveness of the VB algorithms discussed herein. We hope that by reading this tutorial the readers will obtain a general understanding of Bayesian methods and establish connections among popular algorithms used in practice. {\textcopyright} 1999-2012 IEEE.}, author = {Chen, Zhaofu and Babacan, S. Derin and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1109/TMM.2014.2307692}, issn = {1520-9210}, journal = {IEEE Transactions on Multimedia}, keywords = {Bayes methods,graphical models,inverse problems,multimedia signal processing,variational Bayes}, month = {jun}, number = {4}, pages = {1000--1017}, publisher = {IEEE}, title = {{Variational Bayesian Methods For Multimedia Problems}}, url = {http://ieeexplore.ieee.org/document/6747301/}, volume = {16}, year = {2014} }
@article{Salvador2014, abstract = {A new Bayesian Super-Resolution (SR) image registration and reconstruction method is proposed. The new method utilizes a prior distribution based on a general combination of spatially adaptive, or non-stationary, image filters, which includes an adaptive local strength parameter able to preserve both image edges and textures. With the application of variational techniques, the proposed method allows for the automatic estimation of all problem unknowns. An experimental comparison between state of the art methods and the proposed SR approach has been performed on both synthetic and real images. {\textcopyright} 2014 Elsevier Inc.}, author = {Villena, S. and Vega, M. and Molina, R. and Katsaggelos, A.K.}, doi = {10.1016/j.dsp.2014.05.017}, issn = {10512004}, journal = {Digital Signal Processing}, keywords = {Bayesian methods,Parameter estimation,Super-resolution,Total variation,Variational methods}, month = {sep}, pages = {1--10}, title = {{A non-stationary image prior combination in super-resolution}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S1051200414001882}, volume = {32}, year = {2014} }
@article{Martin2014, abstract = {The ability to accurately estimate effective connectivity among brain regions from neuroimaging data could help answering many open questions in neuroscience. We propose a method which uses causality to obtain a measure of effective connectivity from fMRI data. The method uses a vector autoregressive model for the latent variables describing neuronal activity in combination with a linear observation model based on a convolution with a hemodynamic response function. Due to the employed modeling, it is possible to efficiently estimate all latent variables of the model using a variational Bayesian inference algorithm. The computational efficiency of the method enables us to apply it to large scale problems with high sampling rates and several hundred regions of interest. We use a comprehensive empirical evaluation with synthetic and real fMRI data to evaluate the performance of our method under various conditions. {\textcopyright} 2014 Luessi, Babacan, Molina, Booth and Katsaggelos.}, author = {Luessi, Martin and Babacan, S. Derin and Molina, Rafael and Booth, James R. and Katsaggelos, Aggelos K.}, doi = {10.3389/fninf.2014.00045}, issn = {1662-5196}, journal = {Frontiers in Neuroinformatics}, keywords = {Causality,Connectivity,Granger causality,Variational Bayesian method,fMRI}, month = {may}, number = {MAY}, pages = {45 , publisher = Frontiers Media SA}, title = {{Variational Bayesian causal connectivity analysis for fMRI}}, url = {http://journal.frontiersin.org/article/10.3389/fninf.2014.00045/abstract}, volume = {8}, year = {2014} }
@article{Pablo2014b, author = {Ruiz, Pablo and Madero-Orozco, Hiram and Mateos, Javier and {Osiris Vergara-Villegas}, Osslan and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1016/j.sigpro.2013.09.027}, issn = {01651684}, journal = {Signal Processing}, month = {oct}, pages = {296--308}, title = {{Combining Poisson singular integral and total variation prior models in image restoration}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S0165168413003927}, volume = {103}, year = {2014} }
@article{Zhaofu2014a, abstract = {We propose a Bayesian based algorithm to recover sparse signals from compressed noisy measurements in the presence of a smooth background component. This problem is closely related to robust principal component analysis and compressive sensing, and is found in a number of practical areas. The proposed algorithm adopts a hierarchical Bayesian framework for modeling, and employs approximate inference to estimate the unknowns. Numerical examples demonstrate the effectiveness of the proposed algorithm and its advantage over the current state-of-the-art solutions. {\textcopyright} 1994-2012 IEEE.}, author = {Chen, Zhaofu and Molina, Rafael and Katsaggelos, Aggelos K.}, chapter = {1012}, doi = {10.1109/LSP.2014.2321256}, isbn = {1070-9908 1558-2361}, issn = {1070-9908}, journal = {IEEE Signal Processing Letters}, keywords = {Bayesian algorithm,compressive sensing,robust principal component analysis}, month = {aug}, number = {8}, pages = {1012--1016}, title = {{Automated Recovery of Compressedly Observed Sparse Signals From Smooth Background}}, url = {http://ieeexplore.ieee.org/document/6808512/}, volume = {21}, year = {2014} }
@article{Ilya2014, abstract = {Automatic camera calibration has remained a hard topic in computer vision since its inception due to its reliance on the image correspondence problem. This problem becomes even more pronounced when calibrating a depth image with a color image due to a lack of simple correspondences between the two modalities. In this work, we develop a completely automatic, very fast, online algorithm that demonstrates how a consumer-grade depth camera can be calibrated with a color camera with minimal user interaction. {\textcopyright} 2013 Elsevier Inc. All rights reserved.}, author = {Mikhelson, Ilya V. and Lee, Philip G. and Sahakian, Alan V. and Wu, Ying and Katsaggelos, Aggelos K.}, doi = {10.1016/j.jvcir.2013.03.010}, issn = {10473203}, journal = {Journal of Visual Communication and Image Representation}, keywords = {Automatic,Calibration,Color cameras,Depth cameras,Fast,Online,Point cloud,Point correspondence}, month = {jan}, number = {1}, pages = {218--226}, title = {{Automatic, fast, online calibration between depth and color cameras}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S1047320313000503}, volume = {25}, year = {2014} }
@article{Evaggelia2014, abstract = {Despite the important properties of unit norm tight frames (UNTFs) and equiangular tight frames (ETFs), their construction has been proven extremely difficult. The few known techniques produce only a small number of such frames while imposing certain restrictions on frame dimensions. Motivated by the application of incoherent tight frames in compressed sensing (CS), we propose a methodology to construct incoherent UNTFs. When frame redundancy is not very high, the achieved maximal column correlation becomes close to the lowest possible bound. The proposed methodology may construct frames of any dimensions. The obtained frames are employed in CS to produce optimized projection matrices. Experimental results show that the proposed optimization technique improves CS signal recovery, increasing the reconstruction accuracy. Considering that the UNTFs and ETFs are important in sparse representations, channel coding, and communications, we expect that the proposed construction will be useful in other applications, besides the CS. {\textcopyright} 1963-2012 IEEE.}, author = {Tsiligianni, Evaggelia V. and Kondi, Lisimachos P. and Katsaggelos, Aggelos K.}, doi = {10.1109/TIT.2014.2308171}, issn = {0018-9448}, journal = {IEEE Transactions on Information Theory}, keywords = {Grassmannian frames,Unit norm tight frames,compressed sensing}, month = {apr}, number = {4}, pages = {2319--2330}, title = {{Construction of Incoherent Unit Norm Tight Frames With Application to Compressed Sensing}}, url = {http://ieeexplore.ieee.org/document/6748087/}, volume = {60}, year = {2014} }
@article{Cheuk2014, author = {Chan, Cheuk L. and Katsaggelos, A. K. and Sahakian, A. V.}, isbn = {9781315078274}, journal = {Medical Imaging Syst Tech and Ap: Cardiovascular Systems}, pages = {93--146}, title = {{Techniques in image sequence filtering for clinical angiography}}, year = {2014} }
@article{Sotirios2014, abstract = {This paper describes the use of a customized algorithm for the colorization of historical black and white photographs documenting earlier states of paintings. This study specifically focuses on Pablo Picasso's mid-century Mediterranean masterpiece La Joie de Vivre, 1946 (Mus{\'{e}}e Picasso, Antibes, France). The custom-designed algorithm allows computer-controlled spreading of color information on a digital image of black and white historical photographs to obtain accurate color renditions. Expert observation of the present state of the painting, coupled with stratigraphic information from cross sections allows the attribution of color information to selected pixels in the digitized images. The algorithm uses the localized color information and the grayscale intensities of the black and white historical photographs to formulate a set of equations for the missing color values of the remaining pixels. The computational resolution of such equations allows an accurate colorization that preserves brushwork and shading. This new method is proposed as a valuable alternative to the use of commercial software to apply flat areas of color, which is currently the most common practice for colorization efforts in the conservation community. Availability of such colorized images enhances the art-historical understanding of the works and might lead to better-informed treatment. {\textcopyright} The International Institute for Conservation of Historic and Artistic Works 2014.}, author = {Tsaftaris, Sotirios A. and Casadio, Francesca and Andral, Jean-Louis and Katsaggelos, Aggelos K.}, doi = {10.1179/2047058413Y.0000000104}, issn = {0039-3630}, journal = {Studies in Conservation}, keywords = {Colorization algorithm,Cultural heritage,Historical photographs,Image processing,Pablo Picasso}, month = {may}, number = {3}, pages = {125--135}, title = {{A novel visualization tool for art history and conservation: Automated colorization of black and white archival photographs of works of art}}, url = {http://www.tandfonline.com/doi/full/10.1179/2047058413Y.0000000104}, volume = {59}, year = {2014} }
@article{Tao2013, abstract = {Compressive sensing (CS) is an innovative technology, allowing us to capture signals with significantly fewer samples than those required by classical Nyquist theory. We propose a novel adaptive video compressive sensing algorithm to exploit the potential of CS in video acquisition. Each frame is divided into blocks to take advantage of its inhomogeneity. We first classify the blocks into one of three types based on their texture complexity and their temporal difference from neighboring frames based on which we determine the number of required measurements. In the reconstruction process, we use the measurements made for the later frames to assist the recovery of previous ones, thus ensuring improved reconstruction quality even when the number of measurements for each frame is limited. Our experimental results demonstrate that we not only obtain significant visual quality improvement but also achieve at least 2.5 dB gain in peak signal- to-noise ratio compared with the existing video compressive sensing algorithms. {\textcopyright} SPIE and IS&T.}, author = {Li, Tao and Wang, Xiaohua and Wang, Weihe and Katsaggelos, Aggelos K.}, doi = {10.1117/1.JEI.22.4.043003}, issn = {1017-9909}, journal = {Journal of Electronic Imaging}, month = {oct}, number = {4}, pages = {043003}, title = {{Compressive video sensing with limited measurements}}, url = {http://electronicimaging.spiedigitallibrary.org/article.aspx?doi=10.1117/1.JEI.22.4.043003}, volume = {22}, year = {2013} }
@article{xin2013laplacian, abstract = {Visual query-by-capture applications call for a compact visual descriptor with minimum descriptor length. Preserving the visual identification performance while minimising the bit rate is a focus of the on-going MPEG7 CDVS (Compact Descriptors for Visual Search) standardisation effort. In this paper we tackle this problem by adopting Laplacian embedding for SIFT feature compression and employing topology verification based on a novel graph cut measure. In contrast to previous feature compression schemes, we approach the problem by finding a Laplacian embedding that preserves the nearest neighbour relations in feature space. Furthermore, we develop an efficient yet effective topology verification (TV) scheme to perform spatial consistency checking. In contrast to previous works on geometric verification, instead of enumerating all possible combinations of coordinate alignments of an image pair, this TV solution verifies possibly misaligned coordinate sets with a learning method which acquires a proper boundary between the topology representation of matched and non-matched image pairs. Furthermore, this TV solution is invariant to in-plane rotation, scaling and is quite resilient to a range of out-of-plane rotations. The proposed Laplacian embedding and Topological verification scheme are tested with the CDVS dataset and are found to be effective. {\textcopyright} 2012 Elsevier B.V.}, author = {Xin, Xin and Li, Zhu and Katsaggelos, Aggelos K.}, doi = {10.1016/j.image.2012.11.003}, issn = {09235965}, journal = {Signal Processing: Image Communication}, keywords = {Geometrical re-ranking,Laplacian embedding,Mobile visual search,Point set topology,Visual identification}, month = {apr}, number = {4}, pages = {323--333}, publisher = {Elsevier}, title = {{Laplacian embedding and key points topology verification for large scale mobile visual identification}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S0923596512002056}, volume = {28}, year = {2013} }
@article{Martin2013, abstract = {In the simultaneous sparse approximation problem, several latent vectors corresponding to independent random realizations from a common sparsity profile are recovered from an undercomplete set of measurements. In this paper, we address an extension of this problem, where in addition to the common sparsity profile, the vectors of interest are assumed to have a high correlation among each other. Specifically, we consider the case when the non-zero rows in the combined latent signal vectors are considered to be temporally smooth signals. We present a Bayesian formulation of the problem and develop a greedy inference algorithmbased on sparse Bayesian learning for independent observations. A difficulty is that unlike for existing greedy methods, there is no closed form expression for the maximizer of the objective function in the greedy algorithm when row correlations are introduced. We derive two methods to maximize the objective function, one based on the EM algorithm and another on a fixed-point iteration. Empirical results show that the proposed method provides better reconstruction results compared to existing methods, especially when the signal-to-noise ratio is low and the latent signal vectors are highly correlated. We also demonstrate the application of the proposed method to source localization in magnetoencephalography, where it obtains a temporally smooth solution with accurate localization of the brain activity. {\textcopyright} 1991-2012 IEEE.}, author = {Luessi, Martin and Babacan, S. Derin and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1109/TSP.2013.2280441}, issn = {1053-587X}, journal = {IEEE Transactions on Signal Processing}, keywords = {Bayesian methods,MEG/EEG source localization,Sparse Bayesian learning,Sparse signal recovery,Sparsity}, month = {nov}, number = {22}, pages = {5716--5729}, title = {{Bayesian Simultaneous Sparse Approximation With Smooth Signals}}, url = {http://ieeexplore.ieee.org/document/6588611/}, volume = {61}, year = {2013} }
@article{ye2013wireless, abstract = {A wireless video surveillance system consists of three major components: 1) the video capture and preprocessing; 2) the video compression and transmission in wireless sensor networks; and 3) the video analysis at the receiving end. A myriad of research works have been dedicated to this field due to its increasing popularity in surveillance applications. This survey provides a comprehensive overview of existing state-of-the-Art technologies developed for wireless video surveillance, based on the in-depth analysis of the requirements and challenges in current systems. Specifically, the physical network infrastructure for video transmission over wireless channel is analyzed. The representative technologies for video capture and preliminary vision tasks are summarized. For video compression and transmission over the wireless networks, the ultimate goal is to maximize the received video quality under the resource limitation. This is also the main focus of this survey. We classify different schemes into categories including unequal error protection, error resilience, scalable video coding, distributed video coding, and cross-layer control. Crosslayer control proves to be a desirable measure for system-level optimal resource allocation. At the receiver's end, the received video is further processed for higher-level vision tasks, and the security and privacy issues in surveillance applications are also discussed. {\textcopyright} 2013 IEEE.}, author = {Ye, Yun and Ci, Song and Katsaggelos, Aggelos K. and Liu, Yanwei and Qian, Yi and {Yun Ye} and {Song Ci} and Katsaggelos, Aggelos K. and {Yanwei Liu} and {Yi Qian}}, doi = {10.1109/ACCESS.2013.2282613}, issn = {2169-3536}, journal = {IEEE Access}, keywords = {Cross-layer control,Multimedia communications,Video analysis,Video surveillance,Wireless sensor networks}, pages = {646--660}, publisher = {IEEE}, title = {{Wireless Video Surveillance: A Survey}}, url = {http://ieeexplore.ieee.org/document/6603291/}, volume = {1}, year = {2013} }
@article{Changhun2013, author = {Cho, Changhun and Katsaggelos, Aggelos K and Paik, Joonki}, journal = {IEIE Transactions on Smart Processing and Computing}, keywords = {fast discrete curvelet transform,fdct,image restoration,vaguelette-curvelet decomposition}, number = {3}, pages = {140--147}, title = {{The Vaguelette-Curvelet Decomposition for Image Deblurring}}, volume = {2}, year = {2013} }
@article{Lu2013, abstract = {In general, subpixel-based downsampling can achieve higher apparent resolution of the down-sampled images on LCD or OLED displays than pixel-based downsampling. With the frequency domain analysis of subpixel-based downsampling, we discover special characteristics of the luma-chroma color transform choice for monochrome images. With these, we model the anti-aliasing filter design for subpixel-based monochrome image downsampling as a human visual system-based optimization problem with a two-term cost function and obtain a closed-form solution. One cost term measures the luminance distortion and the other term measures the chrominance aliasing in our chosen luma-chroma space. Simulation results suggest that the proposed method can achieve sharper down-sampled gray/font images compared with conventional pixel and subpixel-based methods, without noticeable color fringing artifacts. {\textcopyright} 1992-2012 IEEE.}, author = {Fang, Lu and Au, Oscar C. and Cheung, Ngai-Man and Katsaggelos, Aggelos K. and Li, Houqiang and Zou, Feng}, doi = {10.1109/TIP.2013.2262288}, issn = {1057-7149}, journal = {IEEE Transactions on Image Processing}, keywords = {Subpixel rendering,down-sampling,human visual system,improve resolution}, month = {oct}, number = {10}, pages = {3818--3829}, title = {{Luma-Chroma Space Filter Design for Subpixel-Based Monochrome Image Downsampling}}, url = {http://ieeexplore.ieee.org/document/6514934/}, volume = {22}, year = {2013} }
@article{Amizic2013, author = {Amizic, Bruno and Spinoulas, Leonidas and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1109/TIP.2013.2266100}, issn = {1057-7149}, journal = {IEEE Transactions on Image Processing}, month = {oct}, number = {10}, pages = {3994--4006}, title = {{Compressive Blind Image Deconvolution}}, url = {https://ieeexplore.ieee.org/document/6523098/}, volume = {22}, year = {2013} }
@article{xin2013large, abstract = {Visual search over large image repositories in real time is one of the key challenges for applications such as mobile visual query-by-capture, augmented reality, and biometrics-based identification. Search accuracy and response speed are two important performance factors. This article focuses on one of the important elements of this technology that enables large-scale visual search: indexing (or hashing). Indexing is the process of organizing a database of searchable elements into an efficiently searchable configuration. The searchable elements in our case are compact features extracted from images. This article explores a new indexing scheme. The authors optimize the design of a hash-code collision and counting scheme to enable fast search of visual features of MPEG CDVS. {\textcopyright} 1994-2012 IEEE.}, author = {Xin, Xin and Nagar, Abhishek and Srivastava, Gaurav and Li, Zhu and Fernandes, Felix and Katsaggelos, Aggelos K.}, doi = {10.1109/MMUL.2013.22}, issn = {1070-986X}, journal = {IEEE MultiMedia}, keywords = {CDVS,MPEG,hash-code collision,indexing,large-scale visual search,mobile search,multimedia,multimedia applications}, month = {apr}, number = {2}, pages = {62--71}, publisher = {IEEE}, title = {{Large Visual Repository Search with Hash Collision Design Optimization}}, url = {http://ieeexplore.ieee.org/document/6530593/}, volume = {20}, year = {2013} }
@article{Salvador2013a, abstract = {In this paper the application of image prior combinations to the Bayesian Super Resolution (SR) image registration and reconstruction problem is studied. Two sparse image priors, a Total Variation (TV) prior and a prior based on the ℓ1 norm of horizontal and vertical first-order differences (f.o.d.), are combined with a non-sparse Simultaneous Auto Regressive (SAR) prior. Since, for a given observation model, each prior produces a different posterior distribution of the underlying High Resolution (HR) image, the use of variational approximation will produce as many posterior approximations as priors we want to combine. A unique approximation is obtained here by finding the distribution on the HR image given the observations that minimizes a linear convex combination of Kullback-Leibler (KL) divergences. We find this distribution in closed form. The estimated HR images are compared with the ones obtained by other SR reconstruction methods. {\textcopyright} 2012 Elsevier Inc.}, author = {Villena, S. and Vega, M. and Babacan, S.D. and Molina, R. and Katsaggelos, A.K.}, doi = {10.1016/j.dsp.2012.10.002}, issn = {10512004}, journal = {Digital Signal Processing}, keywords = {Bayesian methods,Parameter estimation,Super resolution,Total variation,Variational methods}, month = {mar}, number = {2}, pages = {530--541}, title = {{Bayesian combination of sparse and non-sparse priors in image super resolution}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S1051200412002400}, volume = {23}, year = {2013} }
@article{chen2013application, abstract = {In this paper, we present a transportation video coding and wireless transmission system specifically tailored to automated vehicle tracking applications. By taking into account the video characteristics and the lossy nature of the wireless channels, we propose video preprocessing and error control approaches to enhance tracking performance while conserving bandwidth resources and computational power at the transmitter. Compared with current state-of-the-art H.264-based implementations, our system is shown to yield over 80% bitrate savings for comparable tracking accuracy. {\textcopyright} 2000-2011 IEEE.}, author = {Chen, Zhaofu and Tsaftaris, Sotirios A. and Soyak, Eren and Katsaggelos, Aggelos K.}, doi = {10.1109/TITS.2013.2266861}, issn = {1524-9050}, journal = {IEEE Transactions on Intelligent Transportation Systems}, keywords = {Error concealment (ERC),Forward error correction (FEC),H.264/AVC,Object tracking,Preprocessing,Surveillance centric coding,Transportation video}, month = {dec}, number = {4}, pages = {2002--2007}, publisher = {IEEE}, title = {{Application-Aware Approach to Compression and Transmission of H.264 Encoded Video for Automated and Centralized Transportation Surveillance}}, url = {https://ieeexplore.ieee.org/document/6544640}, volume = {14}, year = {2013} }
@article{Miguel2013, abstract = {In this paper we propose a space-variant blur estimation and effective denoising/deconvolution method for combining a long exposure blurry image with a short exposure noisy one. The blur in the long exposure shot is mainly caused by camera shake or object motion, and the noise in the underexposed image is introduced by the gain factor applied to the sensor when the ISO is set to an high value. Due to the space variant degradation, the image pair is divided into overlapping patches for processing. The main idea in the deconvolution algorithm is to incorporate a combination of prior image models into a spatially-varying deblurring/denoising framework which is applied to each patch. The method employs a kernel and parameter estimation method to choose between denoising or deblurring each patch. Experiments on both synthetic and real images are provided to validate the proposed approach. {\textcopyright} 2012 Elsevier B.V.}, author = {Tall{\'{o}}n, Miguel and Mateos, Javier and Babacan, S. Derin and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1016/j.inffus.2012.08.003}, issn = {15662535}, journal = {Information Fusion}, keywords = {Blind deconvolution,Image denoising,Image fusion,Low light imaging,Motion blur}, month = {oct}, number = {4}, pages = {396--409}, title = {{Space-variant blur deconvolution and denoising in the dual exposure problem}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S156625351200067X}, volume = {14}, year = {2013} }
@article{Esteban2013, abstract = {In this paper, we propose an algorithm for image restoration based on fusing nonstationary edgepreserving priors. We develop a Bayesian modeling followed by an evidence approximation inference approach for deriving the analytic foundations of the proposed restoration method. Through a series of approximations, the final implementation of the proposed image restoration algorithm is iterative and takes advantage of the Fourier domain. Simulation results over a variety of blurred and noisy standard test images indicate that the presented method comfortably surpasses the current state-of-the-art image restoration for compactly supported degradations. We finally present experimental results by digitally refocusing images captured with controlled defocus, successfully confirming the ability of the proposed restoration algorithm in recovering extra features and rich details, while still preserving edges. {\textcopyright} 2013 Optical Society of America.}, author = {Vera, Esteban and Vega, Miguel and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1364/AO.52.00D102}, issn = {1559-128X}, journal = {Applied Optics}, month = {apr}, number = {10}, pages = {D102}, title = {{Iterative image restoration using nonstationary priors}}, url = {https://opg.optica.org/abstract.cfm?URI=ao-52-10-D102}, volume = {52}, year = {2013} }
@article{Yuan2012, abstract = {Given a collection of images or a short video sequence, we define a thematic object as the key object that frequently appears and is the representative of the visual contents. Successful discovery of the thematic object is helpful for object search and tagging, video summarization and understanding, etc. However, this task is challenging because 1) there lacks a priori knowledge of the thematic objects, such as their shapes, scales, locations, and times of re-occurrences, and 2) the thematic object of interest can be under severe variations in appearances due to viewpoint and lighting condition changes, scale variations, etc. Instead of using a top-down generative model to discover thematic visual patterns, we propose a novel bottom-up approach to gradually prune uncommon local visual primitives and recover the thematic objects. A multilayer candidate pruning procedure is designed to accelerate the image data mining process. Our solution can efficiently locate thematic objects of various sizes and can tolerate large appearance variations of the same thematic object. Experiments on challenging image and video data sets and comparisons with existing methods validate the effectiveness of our method. {\textcopyright} 2011 IEEE.}, author = {Yuan, Junsong and Zhao, Gangqiang and Fu, Yun and Li, Zhu and Katsaggelos, Aggelos K. and Wu, Ying and {Junsong Yuan} and {Gangqiang Zhao} and {Yun Fu} and {Zhu Li} and Katsaggelos, Aggelos K. and {Ying Wu}}, doi = {10.1109/TIP.2011.2181952}, issn = {1057-7149}, journal = {IEEE Transactions on Image Processing}, keywords = {Image data mining,thematic object discovery}, month = {apr}, number = {4}, pages = {2207--2219}, pmid = {22207639}, title = {{Discovering Thematic Objects in Image Collections and Videos}}, url = {http://ieeexplore.ieee.org/document/6112717/}, volume = {21}, year = {2012} }
@article{Ehsan2012, abstract = {We consider the problem of foresighted multimedia resource reciprocation in peer-to-peer (P2P) networks, which consist of rational peers aiming at maximizing their individual utilities. We introduce an artificial currency (credit) to take into account the characteristics of different parts of the video signal. The resource reciprocation with the proposed credit metric can be formulated as a stochastic game, in which the peers determine their optimal strategies using Markov Decision Process (MDP) framework. The introduced framework can be applied to the general video coding, and in particular, is suitable for the scalable video where various parts of the encoded bit stream have significantly different importance for the video quality. {\textcopyright} 2012 Elsevier B.V. All rights reserved.}, author = {Maani, Ehsan and Chen, Zhaofu and Katsaggelos, Aggelos K.}, doi = {10.1016/j.image.2012.02.015}, issn = {09235965}, journal = {Signal Processing: Image Communication}, keywords = {Game theory,P2P multimedia sharing}, month = {may}, number = {5}, pages = {545--554}, title = {{A game theoretic approach to video streaming over peer-to-peer networks}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S0923596512000446}, volume = {27}, year = {2012} }
@article{babacan2012sparse, abstract = {Recovery of low-rank matrices has recently seen significant activity in many areas of science and engineering, motivated by recent theoretical results for exact reconstruction guarantees and interesting practical applications. In this paper, we present novel recovery algorithms for estimating low-rank matrices in matrix completion and robust principal component analysis based on sparse Bayesian learning (SBL) principles. Starting from a matrix factorization formulation and enforcing the low-rank constraint in the estimates as a sparsity constraint, we develop an approach that is very effective in determining the correct rank while providing high recovery performance. We provide connections with existing methods in other similar problems and empirical results and comparisons with current state-of-the-art methods that illustrate the effectiveness of this approach. {\textcopyright} 2012 IEEE.}, archivePrefix = {arXiv}, arxivId = {1102.5288}, author = {Babacan, S. Derin and Luessi, Martin and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1109/TSP.2012.2197748}, eprint = {1102.5288}, issn = {1053-587X}, journal = {IEEE Transactions on Signal Processing}, keywords = {Bayesian methods,low-rankness,matrix completion,outlier detection,robust principal component analysis,sparse Bayesian learning,sparsity,variational Bayesian inference}, month = {aug}, number = {8}, pages = {3964--3977}, publisher = {IEEE}, title = {{Sparse Bayesian Methods for Low-Rank Matrix Estimation}}, url = {http://ieeexplore.ieee.org/document/6194350/}, volume = {60}, year = {2012} }
@article{Lu2012, abstract = {A portable device such as a digital camera with a single sensor and Bayer color filter array (CFA) requires demosaicing to reconstruct a full color image. To display a high resolution image on a low resolution LCD screen of the portable device, it must be down-sampled. The two steps, demosaicing and down-sampling, influence each other. On one hand, the color artifacts introduced in demosaicing may be magnified when followed by down-sampling; on the other hand, the detail removed in the down-sampling cannot be recovered in the demosaicing. Therefore, it is very important to consider simultaneous demosaicing and down-sampling. In this paper, we propose a fast frequency-domain analysis approach for joint demosaicing and subpixel-based down-sampling (FFA-JDSD) of single sensor Bayer images. In FFA-JDSD, we integrate demosaicing into down-sampling by directly performing subpixel- based down-sampling in the Bayer domain, due to which the computational complexity is significantly reduced. We use a frequency domain analysis tool to show that the cut-off frequency of the low-pass filter for JDSD can be effectively extended beyond the Nyquist frequency, resulting in much sharper down-sampled images. Experimental results show that, compared with the methods that separately perform demosaicing and down-sampling, FFAJDSD has much less computational complexity, and can produce much sharper results at the expense of slight color fringing artifact. {\textcopyright} 2012 IEEE.}, author = {Fang, Lu and Au, Oscar C. and Chen, Yan and Katsaggelos, Aggelos K. and Wang, Hanli and Wen, Xing}, doi = {10.1109/TMM.2012.2191269}, issn = {1520-9210}, journal = {IEEE Transactions on Multimedia}, keywords = {Demosaicking,down-sampling,subpixel rendering}, month = {aug}, number = {4}, pages = {1359--1369}, title = {{Joint Demosaicing and Subpixel-Based Down-Sampling for Bayer Images: A Fast Frequency-Domain Analysis Approach}}, url = {http://ieeexplore.ieee.org/document/6171859/}, volume = {14}, year = {2012} }
@article{Miguel2012, abstract = {In this work we develop a variational framework for the combination of several prior models in Bayesian image restoration and apply it to astronomical images. Since each combination of a given observation model and a prior model produces a different posterior distribution of the underlying image, the use of variational posterior distribution approximation on each posterior will produce as many posterior approximations as priors we want to combine. A unique approximation is obtained here by finding the distribution on the unknown image given the observations that minimizes a linear convex combination of the Kullback-Leibler divergences associated with each posterior distribution. We find this distribution in closed form and also relate the proposed approach to other prior combination methods in the literature. Experimental results on both synthetic images and on real astronomical images validate the proposed approach. {\textcopyright} 2011 Elsevier B.V..}, author = {Vega, Miguel and Mateos, Javier and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1016/j.stamet.2011.04.003}, issn = {15723127}, journal = {Statistical Methodology}, keywords = {Astronomical image processing,Bayesian methods,Model combination,Variational methods}, month = {jan}, number = {1-2}, pages = {19--31}, title = {{Astronomical image restoration using variational methods and model combination}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S1572312711000347}, volume = {9}, year = {2012} }
@article{Ilya2012, abstract = {This paper presents a solution to an aiming problem in the remote sensing of vital signs using an integration of two systems. The problem is that to collect meaningful data with a millimeter-wave sensor, the antenna must be pointed very precisely at the subjects chest. Even small movements could make the data unreliable. To solve this problem, we attached a camera to the millimeter-wave antenna, and mounted this combined system on a pan/tilt base. Our algorithm initially finds a subjects face and then tracks him/her through subsequent frames, while calculating the position of the subjects chest. For each frame, the camera sends the location of the chest to the pan/tilt base, which rotates accordingly to make the antenna point at the subjects chest. This paper presents a system for concurrent tracking and data acquisition with results from some sample scenarios. {\textcopyright} 2012 IEEE.}, author = {Mikhelson, Ilya V. and Lee, Philip and Bakhtiari, Sasan and Elmer, Thomas W. and Katsaggelos, Aggelos K. and Sahakian, Alan V.}, doi = {10.1109/TITB.2012.2204760}, issn = {1089-7771}, journal = {IEEE Transactions on Information Technology in Biomedicine}, keywords = {Heart rate,human tracking,millimeter wave,patient monitoring,remote sensing}, month = {sep}, number = {5}, pages = {927--934}, pmid = {22711781}, title = {{Noncontact Millimeter-Wave Real-Time Detection and Tracking of Heart Rate on an Ambulatory Subject}}, url = {http://ieeexplore.ieee.org/document/6217314/}, volume = {16}, year = {2012} }
@article{Leonidas2012, abstract = {In this paper, we briefly describe a single detector passive millimeter-wave imaging system, which has been previously presented. The system uses a cyclic sensing matrix to acquire incoherent measurements of the observed scene and then reconstructs the image using a Bayesian approach. The cyclic nature of the sensing matrix allows for the design of a single unified and compact mask that provides all the required random masks in a convenient way, such that no mechanical mask exchange is needed. Based on this setup, we primarily propose the optimal adaptive selection of sampling submasks out of the full cyclic mask to obtain improved reconstruction results. The reconstructed images show the feasibility of the imaging system as well as its improved performance through the proposed sampling scheme. {\textcopyright} 2012 Optical Society of America.}, author = {Spinoulas, Leonidas and Qi, Jin and Katsaggelos, Aggelos K. and Elmer, Thomas W. and Gopalsami, Nachappa and Raptis, Apostolos C.}, doi = {10.1364/AO.51.006335}, issn = {1559-128X}, journal = {Applied Optics}, month = {sep}, number = {26}, pages = {6335}, title = {{Optimized compressive sampling for passive millimeter-wave imaging}}, url = {https://opg.optica.org/abstract.cfm?URI=ao-51-26-6335}, volume = {51}, year = {2012} }
@article{Nachappa2012, abstract = {Passive millimeter-wave (PMMW) imagers using a single radiometer, called single pixel imagers, employ raster scanning to produce images. A serious drawback of such a single pixel imaging system is the long acquisition time needed to produce a high-fidelity image, arising from two factors: (a) the time to scan the whole scene pixel by pixel and (b) the integration time for each pixel to achieve adequate signal to noise ratio. Recently, compressive sensing (CS) has been developed for single-pixel optical cameras to significantly reduce the imaging time and at the same time produce high-fidelity images by exploiting the sparsity of the data in some transform domain. While the efficacy of CS has been established for single-pixel optical systems, its application to PMMW imaging is not straightforward due to its (a) longer wavelength by three to four orders of magnitude that suffers high diffraction losses at finite size spatial waveform modulators and (b) weaker radiation intensity, for example, by eight orders of magnitude less than that of infrared. We present the development and implementation of a CS technique for PMMW imagers and shows a factor-of-ten increase in imaging speed. {\textcopyright} 2012 Society of Photo-Optical Instrumentation Engineers (SPIE).}, author = {Gopalsami, Nachappa and Liao, Shaolin and Elmer, Thomas W. and Koehl, Eugene R. and Heifetz, Alexander and Raptis, Apostolos C. and Spinoulas, Leonidas and Katsaggelos, Aggelos K.}, doi = {10.1117/1.OE.51.9.091614}, issn = {0091-3286}, journal = {Optical Engineering}, month = {sep}, number = {9}, pages = {091614--1}, title = {{Passive millimeter-wave imaging with compressive sensing}}, url = {http://opticalengineering.spiedigitallibrary.org/article.aspx?doi=10.1117/1.OE.51.9.091614}, volume = {51}, year = {2012} }
@article{Yun2012a, author = {Fu, Yun and Hua, Xian-Sheng and Li, Zhu and Katsaggelos, Aggelos K. and Huang, Thomas S.}, doi = {10.1109/TSMCB.2011.2179292}, issn = {1083-4419}, journal = {IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics)}, month = {apr}, number = {2}, pages = {294--297}, pmid = {22262685}, title = {{Special Issue on Subspace and Manifold Learning for Image and Video Indexing and Search}}, url = {https://ieeexplore.ieee.org/document/6129536/}, volume = {42}, year = {2012} }
@article{cortes2012variational, abstract = {Although in the last decades the use of Magnetic Resonance Imaging has grown in popularity as a tool for the structural analysis of the brain, including MRI, fMRI and recently DTI, the ElectroEncephaloGraphy (EEG) is, still today, an interesting technique for the understanding of brain organization and function. The main reason for this is that the EEG is a direct measure of brain bioelectrical activity, and such activity can be monitorized in the millisecond time window. For some situations and cognitive scenarios, such fine temporal resolution might suffice for some aspects of brain function; however, the EEG spatial resolution is very poor since it is based on a small number of scalp recordings, thus turning the source localization problem into an ill-posed one in which infinite possibilities exist for the localization of the neuronal generators. This is an old problem in computational neuroimaging; indeed, many methods have been proposed to overcome this localization. Here, by performing a Variational Bayesian Inference procedure with a generalized Gaussian prior, we come out with an algorithm that performs simultaneously the estimation of both sources and model parameters. The novelty for the inclusion of the generalized Gaussian prior allows to control the smoothness degree of the estimated sources. Finally, the suggested algorithm is validated on simulated data.}, author = {Cortes, J. M. and Lopez, A. and Molina, R. and Katsaggelos, A. K.}, doi = {10.1140/epjp/i2012-12140-9}, issn = {2190-5444}, journal = {The European Physical Journal Plus}, month = {nov}, number = {11}, pages = {140}, publisher = {Springer Berlin Heidelberg}, title = {{Variational Bayesian localization of EEG sources with generalized Gaussian priors}}, url = {http://link.springer.com/10.1140/epjp/i2012-12140-9}, volume = {127}, year = {2012} }
@article{Lu2011, abstract = {In this paper, we are concerned with image downsampling using subpixel techniques to achieve superior sharpness for small liquid crystal displays (LCDs). Such a problem exists when a high-resolution image or video is to be displayed on low-resolution display terminals. Limited by the low-resolution display, we have to shrink the image. Signal-processing theory tells us that optimal decimation requires low-pass filtering with a suitable cutoff frequency, followed by downsampling. In doing so, we need to remove many useful image details causing blurring. Subpixel-based downsampling, taking advantage of the fact that each pixel on a color LCD is actually composed of individual red, green, and blue subpixel stripes, can provide apparent higher resolution. In this paper, we use frequency-domain analysis to explain what happens in subpixel-based downsampling and why it is possible to achieve a higher apparent resolution. According to our frequency-domain analysis and observation, the cutoff frequency of the low-pass filter for subpixel-based decimation can be effectively extended beyond the Nyquist frequency using a novel antialiasing filter. Applying the proposed filters to two existing subpixel downsampling schemes called direct subpixel-based downsampling (DSD) and diagonal DSD (DDSD), we obtain two improved schemes, i.e., DSD based on frequency-domain analysis (DSD-FA) and DDSD based on frequency-domain analysis (DDSD-FA). Experimental results verify that the proposed DSD-FA and DDSD-FA can provide superior results, compared with existing subpixel or pixel-based downsampling methods. {\textcopyright} 2011 IEEE.}, author = {{Lu Fang} and Au, Oscar C. and {Ketan Tang} and Katsaggelos, Aggelos K. and Fang, Lu and Au, Oscar C. and Tang, Ketan and Katsaggelos, Aggelos K.}, doi = {10.1109/TIP.2011.2165550}, issn = {1057-7149}, journal = {IEEE Transactions on Image Processing}, keywords = {Downsampling,frequency analysis,subpixel rendering}, month = {mar}, number = {3}, pages = {1391--1405}, title = {{Antialiasing Filter Design for Subpixel Downsampling via Frequency-Domain Analysis}}, url = {http://ieeexplore.ieee.org/document/5999717/}, volume = {21}, year = {2012} }
@article{Evaggelia2012a, abstract = {In object-based video representation, video scenes are composed of several arbitrarily shaped video objects (VOs), defined by their texture, shape and motion. In error-prone communications, packet loss results in missing information at the decoder. The impact of transmission errors is minimized through error concealment. In this paper, we propose a spatial error concealment technique for recovering lost shape data. We consider a geometric shape representation consisting of the object boundary, which can be extracted from the $\alpha$-plane. Missing macroblocks result in a broken boundary. A B-spline curve is constructed to replace a missing boundary segment, based on a T-spline representation of the received boundary. We use T-splines because they produce shape-preserving approximations and do not change the characteristics of the original boundary. The representation ensures a good estimation of the first derivatives at the points touching the missing segment. Applying smoothing conditions, we manage to construct a new spline that joins smoothly with the received boundary, leading to successful concealment results. Experimental results on object shapes with different concealment difficulty demonstrate the performance of the proposed method. Comparisons with prior proposed methods are also presented. {\textcopyright} 1992-2012 IEEE.}, author = {Tsiligianni, Evaggelia and Kondi, Lisimachos P. and Katsaggelos, Aggelos K.}, doi = {10.1109/TIP.2012.2192850}, issn = {1057-7149}, journal = {IEEE Transactions on Image Processing}, keywords = {COM-ERC,Error concealment,Shape coding,T-splines}, month = {aug}, number = {8}, pages = {3573--3585}, pmid = {22481824}, title = {{Shape Error Concealment Based on a Shape-Preserving Boundary Approximation}}, url = {http://ieeexplore.ieee.org/document/6177257/}, volume = {21}, year = {2012} }
@article{Naeem2012, author = {Ramzan, Naeem and Izquierdo, Ebroul and Park, Hyunggon and Katsaggelos, Aggelos K. and Pouwelse, Johan}, doi = {10.1016/j.image.2012.04.003}, issn = {09235965}, journal = {Signal Processing: Image Communication}, month = {may}, number = {5}, pages = {379--382}, title = {{Special issue on advances in 2D/3D Video Streaming Over P2P Networks}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S0923596512000823}, volume = {27}, year = {2012} }
@article{Xiaoming2012, abstract = {Purpose: To demonstrate the feasibility of using chemical shift magnetic resonance (MR) imaging fat-water separation methods for quantitative estimation of transcatheter lipiodol delivery to liver tissues. Materials and Methods: Studies were performed in accordance with institutional Animal Care and Use Committee guidelines. Proton nuclear MR spectroscopy was first performed to identify lipiodol spectral peaks and relative amplitudes. Next, phantoms were constructed with increasing lipiodol-water volume fractions. A multiecho chemical shift-based fatwater separation method was used to quantify lipiodol concentration within each phantom. Six rats served as controls; 18 rats underwent catheterization with digital subtraction angiography guidance for intraportal infusion of a 15%, 30%, or 50% by volume lipiodol-saline mixture. MR imaging measurements were used to quantify lipiodol delivery to each rat liver. Lipiodol concentration maps were reconstructed by using both single-peak and multipeak chemical shift models. Intraclass and Spearman correlation coefficients were calculated for statistical comparison of MR imaging-based lipiodol concentration and volume measurements to reference standards (known lipiodol phantom compositions and the infused lipiodol dose during rat studies). Results: Both single-peak and multipeak measurements were well correlated to phantom lipiodol concentrations (r 2 > 0.99). Lipiodol volume measurements were progressively and significantly higher when comparing between animals receiving different doses (P < .05 for each comparison). MR imaging-based lipiodol volume measurements strongly correlated with infused dose (intraclass correlation coefficients > 0.93, P < .001) with both single- and multipeak approaches. Conclusion: Chemical shift MR imaging fat-water separation methods can be used for quantitative measurements of lipiodol delivery to liver tissues. {\textcopyright} RSNA, 2012.}, author = {Yin, Xiaoming and Guo, Yang and Li, Weiguo and Huo, Eugene and Zhang, Zhuoli and Nicolai, Jodi and Kleps, Robert A. and Hernando, Diego and Katsaggelos, Aggelos K. and Omary, Reed A. and Larson, Andrew C.}, doi = {10.1148/radiol.12111916}, issn = {0033-8419}, journal = {Radiology}, month = {jun}, number = {3}, pages = {714--722}, pmid = {22623693}, title = {{Chemical Shift MR Imaging Methods for the Quantification of Transcatheter Lipiodol Delivery to the Liver: Preclinical Feasibility Studies in a Rodent Model}}, url = {http://pubs.rsna.org/doi/10.1148/radiol.12111916}, volume = {263}, year = {2012} }
@article{amizic2012sparse, abstract = {In this article, we propose a novel blind image deconvolution method developed within the Bayesian framework. We concentrate on the restoration of blurred photographs taken by commercial cameras to show its effectiveness. The proposed method is based on a non-convex l p quasi norm with 0<p<1 that is used for the image, and a total variation (TV) based prior that is utilized for the blur. Bayesian inference is carried out by utilizing bounds for both the image and blur priors using a majorization-minimization principle. Maximum a posteriori estimates of the unknown image, blur and model parameters are calculated. Experimental results (i.e., restorations of more than 30 blurred photographs) are presented to demonstrate the advantage of the proposed method compared to existing ones. {\textcopyright} 2012 Amizic et al; licensee Springer.}, author = {Amizic, Bruno and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1186/1687-5281-2012-20}, issn = {16875176}, journal = {Eurasip Journal on Image and Video Processing}, number = {1}, pages = {1--15}, publisher = {SpringerOpen}, title = {{Sparse Bayesian blind image deconvolution with parameter estimation}}, volume = {2012}, year = {2012} }
@article{babacan2012compressive, abstract = {We propose a novel design for light field image acquisition based on compressive sensing principles. By placing a randomly coded mask at the aperture of a camera, incoherent measurements of the light passing through different parts of the lens are encoded in the captured images. Each captured image is a random linear combination of different angular views of a scene. The encoded images are then used to recover the original light field image via a novel Bayesian reconstruction algorithm. Using the principles of compressive sensing, we show that light field images with a large number of angular views can be recovered from only a few acquisitions. Moreover, the proposed acquisition and recovery method provides light field images with high spatial resolution and signal-to-noise-ratio, and therefore is not affected by limitations common to existing light field camera designs. We present a prototype camera design based on the proposed framework by modifying a regular digital camera. Finally, we demonstrate the effectiveness of the proposed system using experimental results with both synthetic and real images. {\textcopyright} 1992-2012 IEEE.}, author = {Babacan, S. Derin and Ansorge, Reto and Luessi, Martin and Mataran, Pablo Ruiz and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1109/TIP.2012.2210237}, issn = {1057-7149}, journal = {IEEE Transactions on Image Processing}, keywords = {Bayesian methods,coded aperture,compressive sensing,computational photography,image reconstruction,light fields}, month = {dec}, number = {12}, pages = {4746--4757}, publisher = {IEEE}, title = {{Compressive Light Field Sensing}}, url = {http://ieeexplore.ieee.org/document/6248701/}, volume = {21}, year = {2012} }
@inproceedings{lopez2012hyperparameters, author = {L{\'{o}}pez, Antonio and Cort{\'{e}}s, Jes{\'{u}}s M and L{\'{o}}pez-Oiler, Domingo and Molina, Rafael and Katsaggelos, Aggelos K}, booktitle = {2012 Proceedings of the 20th European Signal Processing Conference (EUSIPCO)}, organization = {IEEE}, pages = {489--493}, title = {{Hyperparameters estimation for the Bayesian localization of the EEG sources with TV priors}}, year = {2012} }
@article{babacan2012compressive, abstract = {We propose a novel design for light field image acquisition based on compressive sensing principles. By placing a randomly coded mask at the aperture of a camera, incoherent measurements of the light passing through different parts of the lens are encoded in the captured images. Each captured image is a random linear combination of different angular views of a scene. The encoded images are then used to recover the original light field image via a novel Bayesian reconstruction algorithm. Using the principles of compressive sensing, we show that light field images with a large number of angular views can be recovered from only a few acquisitions. Moreover, the proposed acquisition and recovery method provides light field images with high spatial resolution and signal-to-noise-ratio, and therefore is not affected by limitations common to existing light field camera designs. We present a prototype camera design based on the proposed framework by modifying a regular digital camera. Finally, we demonstrate the effectiveness of the proposed system using experimental results with both synthetic and real images. {\textcopyright} 1992-2012 IEEE.}, author = {Babacan, S. Derin and Ansorge, Reto and Luessi, Martin and Mataran, Pablo Ruiz and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1109/TIP.2012.2210237}, issn = {1057-7149}, journal = {IEEE Transactions on Image Processing}, keywords = {Bayesian methods,coded aperture,compressive sensing,computational photography,image reconstruction,light fields}, month = {dec}, number = {12}, pages = {4746--4757}, publisher = {IEEE}, title = {{Compressive Light Field Sensing}}, url = {http://ieeexplore.ieee.org/document/6248701/}, volume = {21}, year = {2012} }
@article{Miguel2011, abstract = {In this paper we propose a novel super-resolution based algorithm for the pansharpening of multispectral images. Within the Bayesian formulation, the proposed methodology incorporates prior knowledge on the expected characteristics of multispectral images; that is, it imposes smoothness within each band by means of the energy associated with the ℓ1 norm of vertical and horizontal first order differences of image pixel values and also takes into account the correlation among the bands of the multispectral image. The observation process is modeled using the sensor characteristics of both panchromatic and multispectral images. The method is tested on real and synthetic images, compared with other pansharpening methods, and the quality of the results assessed both qualitatively and quantitatively. {\textcopyright} 2010 Springer Science+Business Media, LLC.}, author = {Vega, Miguel and Mateos, Javier and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1007/s11265-010-0554-x}, issn = {1939-8018}, journal = {Journal of Signal Processing Systems}, keywords = {Bayesian approach,Interband correlations,Multispectral images,Pansharpening,Super-resolution,Variational methods,ℓ1 image models}, month = {dec}, number = {3}, pages = {509--523}, title = {{Super Resolution of Multispectral Images using ℓ1 Image Models and Interband Correlations}}, url = {http://link.springer.com/10.1007/s11265-010-0554-x}, volume = {65}, year = {2011} }
@article{Eren2011, abstract = {In centralized transportation surveillance systems, video is captured and compressed at low processing power remote nodes and transmitted to a central location for processing. Such compression can reduce the accuracy of centrally run automated object tracking algorithms. In typical systems, the majority of communications bandwidth is spent on encoding temporal pixel variations such as acquisition noise or local changes to lighting. We propose a tracking-aware, H.264-compliant compression algorithm that removes temporal components of low tracking interest and optimizes the quantization of frequency coefficients, particularly those that most influence trackers, significantly reducing bitrate while maintaining comparable tracking accuracy. We utilize tracking accuracy as our compression criterion in lieu of mean squared error metrics. Our proposed system is designed with low processing power and memory requirements in mind, and as such can be deployed on remote nodes. Using H.264/AVC video coding and a commonly used state-of-the-art tracker we show that our algorithm allows for over 90% bitrate savings while maintaining comparable tracking accuracy. {\textcopyright} 2011 IEEE.}, author = {Soyak, Eren and Tsaftaris, Sotirios A. and Katsaggelos, Aggelos K.}, doi = {10.1109/TCSVT.2011.2163448}, issn = {1051-8215}, journal = {IEEE Transactions on Circuits and Systems for Video Technology}, keywords = {Quantization,urban transportation video,video compression,video object tracking,video processing}, month = {oct}, number = {10}, pages = {1378--1389}, title = {{Low-Complexity Tracking-Aware H.264 Video Compression for Transportation Surveillance}}, url = {http://ieeexplore.ieee.org/document/5971775/}, volume = {21}, year = {2011} }
@article{babacan2017variational, abstract = {In this paper, we address the super resolution (SR) problem from a set of degraded low resolution (LR) images to obtain a high resolution (HR) image. Accurate estimation of the sub-pixel motion between the LR images significantly affects the performance of the reconstructed HR image. In this paper, we propose novel super resolution methods where the HR image and the motion parameters are estimated simultaneously. Utilizing a Bayesian formulation, we model the unknown HR image, the acquisition process, the motion parameters and the unknown model parameters in a stochastic sense. Employing a variational Bayesian analysis, we develop two novel algorithms which jointly estimate the distributions of all unknowns. The proposed framework has the following advantages: 1) Through the incorporation of uncertainty of the estimates, the algorithms prevent the propagation of errors between the estimates of the various unknowns; 2) the algorithms are robust to errors in the estimation of the motion parameters; and 3) using a fully Bayesian formulation, the developed algorithms simultaneously estimate all algorithmic parameters along with the HR image and motion parameters, and therefore they are fully-automated and do not require parameter tuning. We also show that the proposed motion estimation method is a stochastic generalization of the classical Lucas-Kanade registration algorithm. Experimental results demonstrate that the proposed approaches are very effective and compare favorably to state-of-the-art SR algorithms. {\textcopyright} 2011 IEEE.}, author = {Babacan, S. Derin and Molina, Rafael and Katsaggelos, Aggelos K. and {Derin Babacan}, S. and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1109/TIP.2010.2080278}, issn = {1057-7149}, journal = {IEEE Transactions on Image Processing}, keywords = {Bayesian methods,parameter estimation,super resolution,total variation,variational methods}, month = {apr}, number = {4}, pages = {984--999}, pmid = {20876021}, publisher = {CRC Press}, title = {{Variational Bayesian Super Resolution}}, url = {https://www.taylorfrancis.com/chapters/edit/10.1201/9781439819319-10/variational-bayesian-super-resolution-reconstruction-derin-babacan-rafael-molina-aggelos-katsaggelos https://www.taylorfrancis.com/books/9781439819319/chapters/10.1201/9781439819319-10 h}, volume = {20}, year = {2011} }
@article{amro2011survey, abstract = {There exist a number of satellites on different earth observation platforms, which provide multispectral images together with a panchromatic image, that is, an image containing reflectance data representative of a wide range of bands and wavelengths. Pansharpening is a pixel-level fusion technique used to increase the spatial resolution of the multispectral image while simultaneously preserving its spectral information. In this paper, we provide a review of the pan-sharpening methods proposed in the literature giving a clear classification of them and a description of their main characteristics. Finally, we analyze how the quality of the pansharpened images can be assessed both visually and quantitatively and examine the different quality measures proposed for that purpose.}, author = {Amro, Israa and Mateos, Javier and Vega, Miguel and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1186/1687-6180-2011-79}, issn = {1687-6180}, journal = {EURASIP Journal on Advances in Signal Processing}, month = {dec}, number = {1}, pages = {79}, publisher = {SpringerOpen}, title = {{A survey of classical methods and new trends in pansharpening of multispectral images}}, url = {https://asp-eurasipjournals.springeropen.com/articles/10.1186/1687-6180-2011-79}, volume = {2011}, year = {2011} }
@article{Sotirios2011, author = {Tsaftaris, Sotirios and Lister, Kristin and Fiedler, Inge and Casadio, Francesca and Katsaggelos, Aggelos}, doi = {10.1109/MSP.2011.940408}, issn = {1053-5888}, journal = {IEEE Signal Processing Magazine}, month = {may}, number = {3}, pages = {113--119}, title = {{Colorizing a Masterpiece [Applications Corner]}}, url = {http://ieeexplore.ieee.org/document/5753071/}, volume = {28}, year = {2011} }
@article{Martin2011, abstract = {In this paper, we propose a novel symmetrical EEG/fMRI fusion method which combines EEG and fMRI by means of a common generative model. We use a total variation (TV) prior to model the spatial distribution of the cortical current responses and hemodynamic response functions, and utilize spatially adaptive temporal priors to model their temporal shapes. The spatial adaptivity of the prior model allows for adaptation to the local characteristics of the estimated responses and leads to high estimation performance for the cortical current distribution and the hemodynamic response functions. We utilize a Bayesian formulation with a variational Bayesian framework and obtain a fully automatic fusion algorithm. Simulations with synthetic data and experiments with real data from a multimodal study on face perception demonstrate the performance of the proposed method. {\textcopyright} 2010 Elsevier Inc.}, author = {Luessi, Martin and Babacan, S. Derin and Molina, Rafael and Booth, James R. and Katsaggelos, Aggelos K.}, doi = {10.1016/j.neuroimage.2010.11.037}, issn = {10538119}, journal = {NeuroImage}, keywords = {M/EEG source localization,Multimodal fusion,Spatial adaptivity,Total variation,Variational Bayes}, month = {mar}, number = {1}, pages = {113--132}, pmid = {21130173}, title = {{Bayesian symmetrical EEG/fMRI fusion with spatially adaptive priors}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S1053811910014679}, volume = {55}, year = {2011} }
@article{Fan2011, abstract = {Compared to other anomalous video event detection approaches that analyze object trajectories only, we propose a context-aware method to detect anomalies. By tracking all moving objects in the video, three different levels of spatiotemporal contexts are considered, i.e., point anomaly of a video object, sequential anomaly of an object trajectory, and co-occurrence anomaly of multiple video objects. A hierarchical data mining approach is proposed. At each level, frequency-based analysis is performed to automatically discover regular rules of normal events. Events deviating from these rules are identified as anomalies. The proposed method is computationally efficient and can infer complex rules. Experiments on real traffic video validate that the detected video anomalies are hazardous or illegal according to traffic regulations. {\textcopyright} 2010 Elsevier Inc. All rights reserved.}, author = {Jiang, Fan and Yuan, Junsong and Tsaftaris, Sotirios A. and Katsaggelos, Aggelos K.}, doi = {10.1016/j.cviu.2010.10.008}, issn = {10773142}, journal = {Computer Vision and Image Understanding}, keywords = {Anomaly detection,Clustering,Context,Data mining,Video surveillance}, month = {mar}, number = {3}, pages = {323--333}, title = {{Anomalous video event detection using spatiotemporal context}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S1077314210002390}, volume = {115}, year = {2011} }
@article{babacan2010bayesian, abstract = {Photographs acquired under low-lighting conditions require long exposure times and therefore exhibit significant blurring due to the shaking of the camera. Using shorter exposure times results in sharper images but with a very high level of noise. In this paper, we address the problem of utilizing two such images in order to obtain an estimate of the original scene and present a novel blind deconvolution algorithm for solving it. We formulate the problem in a hierarchical Bayesian framework by utilizing prior knowledge on the unknown image and blur, and also on the dependency between the two observed images. By incorporating a fully Bayesian analysis, the developed algorithm estimates all necessary model parameters along with the unknown image and blur, such that no user-intervention is needed. Moreover, we employ a variational Bayesian inference procedure, which allows for the statistical compensation of errors occurring at different stages of the restoration, and also provides uncertainties of the estimates. Experimental results with synthetic and real images demonstrate that the proposed method provides very high quality restoration results and compares favorably to existing methods even though no user supervision is needed. {\textcopyright} 2006 IEEE.}, author = {Babacan, Sevket Derin and {Jingnan Wang} and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1109/TIP.2010.2052263}, issn = {1057-7149}, journal = {IEEE Transactions on Image Processing}, keywords = {Bayesian methods,blind deconvolution,image stabilization,parameter estimation,variational distribution approximations}, month = {nov}, number = {11}, pages = {2874--2888}, publisher = {IEEE}, title = {{Bayesian Blind Deconvolution From Differently Exposed Image Pairs}}, url = {http://ieeexplore.ieee.org/document/5482163/}, volume = {19}, year = {2010} }
@article{Sotirios2010a, author = {Tsaftaris, Sotirios A and Zhou, Xiangzhi and Tang, Richard and Katsaggelos, Aggelos and Li, Debiao and Dharmakumar, Rohan}, doi = {10.1186/1532-429X-12-S1-P216}, issn = {1532-429X}, journal = {Journal of Cardiovascular Magnetic Resonance}, month = {jan}, number = {S1}, pages = {P216}, title = {{Automated detection and quantification of microcirculatory oxygenation changes in the heart}}, url = {https://jcmr-online.biomedcentral.com/articles/10.1186/1532-429X-12-S1-P216}, volume = {12}, year = {2010} }
@article{Dalei2010, abstract = {Most existing works on routing for video transmission over multihop wireless networks only focus on how to satisfy the network-oriented quality-of-service (QoS), such as throughput, delay, and packet loss rate rather than application-oriented QoS such as the user-perceived video quality. Although there are some research efforts which use application-centric video quality as the routing metric, they either calculate the video quality based on some predefined rate-distortion function or model without considering the impact of video coding and decoding (including error concealment) on routing, or use exhaustive search or heuristic methods to find the optimal path, leading to high computational complexity and/or suboptimal solutions. In this paper, we propose an application-centric routing framework for real-time video transmission in multihop wireless networks, where expected video distortion is adopted as the routing metric. The major contributions of this paper are: 1) the development of an efficient routing algorithm with the routing metric expressed in terms of the expected video distortion and being calculated on-the-fly, and 2) the development of a quality-driven cross-layer optimization framework to enhance the flexibility and robustness of routing by the joint optimization of routing path selection and video coding, thereby maximizing the user-perceived video quality under a given video playback delay constraint. Both theoretical and experimental results demonstrate that the proposed quality-driven application-centric routing approach can achieve a superior performance over existing network-centric routing approaches. {\textcopyright} 2006 IEEE.}, author = {Wu, Dalei and Ci, Song and Wang, Haohong and Katsaggelos, Aggelos K.}, doi = {10.1109/TCSVT.2010.2057014}, issn = {1051-8215}, journal = {IEEE Transactions on Circuits and Systems for Video Technology}, keywords = {Cross-layer optimization,dynamic programming,error concealment,multihop wireless networks,routing,video coding}, month = {dec}, number = {12}, pages = {1721--1734}, title = {{Application-Centric Routing for Video Streaming Over MultiHop Wireless Networks}}, url = {http://ieeexplore.ieee.org/document/5508380/}, volume = {20}, year = {2010} }
@article{T2010, author = {T, Adali and A, Bovik and F, Juang and A, Katsaggelos and A, C Kot and J, Krolik and Kjray, L I U and D, Malah and V, J Mathews and H, Messer-Yaron and Et al.}, doi = {10.1109/JSTSP.2010.2040787}, issn = {1932-4553}, journal = {IEEE Journal of Selected Topics in Signal Processing}, month = {feb}, number = {1}, pages = {C2--C2}, title = {{IEEE Journal of Selected Topics in Signal Processing publication information}}, url = {http://ieeexplore.ieee.org/document/5393283/}, volume = {4}, year = {2010} }
@article{Xiaoming2010, abstract = {Accurate R2* measurements are critical for many abdominal imaging applications. Conventionally, R2* maps are derived via the monoexponential fitting of signal decay within a series of gradient-echo (GRE) images reconstructed from multichannel datasets combined using a root sum-of-squares (RSS) approach. However, the noise bias at low-SNR TEs from RSS-reconstructed data often causes the underestimation of R2* values. In phantom, ex vivo animal model and normal volunteer studies, we investigated the accuracy of low-SNR R2* measurement when combining truncation and coil combination methods. The accuracy for R2* estimations was shown to be affected by the intrinsic R2* value, SNR level and the chosen reconstruction method. The R2* estimation error was found to decrease with increasing SNR level, decreasing R2* value and the use of the optimal B1-weighted combined (OBC) image reconstruction method. Data truncation based on rigorous voxel-wise SNR estimates can reduce R2* measurement error in the setting of low SNR with fast signal decay. When optimal SNR truncation thresholds are unknown, the OBC method can provide optimal R2* measurements given the minimal truncation requirements. {\textcopyright} 2010 John Wiley & Sons, Ltd.}, author = {Yin, Xiaoming and Shah, Saurabh and Katsaggelos, Aggelos K. and Larson, Andrew C.}, doi = {10.1002/nbm.1539}, issn = {09523480}, journal = {NMR in Biomedicine}, keywords = {Multiple gradient-echo,Noise bias,Optimal B1-weighted image reconstruction,Phase array coils,R2* mapping,Root sum-of-square,Signal to noise ratios,Truncation}, month = {dec}, number = {10}, pages = {1127--1136}, pmid = {21162142}, title = {{Improved R2* measurement accuracy with absolute SNR truncation and optimal coil combination}}, url = {https://onlinelibrary.wiley.com/doi/10.1002/nbm.1539}, volume = {23}, year = {2010} }
@article{chantas2009variational, abstract = {In this paper, a new image prior is introduced and used in image restoration. This prior is based on products of spatially weighted total variations (TV). These spatial weights provide this prior with the flexibility to better capture local image features than previous TV based priors. Bayesian inference is used for image restoration with this prior via the variational approximation. The proposed restoration algorithm is fully automatic in the sense that all necessary parameters are estimated from the data and is faster than previous similar algorithms. Numerical experiments are shown which demonstrate that image restoration based on this prior compares favorably with previous state-of-the-art restoration algorithms. {\textcopyright} 2010 IEEE.}, author = {Chantas, Giannis and Galatsanos, Nikolaos P. and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1109/TIP.2009.2033398}, issn = {1057-7149}, journal = {IEEE Transactions on Image Processing}, keywords = {No Keywords.}, month = {feb}, number = {2}, pages = {351--362}, publisher = {IEEE}, title = {{Variational Bayesian Image Restoration With a Product of Spatially Weighted Total Variation Image Priors}}, url = {http://ieeexplore.ieee.org/document/5272318/}, volume = {19}, year = {2010} }
@article{Jiucai2009, author = {Jiucai, Zhang and Dalei, Wu and Song, Ci and Haohong, Wang and Aggelos, K Katsaggelos}, journal = {J. Commun.}, pages = {600--613}, title = {{Power-aware mobile multimedia: a survey}}, volume = {4}, year = {2009} }
@article{LauraAnn2009, abstract = {Hearing aid users have difficulty hearing target signals, such as speech, in the presence of competing signals or noise. Most solutions proposed to date enhance or extract target signals from background noise and interference based on either location attributes or source attributes. Location attributes typically involve arrival angles at a microphone array. Source attributes include characteristics that are specific to a signal, such as fundamental frequency, or statistical properties that differentiate signals. This paper describes a novel approach to sound source separation, called computational auditory scene analysis-enhanced beamforming (CASA-EB), that achieves increased separation performance by combining the complementary techniques of CASA (a source attribute technique) with beamforming (a location attribute technique), complementary in the sense that they use independent attributes for signal separation. CASA-EB performs sound source separation by temporally and spatially filtering a multichannel input signal, and then grouping the resulting signal components into separated signals, based on source and location attributes. Experimental results show increased signal-to-interference ratio with CASA-EB over beamforming or CASA alone. Copyright {\textcopyright} 2009 L. A. Drake et al.}, author = {Drake, L. A. and Rutledge, J. C. and Zhang, J. and Katsaggelos, A.}, doi = {10.1155/2009/403681}, issn = {1687-6180}, journal = {EURASIP Journal on Advances in Signal Processing}, month = {dec}, number = {1}, pages = {403681}, title = {{A Computational Auditory Scene Analysis-Enhanced Beamforming Approach for Sound Source Separation}}, url = {https://asp-eurasipjournals.springeropen.com/articles/10.1155/2009/403681}, volume = {2009}, year = {2009} }
@article{babacan2008variational, abstract = {In this paper, we present novel algorithms for total variation (TV) based blind deconvolution and parameter estimation utilizing a variational framework. Using a hierarchical Bayesian model, the unknown image, blur, and hyperparameters for the image, blur, and noise priors are estimated simultaneously. A variational inference approach is utilized so that approximations of the posterior distributions of the unknowns are obtained, thus providing a measure of the uncertainty of the estimates. Experimental results demonstrate that the proposed approaches provide higher restoration performance than non-TV-based methods without any assumptions about the unknown hyperparameters. {\textcopyright} 2008 IEEE.}, author = {Babacan, S. Derin and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1109/TIP.2008.2007354}, issn = {10577149}, journal = {IEEE Transactions on Image Processing}, keywords = {Bayesian methods,Blind deconvolution,Parameter estimation,Total variation (TV),Variational methods}, number = {1}, pages = {12--26}, pmid = {19095515}, publisher = {IEEE}, title = {{Variational Bayesian blind deconvolution using a total variation prior}}, volume = {18}, year = {2009} }
@article{Konstantinos2009, abstract = {A new, reduced complexity algorithm is proposed for compensating the Inter-Carrier Interference (ICI) caused by severe PHase Noise (PHN) and Residual Frequency Offset (RFO) in OFDM systems. The algorithm estimates and compensates the most significant terms of the frequency domain ICI process, which are optimally selected via a Minimum Mean Squared Error (MMSE) criterion. The algorithm requires minimal knowledge of the phase process statistics, the estimation of which is also considered. The scheme outperforms previously proposed compensation methods of similar complexity, when severe phase impairments are present. {\textcopyright} 2006 IEEE.}, author = {Nikitopoulos, Konstantinos and Stefanatos, Stelios and Katsaggelos, A.K.}, doi = {10.1109/TWC.2009.071029}, issn = {1536-1276}, journal = {IEEE Transactions on Wireless Communications}, keywords = {Frequency offset,Inter-carrier interference,OFDM,Phase noise}, month = {apr}, number = {4}, pages = {1614--1619}, title = {{Decision-aided compensation of severe phase-impairment-induced inter-carrier interference in frequency-selective OFDM}}, url = {http://ieeexplore.ieee.org/document/4907430/}, volume = {8}, year = {2009} }
@article{jiang2009dynamic, abstract = {The proposed unusual video event detection method is based on unsupervised clustering of object trajectories, which are modeled by hidden Markov models (HMM). The novelty of the method includes a dynamic hierarchical process incorporated in the trajectory clustering algorithm to prevent model overfitting and a 2-depth greedy search strategy for efficient clustering. {\textcopyright} 2009 IEEE.}, author = {{Fan Jiang} and {Ying Wu} and Katsaggelos, Aggelos K A.K. and Jiang, Fan and Wu, Ying and Katsaggelos, Aggelos K A.K.}, doi = {10.1109/TIP.2008.2012070}, issn = {1057-7149}, journal = {IEEE Transactions on Image Processing}, keywords = {Event detection,Unsupervised clustering,Video surveillance}, month = {apr}, number = {4}, pages = {907--913}, publisher = {IEEE}, title = {{A dynamic hierarchical clustering method for trajectory-based unusual video event detection}}, url = {http://ieeexplore.ieee.org/document/4798178/}, volume = {18}, year = {2009} }
@article{gao2009efficient, abstract = {With the phenomenal growth of the online and personal video repositories, an efficient and robust example-based video search solution is required to support applications like query by clip, query by capture, and repeated clip detection. In this letter, video sequences are represented as temporal trajectories via scaling and lower dimensional representation of the video frame luminance field, and a video trajectory indexing and matching scheme is developed to support video clip search. Simulation results demonstrate that the proposed approach achieves excellent performance in both response speed and precision-recall accuracy. {\textcopyright} 2009 IEEE.}, author = {Gao, Li and Li, Zhu and Katsaggelos, Aggelos and {Li Gao} and {Zhu Li} and Katsaggelos, Aggelos}, doi = {10.1109/TCSVT.2009.2026813}, issn = {1051-8215}, journal = {IEEE transactions on circuits and systems for video technology}, keywords = {Modeling,Subspace learning,Video indexing,Video retrieval}, month = {oct}, number = {10}, pages = {1566--1570}, publisher = {IEEE}, title = {{An Efficient Video Indexing and Retrieval Algorithm Using the Luminance Field Trajectory Modeling}}, url = {http://ieeexplore.ieee.org/document/5159407/}, volume = {19}, year = {2009} }
@article{Aggelos2009, abstract = {With the fast-paced development of multimedia computing technologies, multimedia services have become pervasive. However, the design methodology of multimedia communications has still been based on the Internet architecture designed for loss-sensitive delay-insensitive data services, which is no longer applicable for multimedia communications. We believe user-perceived quality is the holy grail of multimedia communications systems. Thus, designing for quality will change the traditional paradigm of multimedia communications. Quality-driven cross-layer design focuses on bridging the gap between users' experience and multimedia systems, since it has been long ignored in previous research. We also hope this special issue can spark and stimulate the research and practice on quality-driven cross-layer optimized multimedia communications.}, author = {Katsaggelos, Aggelos K. and Ci, Song and Wang, Haohong and Zhang, Qian and Argyriou, Antonios}, doi = {10.1109/TMM.2009.2025681}, issn = {1520-9210}, journal = {IEEE Transactions on Multimedia}, month = {oct}, number = {6}, pages = {1049--1051}, title = {{Special Issue on Quality-Driven Cross-Layer Design for Multimedia Communications}}, url = {http://ieeexplore.ieee.org/document/5235193/}, volume = {11}, year = {2009} }
@article{Ehsan2009b, author = {Ehsan, Maani and Aggelos, K Katsaggelos}, journal = {IEEE Transactions on Circuits and Systems for Video Technology}, pages = {407--416 , publisher = IEEE}, title = {{Unequal error protection for robust streaming of scalable video over packet lossy networks}}, volume = {20}, year = {2009} }
@article{Ehsan2008, abstract = {The newly adopted scalable extension of H.264/AVC video coding standard (SVC) demonstrates significant improvements in coding efficiency in addition to an increased degree of supported scalability relative to the scalable profiles of prior video coding standards. Due to the complicated hierarchical prediction structure of the SVC and the concept of key pictures, content-aware rate adaptation of SVC bit streams to intermediate bit rates is a nontrivial task. The concept of quality layers has been introduced in the design of the SVC to allow for fast content-aware prioritized rate adaptation. However, existing quality layer assignment methods are suboptimal and do not consider all network abstraction layer (NAL) units from different layers for the optimization. In this paper, we first propose a technique to accurately and efficiently estimate the quality degradation resulting from discarding an arbitrary number of NAL units from multiple layers of a bitstream by properly taking drift into account. Then, we utilize this distortion estimation technique to assign quality layers to NAL units for a more efficient extraction. Experimental results show that a significant gain can be achieved by the proposed scheme. {\textcopyright} 2009 IEEE.}, author = {Maani, Ehsan and Katsaggelos, Aggelos K.}, doi = {10.1109/TIP.2009.2023152}, issn = {1057-7149}, journal = {IEEE Transactions on Image Processing}, keywords = {Automatic voltage control,Bit rate,Data mining,Encoding,No Index Terms Provided,Scalability,Spatial resolution,Static VAr compensators}, month = {sep}, number = {9}, pages = {2022--2029}, publisher = {IEEE}, title = {{Optimized Bit Extraction Using Distortion Modeling in the Scalable Extension of H.264/AVC}}, url = {http://ieeexplore.ieee.org/document/4926224/}, volume = {18}, year = {2009} }
@article{wu2009quality, abstract = {Service-oriented architecture provides a solution to the increasing network complexity due to ever-growing heterogeneous networks. As the most significant component of SOA, the decision engine is to create a workflow, defined as a sequence of individual data processing entities, for providing end-to-end QoS of a given task. Although the workflow of video transmission is generally known, existing solutions are often monolithic. Furthermore, there is no decision engine to select a workflow based on the best user-perceived quality. In this article we propose a service-oriented decision engine framework, which consists of a decision engine, a performance evaluation component, and other major SOA components to support real-time video transmission over wireless multihop networks, aiming to provide the best user-perceived video quality under application-centric QoS constraints. Based on the investigation of the stateof- the-art research efforts on SOA, some key issues for wireless live video transmission are discussed, and a case study for live video transmission is given to illustrate the proposed scheme. The superior performance of the proposed service-oriented decision engine is validated by experimental results. {\textcopyright} 2006 IEEE.}, author = {Wu, Dalei and Ci, Song and Luo, Haiyan and Wang, Haohong and Katsaggelos, Aggelos and {Dalei Wu} and {Song Ci} and {Haiyan Luo} and {Haohong Wang} and Katsaggelos, Aggelos}, doi = {10.1109/MWC.2009.5281255}, issn = {1536-1284}, journal = {IEEE Wireless Communications}, month = {aug}, number = {4}, pages = {48--54}, publisher = {IEEE}, title = {{A quality-driven decision engine for live video transmission under service-oriented architecture}}, url = {http://ieeexplore.ieee.org/document/5281255/}, volume = {16}, year = {2009} }
@article{Sotirios2009, author = {Tsaftaris, S.A. and Katsaggelos, A.K.}, doi = {10.1109/TNB.2009.2026371}, issn = {1536-1241}, journal = {IEEE Transactions on NanoBioscience}, month = {sep}, number = {3}, pages = {259--270}, title = {{Retrieval Efficiency of DNA-Based Databases of Digital Signals}}, url = {http://ieeexplore.ieee.org/document/5161324/}, volume = {8}, year = {2009} }
@article{dai2009softcuts, abstract = {Designing effective image priors is of great interest to image super-resolution (SR), which is a severely under-determined problem. An edge smoothness prior is favored since it is able to suppress the jagged edge artifact effectively. However, for soft image edges with gradual intensity transitions, it is generally difficult to obtain analytical forms for evaluating their smoothness. This paper characterizes soft edge smoothness based on a novel SoftCuts metric by generalizing the Geocuts method [1]. The proposed soft edge smoothness measure can approximate the average length of all level lines in an intensity image. Thus, the total length of all level lines can be minimized effectively by integrating this new form of prior. In addition, this paper presents a novel combination of this soft edge smoothness prior and the alpha matting technique for color image SR, by adaptively normalizing image edges according to their $\alpha$-channel description. This leads to the adaptive SoftCuts algorithm, which represents a unified treatment of edges with different contrasts and scales. Experimental results are presented which demonstrate the effectiveness of the proposed method. {\textcopyright} 2009 IEEE.}, author = {{Shengyang Dai} and {Mei Han} and {Wei Xu} and {Ying Wu} and {Yihong Gong} and Katsaggelos, Aggelos K A.K. and Dai, Shengyang and Han, Mei and Xu, Wei and Wu, Ying and Gong, Yihong and Katsaggelos, Aggelos K A.K.}, doi = {10.1109/TIP.2009.2012908}, issn = {1057-7149}, journal = {IEEE Transactions on Image Processing}, keywords = {Edge smoothness,SoftCuts,Super-resolution (SR),$\alpha$-channel description}, month = {may}, number = {5}, pages = {969--981}, publisher = {IEEE}, title = {{SoftCuts: A Soft Edge Smoothness Prior for Color Image Super-Resolution}}, url = {http://ieeexplore.ieee.org/document/4808429/}, volume = {18}, year = {2009} }
@article{Martin2009, abstract = {Image thresholding is a very common image processing operation, since almost all image processing schemes need some sort of separation of the pixels into different classes. In order to determine the thresholds, most methods analyze the histogram of the image. The optimal thresholds are often found by either minimizing or maximizing an objective function with respect to the values of the thresholds. By defining two classes of objective functions for which the optimal thresholds can be found by efficient algorithms, this paper provides a framework for determining the solution approach for current and future multilevel thresholding algorithms. We show, for example, that the method proposed by Otsu and other well-known methods have objective functions belonging to these classes. By implementing the algorithms in ANSI C and comparing their execution times, we can also make quantitative statements about their performance.}, author = {Eichmann, Marco}, doi = {10.1117/1.3073891}, issn = {1017-9909}, journal = {Journal of Electronic Imaging}, month = {jan}, number = {1}, pages = {013004}, title = {{Framework for efficient optimal multilevel image thresholding}}, url = {http://electronicimaging.spiedigitallibrary.org/article.aspx?doi=10.1117/1.3073891}, volume = {18}, year = {2009} }
@article{Rafael2008, author = {Molina, Rafael and Vega, Miguel and Mateos, Javier and Katsaggelos, Aggelos K.}, doi = {10.1016/j.acha.2007.03.006}, issn = {10635203}, journal = {Applied and Computational Harmonic Analysis}, month = {mar}, number = {2}, pages = {251--267}, title = {{Variational posterior distribution approximation in Bayesian super resolution reconstruction of multispectral images}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S1063520307001133}, volume = {24}, year = {2008} }
@article{Ioannis2008, author = {Koktzoglou, Ioannis and Tsaftaris, Sotirios A and Li, Debiao and Katsaggelos, Aggelos K and Dharmakumar, Rohan}, doi = {10.1186/1532-429X-10-S1-A366}, issn = {1532-429X}, journal = {Journal of Cardiovascular Magnetic Resonance}, month = {oct}, number = {S1}, pages = {A366}, title = {{2097 Automated tracking of a passive intramyocardial needle with off-resonance mri: a feasibility study}}, url = {https://jcmr-online.biomedcentral.com/articles/10.1186/1532-429X-10-S1-A366}, volume = {10}, year = {2008} }
@article{Stefanos2008, abstract = {Super-resolution (SR) is the term used to define the process of estimating a high resolution (HR) image or a set of HR images from a set of low resolution (LR) observations. In this paper we propose a class of SR algorithms based on the maximum a posteriori (MAP) framework. These algorithms utilize a new multichannel image prior model, along with the state-of-the art image prior and observation models. Numerical experiments comparing the proposed algorithms, demonstrate the advantages of the adopted multichannel approach. copyright by EURASIP.}, author = {Stefanos, P Belekos and Nikolaos, P Galatsanos and Aggelos, K Katsaggelos and Belekos, Stefanos P and Galatsanos, Nikolaos P and Katsaggelos, Aggelos K}, doi = {10.1109/TIP.2010.2042115}, isbn = {22195491 , issue = 6}, issn = {1057-7149}, journal = {IEEE Transactions on Image Processing}, month = {jun}, number = {6}, pages = {1451--1464}, title = {{Maximum a Posteriori Video Super-Resolution Using a New Multichannel Image Prior}}, url = {http://ieeexplore.ieee.org/document/5404316/}, volume = {19}, year = {2008} }
@article{Aggelos2007e, abstract = {In this paper we propose and analyze a globally and locally adaptive super-resolution Bayesian methodology for pansharpening of multispectral images. The methodology incorporates prior knowledge on the expected characteristics of the multispectral images uses the sensor characteristics to model the observation process of both panchromatic and multispectral images and includes information on the unknown parameters in the model in the form of hyperprior distributions. Using real and synthetic data, the pansharpened multispectral images are compared with the images obtained by other pansharpening methods and their quality is assessed both qualitatively and quantitatively. The Author 2008. Published by Oxford University Press on behalf of The British Computer Society. All rights reserved.}, author = {Vega, M. and Mateos, J. and Molina, R. and Katsaggelos, A.K.}, doi = {10.1093/comjnl/bxn031}, issn = {0010-4620}, journal = {The Computer Journal}, keywords = {Bayesian models,Hyperspectral images,Super-resolution}, month = {feb}, number = {1}, pages = {153--167}, title = {{Super-Resolution of Multispectral Images}}, url = {https://academic.oup.com/comjnl/article-lookup/doi/10.1093/comjnl/bxn031}, volume = {52}, year = {2008} }
@article{Jianwei2008, abstract = {Multi-user video streaming over wireless channels is a challenging problem, where the demand for better video quality and small transmission delays needs to be reconciled with the limited and often time-varying communication resources. This paper presents a framework for joint network optimization, source adaptation, and deadline-driven scheduling for multi-user video streaming over wireless networks. We develop a joint adaptation, resource allocation and scheduling (JARS) algorithm, which allocates the communication resource based on the video users' quality of service, adapts video sources based on smart summarization, and schedules the transmissions to meet the frame delivery deadlines. The proposed algorithm leads to near full utilization of the network resources and satisfies the delivery deadlines for all video frames. Substantial performance improvements are achieved compared with heuristic schemes that do not take the interactions between multiple users into consideration. {\textcopyright} 2006 IEEE.}, author = {Jianwei, Huang and Zhu, Li and Mung, Chiang and Katsaggelos, A K}, chapter = {582}, doi = {10.1109/tcsvt.2008.919109}, isbn = {1051-8215 1558-2205}, journal = {IEEE Transactions on Circuits and Systems for Video Technology}, keywords = {Collaborative video streaming,Optimization decompo}, number = {5}, pages = {582--595}, title = {{Joint Source Adaptation and Resource Allocation for Multi-User Wireless Video Streaming}}, volume = {18}, year = {2008} }
@article{AggelosKonstantinos2010, abstract = {The project has developed statistical approaches for the detection of abnormal video events for surveillance applications. The project proposes to extend such approaches and apply them towards the classification of vehicle trajectories in roadway video data for analysis and mitigation of traffic congestion. With the proposed approach, traffic information will first be analyzed off-line in an automated fashion. The project examines both the behavior of each vehicle independently but also its interaction with other vehicles. The effect of abnormal events onto incoming traffic will be a central objective of the investigation. The goal is to provide the foundations of a system that will allow for the off-line analysis of video data. The results of the off-line analysis could be utilized in two major ways: (i) by transportation officials to consider revising transportation rules and regulations and (ii) in developing on-line technologies for tracking the most disruptive abnormal events and minimizing their effect in creating congestion, via, for example, deployment of emergency vehicles, timely response of transportation agencies, and roadside information display systems.}, author = {K., Katsaggelos and S., Tsaftaris and Y., Wu and {Derin Babacan} and Jiang, Fan}, journal = {Transportation}, pages = {5}, title = {{Video Traffic Analysis for Abnormal Event Detection}}, url = {http://www.ccitt.northwestern.edu/documents/FinalReportvideotrafficanalysis.pdf}, year = {2008} }
@article{babacan2008parameter, abstract = {In this paper, we propose novel algorithms for total variation (TV) based image restoration and parameter estimation utilizing variational distribution approximations. Within the hierarchical Bayesian formulation, the reconstructed image and the unknown hyperparameters for the image prior and the noise are simultaneously estimated. The proposed algorithms provide approximations to the posterior distributions of the latent variables using variational methods. We show that some of the current approaches to TV-based image restoration are special cases of our framework. Experimental results show that the proposed approaches provide competitive performance without any assumptions about unknown hyperparameters and clearly outperform existing methods when additional information is included. {\textcopyright} 2008 IEEE.}, author = {Babacan, S.D. and Molina, Rafael and Katsaggelos, A.K.}, doi = {10.1109/TIP.2007.916051}, issn = {1057-7149}, journal = {IEEE Transactions on Image Processing}, keywords = {Bayesian methods,Image restoration,Parameter estimation,Total variation (TV),Variational methods}, month = {mar}, number = {3}, pages = {326--339}, pmid = {18270122}, publisher = {IEEE}, title = {{Parameter Estimation in TV Image Restoration Using Variational Distribution Approximation}}, url = {http://ieeexplore.ieee.org/document/4446214/}, volume = {17}, year = {2008} }
@article{Konstantinos2005, abstract = {We consider the transmission of a Gaussian source through a block fading channel. Assuming each block is decoded independently, the received distortion depends on the tradeoff between quantization accuracy and probability of outage. Namely, higher quantization accuracy requires a higher channel code rate, which increases the probability of outage. We first treat an outage as an erasure, and evaluate the received mean distortion with erasure coding across blocks as a function of the code length. We then evaluate the performance of scalable, or multi-resolution coding in which coded layers are superimposed within a coherence block, and the layers are sequentially decoded. Both the rate and power allocated to each layer are optimized. In addition to analyzing the performance with a finite number of layers, we evaluate the mean distortion at high Signal-to-Noise Ratios as the number of layers becomes infinite. As the block length of the erasure code increases to infinity, the received distortion converges to a deterministic limit, which is less than the mean distortion with an infinite-layer scalable coding scheme. However, for the same standard deviation in received distortion, infinite layer scalable coding performs slightly better than erasure coding, and with much less decoding delay. {\textcopyright} 2008 IEEE.}, author = {Zachariadis, Konstantinos and Honig, Michael and Katsaggelos, Aggelos}, doi = {10.1109/TCOMM.2008.060387}, issn = {0090-6778}, journal = {IEEE Transactions on Communications}, keywords = {Broadcast channel,Fading channel,Rate distortion,Scalable coding,Source-channel coding}, month = {jul}, number = {7}, pages = {1080--1091}, title = {{Source fidelity over fading channels: performance of erasure and scalable codes}}, url = {http://ieeexplore.ieee.org/document/4568449/}, volume = {56}, year = {2008} }
@article{Yi2008, abstract = {This paper addresses the problem of multi-user video transmission over the uplink of multi-carrier networks from an information theoretic perspective. Under the constraints imposed by the Physical (PHY) and Medium Access Control (MAC) layers, we exploit the unique property of state-of-the-art video coders that can provide bitstream prioritization in terms of distortion impact and solve the problem of allocating wireless resources, i.e., power and rate among multiple users such that the weighted sum of the overall video qualities is maximized. An optimality condition is derived to describe the achievable convex utility region. We start from the two-user case and develop an algorithm for the optimal resource allocation. Inspired by the intuition gained from the two-user case, we extend the algorithm to the multiple-user case. Our numerical simulations show that the proposed resource allocation algorithms give significant performance improvements as compared to application-layer agnostic solutions that do not consider the quality impact. {\textcopyright}2008 IEEE.}, author = {Maani, Ehsan and Pahalawatta, Peshala V. and Berry, Randall and Pappas, Thrasyvoulos N. and Katsaggelos, Aggelos K.}, doi = {10.1109/TIP.2008.2001402}, isbn = {9781424420742 05361486 , issue = 9}, issn = {1057-7149}, journal = {IEEE Transactions on Image Processing}, keywords = {Multi-carrier networks,Utility driven resource man}, month = {sep}, number = {9}, pages = {1663--1671}, title = {{Resource Allocation for Downlink Multiuser Video Transmission Over Wireless Lossy Networks}}, url = {http://ieeexplore.ieee.org/document/4599190/}, volume = {17}, year = {2008} }
@article{Stelios2008, abstract = {This paper addresses the problem of data detection in orthogonal frequency division multiplexing (OFDM) systems operating under a time-varying multipath fading channel. Optimal detection in such a scenario is infeasible, which makes the introduction of approximations necessary. The typical joint data-channel estimators are decision directed, that is, assume perfect past data decisions. However, their performance is subject to error propagation phenomena. The variational Bayes method is employed here, which approximates the joint data and channel distribution as a separable one, greatly simplifying the problem. The data detection part of the resulting algorithm provides soft data estimates that are used for channel tracking. The channel itself is modeled as an autoregressive process allowing for a Kalman-like tracking algorithm. According to the developed algorithm, both data and channel estimates are exchanged and updated in an iterative manner. The performance of the proposed algorithm is evaluated by simulations. Furthermore, since OFDM is extremely sensitive to the presence of phase noise, the algorithm is extended to operate under severe phase noise conditions, with moderate performance degradation. {\textcopyright} 2008 IEEE.}, author = {Stefanatos, Stelios and Katsaggelos, A.K.}, doi = {10.1109/TSP.2008.925968}, issn = {1053-587X}, journal = {IEEE Transactions on Signal Processing}, keywords = {Channel tracking,Joint detection-estimation,Orthogonal frequency division multiplexing (OFDM),Phase noise,Variational Bayes method}, month = {sep}, number = {9}, pages = {4230--4243}, title = {{Joint Data Detection and Channel Tracking for OFDM Systems With Phase Noise}}, url = {http://ieeexplore.ieee.org/document/4527200/}, volume = {56}, year = {2008} }
@article{Javier2008, abstract = {In this paper we propose a novel algorithm for the pansharpening of multispectral images based on the use of a Total Variation (TV) image prior. Within the Bayesian formulation, the proposed methodology incorporates prior knowledge on the expected characteristics of multispectral images, and uses the sensor characteristics to model the observation process of both panchromatic and multispectral images. The pansharpened multispectral images are compared with the images obtained by other parsharpening methods and their quality is assessed both qualitatively and quantitatively. {\textcopyright} 2008 IOP Publishing Ltd.}, author = {Mateos, Javier and Vega, Miguel and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1088/1742-6596/139/1/012022}, issn = {1742-6596}, journal = {Journal of Physics: Conference Series}, month = {nov}, pages = {012022}, title = {{Pansharpening of multispectral images using a TV-based super-resolution algorithm}}, url = {https://iopscience.iop.org/article/10.1088/1742-6596/139/1/012022}, volume = {139}, year = {2008} }
@article{Zhu2008, abstract = {The deployment of the higher data rate wireless infrastructure systems and the emerging convergence of voice, video, and data services have been driving various modern multimedia applications, such as video streaming and mobile TV. However, the greatest challenge for video transmission over an uplink multiaccess wireless channel is the limited channel bandwidth and battery energy of a mobile device. In this paper, we pursue an energy-efficient video communication solution through joint video summarization and transmission adaptation over a slow fading wireless channel. Video summarization, coding and modulation schemes, and packet transmission are optimally adapted to the unique packet arrival and delay characteristics of the video summaries. In addition to the optimal solution, we also propose a heuristic solution that has close-to-optimal performance. Operational energy efficiency versus video distortion performance is characterized under a summarization setting. Simulation results demonstrate the advantage of the proposed scheme in energy efficiency and video transmission quality.}, author = {Li, Zhu and Zhai, Fan and Katsaggelos, Aggelos K.}, doi = {10.1155/2008/657032}, issn = {1687-6180}, journal = {EURASIP Journal on Advances in Signal Processing}, month = {dec}, number = {1}, pages = {657032}, title = {{Joint Video Summarization and Transmission Adaptation for Energy-Efficient Wireless Video Streaming}}, url = {https://asp-eurasipjournals.springeropen.com/articles/10.1155/2008/657032}, volume = {2008}, year = {2008} }
@article{Yun2008, abstract = {Subspace and similarity metric learning are important issues for image and video analysis in the scenarios of both computer vision and multimedia fields. Many real-world applications, such as image clustering/labeling and video indexing/retrieval, involve feature space dimensionality reduction as well as feature matching metric learning. However, the loss of information from dimensionality reduction may degrade the accuracy of similarity matching. In practice, such basic conflicting requirements for both feature representation efficiency and similarity matching accuracy need to be appropriately addressed. In the style of "Thinking Globally and Fitting Locally", we develop Locally Embedded Analysis (LEA) based solutions for visual data clustering and retrieval. LEA reveals the essential low-dimensional manifold structure of the data by preserving the local nearest neighbor affinity, and allowing a linear subspace embedding through solving a graph embedded eigenvalue decomposition problem. A visual data clustering algorithm, called Locally Embedded Clustering (LEC), and a local similarity metric learning algorithm for robust video retrieval, called Locally Adaptive Retrieval (LAR), are both designed upon the LEA approach, with variations in local affinity graph modeling. For large size database applications, instead of learning a global metric, we localize the metric learning space with kd-tree partition to localities identified by the indexing process. Simulation results demonstrate the effective performance of proposed solutions in both accuracy and speed aspects. {\textcopyright} 2007 Elsevier Inc. All rights reserved.}, author = {Fu, Yun and Li, Zhu and Huang, Thomas S. and Katsaggelos, Aggelos K.}, doi = {10.1016/j.cviu.2007.09.017}, issn = {10773142}, journal = {Computer Vision and Image Understanding}, keywords = {Dimensionality reduction,Image and video retrieval,Locally adaptive retrieval,Locally embedded analysis,Locally embedded clustering,Manifold,Similarity matching,Subspace learning,Visual clustering}, month = {jun}, number = {3}, pages = {390--402}, title = {{Locally adaptive subspace and similarity metric learning for visual data clustering and retrieval}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S1077314207001518}, volume = {110}, year = {2008} }
@article{tsaftaris2008not, author = {Tsaftaris, S. A. and Katsaggelos, A. K.}, doi = {10.1109/JPROC.2007.913496}, issn = {0018-9219}, journal = {Proceedings of the IEEE}, number = {3}, pages = {375--377}, publisher = {IEEE INSTITUTE OF ELECTRICAL AND ELECTRONICS}, title = {{The Not So Digital Future of Digital Signal Processing [Point of View]}}, url = {http://ieeexplore.ieee.org/document/4446225/}, volume = {96}, year = {2008} }
@article{Fabrizio2007, abstract = {Cross-layering is a design paradigm for overcoming the limitations deriving from the ISO/OSI layering principle, thus improving the performance of communications in specific scenarios, such as wireless multimedia communications. However, most available solutions are based on empirical considerations, and do not provide a theoretical background supporting such approaches. The paper aims at providing an analytical framework for the study of single-hop video delivery over a wireless link, enabling cross-layer interactions for performance optimization using power control and FEC and providing a useful tool to determine the potential gain deriving from the employment of such design paradigm. The analysis is performed using rate-distortion information of an embedded video bitstream jointly with a Lagrangian power minimization approach. Simulation results underline that cross-layering can provide relevant improvement in specific environments and that the proposed approach is able to capitalize on the advantage deriving from its deployment.}, author = {Granelli, Fabrizio and Costa, Cristina E. and Katsaggelos, Aggelos K.}, doi = {10.1155/2007/95807}, issn = {1687-5680}, journal = {Advances in Multimedia}, pages = {1--14}, title = {{A Study on the Usage of Cross-Layer Power Control and Forward Error Correction for Embedded Video Transmission over Wireless Links}}, url = {http://www.hindawi.com/journals/am/2007/095807/abs/}, volume = {2007}, year = {2007} }
@article{Barreto2007, author = {Barreto, D. and Alvarez, L. D. and Molina, R. and Katsaggelos, A. K. and Callic{\'{o}}, G. M.}, doi = {10.1007/s11045-007-0019-y}, issn = {0923-6082}, journal = {Multidimensional Systems and Signal Processing}, month = {sep}, number = {2-3}, pages = {59--81}, title = {{Region-based super-resolution for compression}}, url = {https://link.springer.com/10.1007/s11045-007-0019-y}, volume = {18}, year = {2007} }
@article{pahalawatta2007content, abstract = {A cross-layer packet scheduling scheme that streams pre-encoded video over wireless downlink packet access networks to multiple users is presented. The scheme can be used with the emerging wireless standards such as HSDPA and IEEE 802.16. A gradient based scheduling scheme is used in which user data rates are dynamically adjusted based on channel quality as well as the gradients of a utility function. The user utilities are designed as a function of the distortion of the received video. This enables distortion-aware packet scheduling both within and across multiple users. The utility takes into account decoder error concealment, an important component in deciding the received quality of the video. We consider both simple and complex error concealment techniques. Simulation results show that the gradient based scheduling framework combined with the content-aware utility functions provides a viable method for downlink packet scheduling as it can significantly outperform current content-independent techniques. Further tests determine the sensitivity of the system to the initial video encoding schemes, as well as to non-real-time packet ordering techniques. {\textcopyright} 2007 IEEE.}, author = {Pahalawatta, Peshala and Berry, Randall and Pappas, Thrasyvoulos and Katsaggelos, Aggelos}, doi = {10.1109/JSAC.2007.070511}, issn = {0733-8716}, journal = {IEEE Journal on Selected Areas in Communications}, keywords = {Cross-layer design,H.264,HSDPA,Video streaming,Wireless packet scheduling}, month = {may}, number = {4}, pages = {749--759}, publisher = {IEEE}, title = {{Content-aware resource allocation and packet scheduling for video transmission over wireless networks}}, url = {http://ieeexplore.ieee.org/document/4205057/}, volume = {25}, year = {2007} }
@article{de2007signal, author = {{De Natale}, Francesco G. B. and Katsaggelos, Aggelos K. and Mayora, Oscar and Wu, Ying}, doi = {10.1155/2007/91730}, issn = {1687-6180}, journal = {EURASIP Journal on Advances in Signal Processing}, month = {dec}, number = {1}, pages = {091730}, publisher = {Springer International Publishing}, title = {{Signal Processing Technologies for Ambient Intelligence in Home-Care Applications}}, url = {https://asp-eurasipjournals.springeropen.com/articles/10.1155/2007/91730}, volume = {2007}, year = {2007} }
@article{Peshala2007a, abstract = {As wireless technology evolves towards its fourth generation (4G) of development, the prospect of offering multimedia services such as on-demand video streaming and video conferencing to wireless mobile clients becomes increasingly more viable. The eventual success of such applications depends on the efficient management of the limited system resources while taking into account the time-varying wireless channel conditions as well as the varying multimedia source content. In this paper, we review some of the recent advances in cross-layer design schemes, which aim at providing significant gains in performance for video streaming systems through content-aware resource allocation. Advances in both, real-time video streaming, where the video is encoded and transmitted in real-time, as well as, on-demand video streaming, where the video is pre-encoded in a media server, are considered. Copyright {\textcopyright} 2007 John Wiley & Sons, Ltd.}, author = {Pahalawatta, Peshala V. and Katsaggelos, Aggelos K.}, doi = {10.1002/wcm.469}, issn = {15308669}, journal = {Wireless Communications and Mobile Computing}, keywords = {Cross-layer optimization,Multi-user video transmission,Video streaming,Wireless video}, month = {feb}, number = {2}, pages = {131--142}, title = {{Review of content-aware resource allocation schemes for video streaming over wireless networks}}, url = {https://onlinelibrary.wiley.com/doi/10.1002/wcm.469}, volume = {7}, year = {2007} }
@article{MinKyu2007, author = {Park, Min Kyu and Kang, Moon-Gi and Katsaggelos, Aggelos K.}, doi = {10.1117/1.2802611}, issn = {0091-3286}, journal = {Optical Engineering}, month = {nov}, number = {11}, pages = {117004}, title = {{Regularized high-resolution image reconstruction considering inaccurate motion information}}, url = {http://opticalengineering.spiedigitallibrary.org/article.aspx?doi=10.1117/1.2802611}, volume = {46}, year = {2007} }
@article{Miguel2006, abstract = {Most of the available digital color cameras use a single image sensor with a color filter array (CFA) in acquiring an image. In order to produce a visible color image, a demosaicing process must be applied, which produces undesirable artifacts. An additional problem appears when the observed color image is also blurred. This paper addresses the problem of deconvolving color images observed with a single coupled charged device (CCD)from the super-resolution point of view. Utilizing the Bayesian paradigm, an estimate of the reconstructed image and the model parameters is generated. The proposed method is tested on real images. Copyright {\textcopyright} Hindawi Publishing Corporation. All rights reserved.}, author = {Vega, Miguel and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1155/ASP/2006/25072}, issn = {1687-6180}, journal = {EURASIP Journal on Advances in Signal Processing}, month = {dec}, number = {1}, pages = {025072}, title = {{A Bayesian Super-Resolution Approach to Demosaicing of Blurred Images}}, url = {https://asp-eurasipjournals.springeropen.com/articles/10.1155/ASP/2006/25072}, volume = {2006}, year = {2006} }
@article{Molina2006, author = {Molina, Rafael and Mateos, Javier and Katsaggelos, Aggelos K.}, doi = {10.1109/TIP.2006.881972}, issn = {1057-7149}, journal = {IEEE Transactions on Image Processing}, month = {dec}, number = {12}, pages = {3715--3727}, title = {{Blind Deconvolution Using a Variational Approach to Parameter, Image, and Blur Estimation}}, url = {http://ieeexplore.ieee.org/document/4011964/}, volume = {15}, year = {2006} }
@article{wang2006joint, abstract = {In recent years, joint source-channel coding for multimedia communications has gained increased popularity. However, very limited work has been conducted to address the problem of joint source-channel coding for object-based video. In this paper, we propose a data hiding scheme that improves the error resilience of object-based video by adaptively embedding the shape and motion information into the texture data. Within a rate-distortion theoretical framework, the source coding, channel coding, data embedding, and decoder error concealment are jointly optimized based on knowledge of the transmission channel conditions. Our goal is to achieve the best video quality as expressed by the minimum total expected distortion. The optimization problem is solved using Lagrangian relaxation and dynamic programming. The performance of the proposed scheme is tested using simulations of a Rayleigh-fading wireless channel, and the algorithm is implemented based on the MPEG-4 verification model. Experimental results indicate that the proposed hybrid source-channel coding scheme significantly outperforms methods without data hiding or unequal error protection. {\textcopyright} 2006 IEEE.}, author = {{Haohong Wang} and Tsaftaris, S.A. Sotirios A and Katsaggelos, Aggelos K A.K. and Wang, Haohong and Tsaftaris, S.A. Sotirios A and Katsaggelos, Aggelos K A.K.}, doi = {10.1109/TIP.2006.875194}, issn = {1057-7149}, journal = {IEEE Transactions on image processing}, keywords = {Data embedding,Data hiding,Joint source-channel coding,MPEG-4 standard,Object-based video,Rate-distortion,Unequal error protection (UEP),Video coding,Video communications,Wireless channel}, month = {aug}, number = {8}, pages = {2158--2169}, pmid = {16900673}, publisher = {IEEE}, title = {{Joint source-channel coding for wireless object-based video communications utilizing data hiding}}, url = {http://ieeexplore.ieee.org/document/1658082/}, volume = {15}, year = {2006} }
@article{schuster2004motion, abstract = {The introduction of Video Objects (VOs) is one of the innovations of MPEG-4. The $\alpha$plane of a VO defines its shape at a given instance in time and hence determines the boundary of its texture. In packet-based networks, shape, motion, and texture are subject to loss. While there has been considerable attention paid to the concealment of texture and motion errors, little has been done in the field of shape error concealment. In this paper we propose a post-processing shape err or concealment technique that uses the motion compensated boundary information of the previously received $\alpha$-plane. The proposed approach is based on matching received boundary segments in the current frame to the boundary in the previous frame. This matching is achieved by finding a maximally smooth motion vector field. After the current boundary segments are matched to the previous boundary, the missing boundary pieces are reconstructed by motion compensation. Experimental results demonstrating the performance of the proposed motion compensated shape error concealment method, and comparing it with the previously proposed weighted side matching method [1] are presented. {\textcopyright} 2006 IEEE.}, author = {Schuster, G.M. and Katsaggelos, A.K.}, doi = {10.1109/ICIP.2004.1418718}, institution = {IEEE}, isbn = {0-7803-8554-3}, issn = {1057-7149}, journal = {2004 International Conference on Image Processing, 2004. ICIP '04.}, keywords = {Dynamic programming,Error concealment,MPEG-4,Motion compensation}, month = {feb}, number = {2}, pages = {501--510}, pmid = {16479820}, publisher = {IEEE}, title = {{Motion compensated shape error concealment}}, url = {https://ieeexplore.ieee.org/document/1576823 http://ieeexplore.ieee.org/document/1418718/}, volume = {1}, year = {2006} }
@article{aleksic2006automatic, abstract = {The performance of an automatic facial expression recognition system can be significantly improved by modeling the reliability of different streams of facial expression information utilizing multistream hidden Markov models (HMMs). In this paper, we present an automatic multistream HMM facial expression recognition system and analyze its performance. The proposed system utilizes facial animation parameters (FAPs), supported by the MPEG-4 standard, as features for facial expression classification. Specifically, the FAPs describing the movement of the outer-lip contours and eyebrows are used as observations. Experiments are first performed employing single-stream HMMs under several different scenarios, utilizing outer-lip and eyebrow FAPs individually and jointly. A multistream HMM approach is proposed for introducing facial expression and FAP group dependent stream reliability weights. The stream weights are determined based on the facial expression recognition results obtained when FAP streams are utilized individually. The proposed multistream HMM facial expression system, which utilizes stream reliability weights, achieves relative reduction of the facial expression recognition error of 44% compared to the single-stream HMM system. Copyright 2006, IEE.}, author = {Aleksic, P.S. and Katsaggelos, A.K.}, doi = {10.1109/TIFS.2005.863510}, issn = {1556-6013}, journal = {IEEE Transactions on Information Forensics and Security}, keywords = {Automatic facial expression recognition,Facial animation parameters,Hidden Markov models,MPEG-4 standards,Multistream HMM}, month = {mar}, number = {1}, pages = {3--11}, publisher = {IEEE}, title = {{Automatic Facial Expression Recognition Using Facial Animation Parameters and Multistream HMMs}}, url = {http://ieeexplore.ieee.org/document/1597130/}, volume = {1}, year = {2006} }
@article{Petar2006, author = {Aleksic, P.S. and Katsaggelos, A.K.}, doi = {10.1109/JPROC.2006.886017}, issn = {0018-9219}, journal = {Proceedings of the IEEE}, month = {nov}, number = {11}, pages = {2025--2044}, title = {{Audio-Visual Biometrics}}, url = {https://ieeexplore.ieee.org/iel5/5/4052463/04052464.pdf http://ieeexplore.ieee.org/document/4052464/}, volume = {94}, year = {2006} }
@article{Zhu2006a, author = {Li, Zhu and Huang, Jianwei and Katsaggelos, Aggelos K and Chiang, Mung}, journal = {China Communications}, keywords = {collaborative video,optimization decomposition,pricing control,rate-distortion modeling,streaming,video adaptation}, number = {October}, pages = {58--70}, title = {{Intelligent Wireless Video Communication : Source Adaptation and Multi-User Collaboration}}, url = {https://www.academia.edu/download/31006241/7.pdf}, year = {2006} }
@article{Jian-wei2006, abstract = {We solve the problem of uplink video streaming in CDMA cellular networks by jointly designing the rate control and scheduling algorithms. In the pricing-based distributed rate control algorithm, the base station announces a price for the per unit average rate it can support, and the mobile devices choose their desired average transmission rates by balancing their video quality and cost of transmission. Each mobile device then determines the specific video frames to transmit by a video summarization process. In the time-division-multiplexing (TDM) scheduling algorithm, the base station collects the information on frames to be transmitted from all devices within the current time window, sorts them in increasing order of deadlines, and schedules the transmissions in a TDM fashion. This joint algorithm takes advantage of the multi-user content diversity, and maximizes the network total utility (i.e., minimize the network total distortion), while satisfying the delivery deadline constraints. Simulations showed that the proposed algorithm significantly outperforms the constant rate provision algorithm.}, author = {Huang, Jian-wei and Li, Zhu and Chiang, Mung and Katsaggelos, Aggelos K.}, doi = {10.1631/jzus.2006.A0801}, issn = {1673-565X}, journal = {Journal of Zhejiang University-SCIENCE A}, keywords = {Code division multiple access,Cross-layer design,Pricing,Uplink communications,Video streaming,Video summarization}, month = {may}, number = {5}, pages = {801--810}, title = {{Joint rate control and scheduling for wireless uplink video streaming}}, url = {http://link.springer.com/10.1631/jzus.2006.A0801}, volume = {7}, year = {2006} }
@article{woods2005stochastic, abstract = {Using a stochastic framework, we propose two algorithms for the problem of obtaining a single high-resolution image from multiple noisy, blurred, and undersampled images. The first is based on a Bayesian formulation that is implemented via the expectation maximization algorithm. The second is based on a maximum a posteriori formulation. In both of our formulations, the registration, noise, and image statistics are treated as unknown parameters. These unknown parameters and the high-resolution image are estimated jointly based on the available observations. We present an efficient implementation of these algorithms in the frequency domain that allows their application to large images. Simulations are presented that test and compare the proposed algorithms. {\textcopyright} 2006 IEEE.}, author = {Woods, N.A. and Galatsanos, N.P. and Katsaggelos, A.K.}, doi = {10.1109/TIP.2005.860355}, issn = {1057-7149}, journal = {IEEE Transactions on Image Processing}, month = {jan}, number = {1}, pages = {201--213}, pmid = {16435550}, publisher = {IEEE}, title = {{Stochastic methods for joint registration, restoration, and interpolation of multiple undersampled images}}, url = {https://ieeexplore.ieee.org/document/1556638}, volume = {15}, year = {2006} }
@article{katsaggelos2006efficient, author = {Katsaggelos, A K and Pahalawatta, P V}, journal = {Virtual Observatory: Plate Content Digitization, Archive Mining and Image Sequence Processing}, pages = {234--244}, title = {{Efficient Video Communication over Lossy Channels}}, url = {https://ui.adsabs.harvard.edu/abs/2006vopc.conf..234K}, year = {2006} }
@article{Yiftach2006, author = {Eisenberg, Yiftach and {Fan Zhai} and Pappas, T.N. and Berry, Randall and Katsaggelos, A.K.}, doi = {10.1109/TIP.2005.860600}, issn = {1057-7149}, journal = {IEEE Transactions on Image Processing}, month = {feb}, number = {2}, pages = {289--299}, title = {{VAPOR: variance-aware per-pixel optimal resource allocation}}, url = {https://ieeexplore.ieee.org/document/1576802}, volume = {15}, year = {2006} }
@article{wang2005rate, abstract = {In object-based video encoding, the encoding of the video data is decoupled into the encoding of shape, motion, and texture information, which enables certain functionalities, like content-based interactivity and content-based scalability. The fundamental problem, however, of how to jointly encode this separate information to reach the best coding efficiency has not been studied thoroughly. In this paper, we present an operational rate-distortion optimal scheme for the allocation of bits among shape, motion, and texture in object-based video encoding. Our approach is based on Lagrangian relaxation and dynamic programming. We implement our algorithm on the MPEG-4 video verification model, although it is applicable to any object-based video encoding scheme. The performance is accessed utilizing a proposed metric that jointly captures the distortion due to the encoding of the shape and texture. Experimental results demonstrate that the gains of lossy shape encoding depend on the percentage the shape bits occupy out of the total bit budget. This gain may be small or may be realized at very low bit rates for certain typical scenes. {\textcopyright} 2005 IEEE.}, author = {Wang, Haohong and Schuster, G.M. Guido M. and Katsaggelos, Aggelos K. A.K. and {Haohong Wang} and Schuster, G.M. Guido M. and Katsaggelos, Aggelos K. A.K.}, chapter = {1113}, doi = {10.1109/TCSVT.2005.852629}, isbn = {1051-8215}, issn = {1051-8215}, journal = {IEEE Transactions on Circuits and Systems for Video Technology}, keywords = {MPEG-4,Object-based video,Rate-distortion,Shape coding,Video coding}, month = {sep}, number = {9}, pages = {1113--1123}, publisher = {IEEE}, title = {{Rate-distortion optimal bit allocation for object-based video coding}}, url = {http://ieeexplore.ieee.org/document/1501879/}, volume = {15}, year = {2005} }
@article{lopezbayesian, abstract = {ABSTRACT Emission tomography images are degraded due to the presence of noise and several physical factors like attenuation and scattering. To remove the attenuation effect from the emission tomography reconstruction, attenuation correction factors (ACFs) are used. These ACFs are obtained from a transmission scan and it is well known that they are homogeneous within each tissue and present abrupt variations in the transition between tissues.}, author = {L{\'{o}}pez, A and Garrido, J and Molina, R and Katsaggelos, A K}, journal = {ICIP}, title = {{Bayesian Transmission Image Reconstruction Using Compound Gauss-Markov Prior Models}}, url = {https://www.academia.edu/2704617/BAYESIAN_TRANSMISSION_IMAGE_RECONSTRUCTION_USING_COMPOUND_GAUSS_MARKOV_PRIOR_MODELS}, year = {2005} }
@article{zhai2005joint, abstract = {Differentiated Services (DiffServ) is one of the leading architectures for providing quality of service in the Internet. We propose a scheme for real-time video transmission over a DiffServ network that jointly considers video source coding, packet classification, and error concealment within a framework of costdistortion optimization. The selections of encoding parameters and packet classification are both used to manage end-to-end delay variations and packet losses within the network. We present two dual formulations of the proposed scheme: the minimum distortion problem, in which the objective is to minimize the end-to-end distortion subject to cost and delay constraints, and the minimum cost problem, which minimizes the total cost subject to end-to-end distortion and delay constraints. A solution to these problems using Lagrangian relaxation and dynamic programming is given. Simulation results demonstrate the advantage of jointly adapting the source coding and packet classification in DiffServ networks. {\textcopyright} 2005 IEEE.}, author = {Zhai, Fan and Luna, Carlos E. C.E. and Eisenberg, Yiftach and Pappas, T.N. Thrasyvoulos N. and Berry, Randall and Katsaggelos, Aggelos K. A.K. and {Fan Zhai} and Luna, Carlos E. C.E. and Eisenberg, Yiftach and Pappas, T.N. Thrasyvoulos N. and Berry, Randall and Katsaggelos, Aggelos K. A.K.}, chapter = {716}, doi = {10.1109/TMM.2005.850989}, isbn = {1520-9210}, issn = {15209210}, journal = {IEEE Transactions on Multimedia}, keywords = {Error concealment,Error resilience,Joint source-ch,Joint source-channel coding,Multimedia communication,Optimal resource allocation,QoS,Unequal error protection (UEP)}, month = {aug}, number = {4}, pages = {716--725}, publisher = {IEEE}, title = {{Joint source coding and packet classification for real-time video transmission over Differentiated Services networks}}, url = {http://ieeexplore.ieee.org/document/1468156/}, volume = {7}, year = {2005} }
@article{Fan2005a, author = {Fan, Zhai and Yiftach, Eisenberg and Aggelos, K Katsaggelos}, journal = {Handbook of Image and Video Processing}, pages = {1065--1082 , publisher = Academic}, title = {{Joint source-channel coding for video communications}}, url = {http://www.eecs.northwestern.edu/$\sim$fzhai/publications/Handbook_Image_Video_Processing_bookchapter.pdf}, year = {2005} }
@article{wang2005cost, abstract = {Object-based video coding is a relatively new technique to meet the fast growing demand for interactive multimedia applications. Compared with conventional frame-based video coding, it consists of two types of source data: shape information and texture information. Recently, joint source-channel coding for multimedia communications has gained increased popularity. However, very limited work has been conducted to address the problem of joint source-channel coding for object-based video. In this paper, we propose a cost-distortion optimal unequal error protection (UEP) scheme for object-based video communications. Our goal is to achieve the best video quality (minimum total expected distortion) with constraints on transmission cost and delay in a lossy network environment. The problem is solved using Lagarangian relaxation and dynamic programming. The performance of the proposed scheme is tested using simulations of a narrow-band block-fading wireless channel with additive white Gaussian noise and a simplified differentiated services Internet channel. Experimental results indicate that the proposed UEP scheme can significantly outperform equal error protection methods. {\textcopyright} 2005 IEEE.}, author = {{Haohong Wang} and {Fan Zhai} and Eisenberg, Yiftach and Katsaggelos, Aggelos K A.K. and Wang, Haohong and Zhai, Fan and Eisenberg, Yiftach and Katsaggelos, Aggelos K A.K.}, doi = {10.1109/TCSVT.2005.857305}, issn = {1051-8215}, journal = {IEEE Transactions on Circuits and Systems for Video Technology}, keywords = {Differentiated service (Diffserv) network,Joint source-channel coding,Lossy network,MPEG-4 standard,Object-based video,Rate distortion,Unequal error protection (UEP),Video coding,Video communications,Wireless channel}, month = {dec}, number = {12}, pages = {1505--1516}, publisher = {IEEE}, title = {{Cost-distortion optimized unequal error protection for object-based video communications}}, url = {http://ieeexplore.ieee.org/document/1545999/}, volume = {15}, year = {2005} }
@article{Tzavidas2005, author = {Tzavidas, S. and Katsaggelos, A.K.}, doi = {10.1109/TMM.2005.854430}, issn = {1520-9210}, journal = {IEEE Transactions on Multimedia}, month = {oct}, number = {5}, pages = {880--890}, title = {{A multicamera setup for generating stereo panoramic video}}, url = {http://ieeexplore.ieee.org/document/1510635/}, volume = {7}, year = {2005} }
@article{li2005minmax, abstract = {The need for video summarization originates primarily from a viewing time constraint. A shorter version of the original video sequence is desirable in a number of applications. Clearly, a shorter version is also necessary in applications where storage, communication bandwidth and/or power are limited. In this paper, our work is based on a MINMAX optimization formulation with viewing time, frame skip and bit rate constraints. New metrics for missing frame and video summary distortions are introduced. Optimal algorithm based on dynamic programming is presented along with experimental results. {\textcopyright} 2005 IEEE.}, author = {{Zhu Li} and Schuster, G.M. Guido M. and Katsaggelos, Aggelos K. A.K. and Li, Zhu and Schuster, G.M. Guido M. and Katsaggelos, Aggelos K. A.K.}, chapter = {1245}, doi = {10.1109/TCSVT.2005.854230}, isbn = {1051-8215}, issn = {1051-8215}, journal = {IEEE Transactions on Circuits and Systems for Video Technology}, keywords = {Dynamic programming,Rate-distortion optimization,Video analysis,Video summarization}, month = {oct}, number = {10}, pages = {1245--1256}, publisher = {IEEE}, title = {{MINMAX optimal video summarization}}, url = {http://ieeexplore.ieee.org/document/1512242/}, volume = {15}, year = {2005} }
@article{Sotirios2005, author = {Tsaftaris, Sotirios and Hatzimanikatis, Vassily and Katsaggelos, Aggelos}, journal = {Journal of the Japan Society of Simulation Technology (JSST) special issue "Application and Simulation of DNA Computing"}, keywords = {database,dna,dna_dsp,tsaftaris}, number = {4}, pages = {268--276}, title = {{In silico estimation of annealing specificity of query searches in DNA databases}}, volume = {24}, year = {2005} }
@article{li2005fast, abstract = {Content-based video retrieval technology holds the key to the efficient management and sharing of video content from different sources, in different scales, across different platforms, and over different communication channels. In this work fast video shot retrieval algorithms based on the geometry of video sequence traces in the principal component space are presented. Techniques to address scale (spatial and temporal) issues, in addition to noise and other possible distortions, such as frame dropping, are discussed. Experimental results demonstrate the eifectiveness of the proposed approach. {\textcopyright} IEE, 2005.}, author = {Li, Z. and Katsaggelos, A.K. and Gandhi, B.}, doi = {10.1049/ip-vis:20045083}, issn = {1350245X}, journal = {IEE Proceedings - Vision, Image, and Signal Processing}, number = {3}, pages = {367}, publisher = {IET Digital Library}, title = {{Fast video shot retrieval based on trace geometry matching}}, url = {https://digital-library.theiet.org/content/journals/10.1049/ip-vis_20045083}, volume = {152}, year = {2005} }
@article{Hong2005, author = {Hong, Min-Cheol and Stathaki, Tania and Katsaggelos, Aggelos K.}, doi = {10.1117/1.1867452}, issn = {1017-9909}, journal = {Journal of Electronic Imaging}, month = {jan}, number = {1}, pages = {013004}, title = {{Iterative regularized mixed norm multichannel image restoration}}, url = {http://electronicimaging.spiedigitallibrary.org/article.aspx?doi=10.1117/1.1867452}, volume = {14}, year = {2005} }
@article{zhai2003joint, abstract = {We consider efficiently transmitting video over a hybrid wireless/wire-line network by optimally allocating resources across multiple protocol layers. Specifically, we present a framework of joint source-channel coding and power adaptation, where error resilient source coding, channel coding, and transmission power adaptation are jointly designed to optimize video quality given constraints on the total transmission energy and delay for each video frame. In particular, we consider the combination of two types of channel coding - inter-packet coding (at the transport layer) to provide protection against packet dropping in the wire-line network and intra-packet coding (at the link layer) to provide protection against bit errors in the wireless link. In both cases, we allow the coding rate to be adaptive to provide unequal error protection at both the packet and frame level. In addition to both types of channel coding, we also compensate for channel errors by adapting the transmission power used to send each packet. An efficient algorithm based on Lagrangian relaxation and the method of alternating variables is proposed to solve the resulting optimization problem. Simulation results are shown to illustrate the advantages of joint optimization across multiple layers. {\textcopyright} 2005 Elsevier B.V. All rights reserved.}, author = {Zhai, Fan and Eisenberg, Yiftach and Pappas, Thrasyvoulos N. and Berry, Randall and Katsaggelos, Aggelos K.}, doi = {10.1016/j.image.2005.02.002}, institution = {The University; 1998}, issn = {09235965}, journal = {Signal Processing: Image Communication}, keywords = {Cross layer,Error concealment,Error resilience,Multimedia streaming,Product FEC,QoS,Unequal error protection (UEP)}, month = {apr}, number = {4}, pages = {371--387}, title = {{Joint source-channel coding and power adaptation for energy efficient wireless video communications}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S0923596505000123}, volume = {20}, year = {2005} }
@article{molina2005super, author = {Molina, R and Mateos, J and Katsaggelos, A K}, journal = {Virtual observatories: Plate Content Digitization, Archive Mining and Image Sequence processing, edited by Henron Press, Sofia (Bulgary)}, pages = {1--10}, title = {{Super resolution reconstruction of multispectral images ∗}}, url = {https://ccia.ugr.es/vip/files/conferences/Sofia2005.pdf}, year = {2005} }
@article{katsaggelos2005advances, abstract = {Multimedia applications involving the transmission of video over communication networks are rapidly increasing in popularity. Such applications can greatly benefit from adapting video coding parameters to network conditions as well as adapting network parameters to better support the application requirements. These two dimensions can both be viewed as allocating source and network resources to improve video quality. In this paper, we highlight recent advances in optimal resource allocation for real-time video communications over unreliable and resource constrained communication channels. More specifically, we focus on point-to-point coding and delivery schemes in which the sequences are encoded on the fly. We present a high-level framework for resource-distortion optimization. The framework can be used for jointly considering factors across network layers, including source coding, channel resource allocation, and error concealment. For example, resources can take the form of transmission energy in a wireless channel, and transmission cost in a DiffServ-based Internet channel. This framework can be used to optimally trade off resource consumption with end-to-end video quality in packet-based video transmission. After giving an overview of this framework, we review recent work in two areas - energy efficient wireless video transmission and resource allocation for Internet-based applications. {\textcopyright} 2005 IEEE.}, author = {Katsaggelos, A.K. and Eisenberg, Yiftach and Zhai, Fan and Berry, Randall and Pappas, T.N.}, doi = {10.1109/JPROC.2004.839621}, issn = {0018-9219}, journal = {Proceedings of the IEEE}, keywords = {Cross-layer design,Distortion estimation,Energy efficient,Error resilience,Internet video,Wireless video}, month = {jan}, number = {1}, pages = {135--147}, publisher = {IEEE}, title = {{Advances in Efficient Resource Allocation for Packet-Based Real-Time Video Transmission}}, url = {http://ieeexplore.ieee.org/document/1369704/}, volume = {93}, year = {2005} }
@article{Aggelos2005, abstract = {Transmitting video over wireless channels from mobile devices has gained increased popularity in a wide range of applications. A major obstacle in these types of applications is the limited energy supply in mobile device batteries. For this reason, efficiently utilizing energy is a critical issue in designing wireless video communication systems. This article highlights recent advances in joint source coding and optimal energy allocation. We present a general framework that takes into account multiple factors, including source coding, channel resource allocation, and error concealment, for the design of energy-efficient wireless video communication systems. This framework can take various forms and be applied to achieve the optimal trade-off between energy consumption and video delivery quality during wireless video transmission. {\textcopyright} 2005 IEEE.}, author = {Katsaggelos, A.K. and {Fan Zhai} and Eisenberg, Yiftach and Berry, Randall}, doi = {10.1109/MWC.2005.1497855}, issn = {1536-1284}, journal = {IEEE Wireless Communications}, month = {aug}, number = {4}, pages = {24--30}, title = {{Energy-efficient wireless video coding and delivery}}, url = {http://ieeexplore.ieee.org/document/1497855/}, volume = {12}, year = {2005} }
@article{li2005rate, abstract = {The need for video summarization originates primarily from a viewing time constraint. A shorter version of the original video sequence is desirable in a number of applications. Clearly, a shorter version is also necessary in applications where storage, communication bandwidth, and/or power are limited. The summarization process inevitably introduces distortion. The amount of summarization distortion is related to its "conciseness," or the number of frames available in the summary. If there are m frames in the original sequence and n frames in the summary, we define the summarization rate as m/n, to characterize this "conciseness." We also develop a new summarization distortion metric and formulate the summarization problem as a rate-distortion optimization problem. Optimal algorithms based on dynamic programming are presented and compared experimentally with heuristic algorithms. Practical constraints, like the maximum number of frames that can be skipped, are also considered in the formulation and solution of the problem. {\textcopyright} 2005 IEEE.}, author = {Li, Zhu and Schuster, G.M. Guido M. and Katsaggelos, Aggelos K. A.K. and Gandhi, Bhavan and {Zhu Li} and Schuster, G.M. Guido M. and Katsaggelos, Aggelos K. A.K. and Gandhi, Bhavan}, doi = {10.1109/TIP.2005.854477}, issn = {1057-7149}, journal = {IEEE Transactions on Image Processing}, keywords = {Dynamic programming (DP),Rate-distortion optimization,Video analysis,Video summarization}, month = {oct}, number = {10}, pages = {1550--1560}, pmid = {16238060}, publisher = {IEEE}, title = {{Rate-distortion optimal video summary generation}}, url = {http://ieeexplore.ieee.org/document/1510689/}, volume = {14}, year = {2005} }
@article{segall2004bayesian, abstract = {Super-resolution algorithms recover high-frequency information from a sequence of low-resolution observations. In this paper, we consider the impact of video compression on the super-resolution task. Hybrid motion-compensation and transform coding schemes are the focus, as these methods provide observations of the underlying displacement values as well as a variable noise process. We utilize the Bayesian framework to incorporate this information and fuse the super-resolution and post-processing problems. A tractable solution is defined, and relationships between algorithm parameters and information in the compressed bitstream are established. The association between resolution recovery and compression ratio is also explored. Simulations illustrate the performance of the procedure with both synthetic and nonsynthetic sequences. {\textcopyright} 2004 IEEE.}, author = {Segall, C.A. and Katsaggelos, A.K. and Molina, Rafael and Mateos, Javier}, doi = {10.1109/TIP.2004.827230}, issn = {1057-7149}, journal = {IEEE Transactions on Image Processing}, month = {jul}, number = {7}, pages = {898--911}, pmid = {15648857}, publisher = {IEEE}, title = {{Bayesian Resolution Enhancement of Compressed Video}}, url = {http://ieeexplore.ieee.org/document/1303643/}, volume = {13}, year = {2004} }
@article{Park2004, author = {Park, S.C. and Kang, M.G. and Segall, C.A. and Katsaggelos, A.K.}, doi = {10.1109/TIP.2003.819233}, issn = {1057-7149}, journal = {IEEE Transactions on Image Processing}, month = {apr}, number = {4}, pages = {573--585}, title = {{Spatially Adaptive High-Resolution Image Reconstruction of DCT-Based Compressed Images}}, url = {http://ieeexplore.ieee.org/document/1284393/}, volume = {13}, year = {2004} }
@article{Sotirios2004a, author = {Tsaftaris, S.A. and Katsaggelos, A.K. and Pappas, T.N. and Papoutsakis, E.T.}, doi = {10.1109/MSP.2004.1328093}, issn = {1053-5888}, journal = {IEEE Signal Processing Magazine}, month = {sep}, number = {5}, pages = {100--106}, title = {{Life sciences - DNA computing from a signal processing viewpoint}}, url = {http://ieeexplore.ieee.org/document/1328093/}, volume = {21}, year = {2004} }
@article{aleksic2004speech, abstract = {There is a strong correlation between the building blocks of speech (phonemes) and the building blocks of visual speech (visimes). In this paper, this correlation is exploited and an approach is proposed for synthesizing the visual representation of speech from a narrow-band acoustic speech signal. The visual speech is represented in terms of the facial animation parameters (FAPs), supported by the MPEG-4 standard. The main contribution of this paper is the development of a correlation hidden Markov model (CHMM) system, which integrates independently trained acoustic HMM (AHMM) and visual HMM (VHMM) systems, in order to realize speech-to-video synthesis. The proposed CHMM system allows for different model topologies for acoustic and visual HMMs. It performs late integration and reduces the amount of required training data compared to early integration modeling techniques. Temporal accuracy experiments, comparison of the synthesized FAPs to the original FAPs, and audio-visual automatic speech recognition (AV-ASR) experiments utilizing the synthesized visual speech were performed in order to objectively measure the performance of the system. The objective experiments demonstrated that the proposed approach reduces time alignment errors by 40.5% compared to the conventional temporal scaling method, that the synthesized FAP sequences are very similar to the original FAP sequences, and that synthesized FAP sequences contain visual speechreading information that can improve AV-ASR performance.}, author = {Aleksic, P.S. and Katsaggelos, A.K.}, doi = {10.1109/TCSVT.2004.826760}, issn = {1051-8215}, journal = {IEEE Transactions on Circuits and Systems for Video Technology}, keywords = {Audio-visual speech recognition,Correlation hidden Markov models (CHMMs),Facial animation parameters (FAPs),Speech-to-video synthesis}, month = {may}, number = {5}, pages = {682--692}, publisher = {IEEE}, title = {{Speech-To-Video Synthesis Using MPEG-4 Compliant Visual Features}}, url = {http://ieeexplore.ieee.org/document/1294959/}, volume = {14}, year = {2004} }
@article{Ebroul2004, author = {Izquierdo, Ebroul and Katsaggelos, A.K. and Strintzis, M.G.}, doi = {10.1109/TCSVT.2004.828719}, issn = {1051-8215}, journal = {IEEE Transactions on Circuits and Systems for Video Technology}, month = {may}, number = {5}, pages = {569--571}, title = {{Introduction to the Special Issue on Audio and Video Analysis for Multimedia Interactive Services}}, url = {http://ieeexplore.ieee.org/document/1294949/}, volume = {14}, year = {2004} }
@article{schuster2004shape, abstract = {The introduction of video objects (VOs) is one of the innovations of MPEG-4. The $\alpha$-plane of a VO defines its shape at a given instance in time and hence determines the boundary of its texture. In packet-based networks, shape, motion, and texture are subject to loss. While there has been considerable attention paid to the concealment of texture and motion errors, little has been done in the field of shape error concealment. In this paper, we propose a post-processing shape error-concealment technique that uses geometric boundary information of the received $\alpha$-plane. Second-order Hermite splines are used to model the received boundary in the neighboring blocks, while third order Hermite splines are used to model the missing boundary. The velocities of these splines are matched at the boundary point closest to the missing block. There exists the possibility of multiple concealing splines per group of lost boundary parts. Therefore, we draw every concealment spline combination that does not self-intersect and keep all possible results until the end. At the end, we select the concealment solution that results in one closed boundary. Experimental results demonstrating the performance of the proposed method and comparisons with prior proposed methods are presented.}, author = {Schuster, G.M. and Li, Xiaohuan and Katsaggelos, A.K.}, doi = {10.1109/TIP.2004.827226}, issn = {1057-7149}, journal = {IEEE Transactions on Image Processing}, keywords = {Error concealment,Hermite spline,MPEG-4,Shape coding}, month = {jun}, number = {6}, pages = {808--820}, pmid = {15648871}, publisher = {IEEE}, title = {{Shape Error Concealment Using Hermite Splines}}, url = {http://ieeexplore.ieee.org/document/1298837/}, volume = {13}, year = {2004} }
@article{tsaftaris2004can, author = {Tsaftaris, S.A. and Katsaggelos, A.K. and Pappas, T.N. and Papoutsakis, E.T.}, doi = {10.1109/MSP.2004.1359142}, issn = {1053-5888}, journal = {IEEE Signal Processing Magazine}, month = {nov}, number = {6}, pages = {57--61}, publisher = {IEEE}, title = {{How can DNA computing be applied to digital signal processing?}}, url = {http://ieeexplore.ieee.org/document/1359142/}, volume = {21}, year = {2004} }
@article{alvarez2004high, abstract = {In this article, we address the problem of obtaining a high-resolution (HR) image from a compressed low-resolution (LR) video sequence. Motion information plays a critical role in solving this problem, and we determine which pixels in the sequence provide useful information for calculating the high-resolution image. The bit stream of hybrid motion compensated video compression methods includes low-resolution motion-compensated images; we therefore also study which pixels in these images should be used to increase the quality of the reconstructed image. Once the useful (observable) pixels in the low-resolution and motion-compensated sequences have been detected, we modify the acquisition model to only account for these observations. The proposed approach is tested on real compressed video sequences and the improved performance is re ported. {\textcopyright} 2004 Wiley Periodicals, Inc.}, author = {Alvarez, L. D. and Mateos, J. and Molina, R. and Katsaggelos, A. K.}, doi = {10.1002/ima.20008}, issn = {0899-9457}, journal = {International Journal of Imaging Systems and Technology}, keywords = {Compressed low-resolution video,High-resolution image,Motion estimation,Observability map,Observable pixel}, number = {2}, pages = {58--66}, publisher = {Wiley Subscription Services, Inc., A Wiley Company Hoboken}, title = {{High-resolution images from compressed low-resolution video: Motion estimation and observable pixels}}, url = {https://onlinelibrary.wiley.com/doi/10.1002/ima.20008}, volume = {14}, year = {2004} }
@article{Antonio2004, author = {L{\'{o}}pez, Antonio and Molina, Rafael and Katsaggelos, Aggelos K. and Rodriguez, Antonio and L{\'{o}}pez, Jos{\'{e}} M. and Llamas, Jos{\'{e}} M.}, doi = {10.1002/ima.20003}, issn = {08999457}, journal = {International Journal of Imaging Systems and Technology}, number = {1}, pages = {21--27}, title = {{Parameter estimation in Bayesian reconstruction of SPECT images: An aid in nuclear medicine diagnosis}}, url = {https://onlinelibrary.wiley.com/doi/10.1002/ima.20003}, volume = {14}, year = {2004} }
@article{Tom2004, abstract = {This paper presents a method to find the operational rate-distortion optimal solution for an overcomplete signal decomposition. The idea of using overcomplete dictionaries, or frames, is to get a sparse representation of the signal. Traditionally, sub-optimal algorithms, such as matching pursuit (MP), are used for this purpose. When using frames in a lossy compression scheme, the major issue is to find the best possible rate-distortion (RD) tradeoff. Given the frame and the variable length code (VLC) table embedded in the entropy coder, the solution to the problem of establishing the best RD tradeoff is highly complex. The proposed approach reduces this complexity significantly by structuring the solution approach such that the dependent quantizer allocation problem reduces to an independent one. In addition, the use of a solution tree further reduces the complexity. It is important to note that this large reduction in complexity is achieved without sacrificing optimality. The optimal rate-distortion solution depends on the selection of the frame and the VLC table embedded in the entropy coder. Thus, frame design and VLC optimization is part of this work. We experimentally demonstrate that the new approach outperforms rate-distortion optimized (RDO) matching pursuit, previously proposed by Gharavi-Alkhansari.}, author = {Ryen, Tom and Schuster, G.M. and Katsaggelos, A.K.}, doi = {10.1109/TSP.2004.826184}, issn = {1053-587X}, journal = {IEEE Transactions on Signal Processing}, keywords = {Depth-first search,Frame design,Overcomplete dictionary,QR-decomposition,Rate-distortion optimization}, month = {may}, number = {5}, pages = {1352--1363}, title = {{A Rate-Distortion Optimal Alternative to Matching Pursuit}}, url = {https://ieeexplore.ieee.org/iel5/78/28675/01284833.pdf http://ieeexplore.ieee.org/document/1284833/}, volume = {52}, year = {2004} }
@article{Lisimachos2004, abstract = {A major problem in object-oriented video coding and MPEG-4 is the encoding of object boundaries. Traditionally this problem is treated separately from the texture encoding problem. In this paper, we present a vertex-based shape coding method which is optimal in the operational rate-distortion sense and takes into account the texture information of the video frames. This is accomplished by utilizing a variable-width tolerance band whose width is a function of the texture profile. As an example, this width is inversely proportional to the magnitude of the image gradient. Thus, in areas where the confidence in the estimation of the boundary is low and/or coding errors in the boundary will not affect the application (e.g., object-oriented coding and MPEG-4) significantly, a larger boundary approximation error is allowed. We present experimental results which demonstrate the effectiveness of the proposed algorithm.}, author = {Kondi, L.P. and Melnikov, Gerry and Katsaggelos, A.K.}, doi = {10.1109/TCSVT.2004.825569}, issn = {1051-8215}, journal = {IEEE Transactions on Circuits and Systems for Video Technology}, keywords = {Boundary coding,MPEG-4,Operational rate-distortion,Operational rate-distortion (ORD) theory,Shape coding,Shape-adaptive DCT}, month = {apr}, number = {4}, pages = {528--533}, publisher = {IEEE}, title = {{Joint Optimal Object Shape Estimation and Encoding}}, url = {http://ieeexplore.ieee.org/document/1281827/}, volume = {14}, year = {2004} }
@article{nakagaki2003vq, abstract = {In this paper, learning-based algorithms for image restoration and blind image restoration are proposed. Such algorithms deviate from the traditional approaches in this area, by utilizing priors that are learned from similar images. Original images and their degraded versions by the known degradation operator (restoration problem) are utilized for designing the VQ codebooks. The codevectors are designed using the blurred images. For each such vector, the high frequency information obtained from the original images is also available. During restoration, the high frequency information of a given degraded image is estimated from its low frequency information based on the codebooks. For the blind restoration problem, a number of codebooks are designed corresponding to various versions of the blurring function. Given a noisy and blurred image, one of the codebooks is chosen based on a similarity measure, therefore providing the identification of the blur. To make the restoration process computationally efficient, the Principal Component Analysis (PCA) and VQ-Nearest Neighborhood approaches are utilized. Simulation results are presented to demonstrate the effectiveness of the proposed algorithms.}, author = {Nakagaki, Ryo and Katsaggelos, A.K.}, doi = {10.1109/TIP.2003.816007}, issn = {1057-7149}, journal = {IEEE Transactions on Image Processing}, keywords = {Blur identification,Compression,Image restoration,Vector quantization}, month = {sep}, number = {9}, pages = {1044--1053}, publisher = {IEEE}, title = {{A VQ-based blind image restoration algorithm}}, url = {http://ieeexplore.ieee.org/document/1221758/}, volume = {12}, year = {2003} }
@article{Luna2003, author = {Luna, C.E. and Eisenberg, Y. and Berry, R. and Pappas, T.N. and Katsaggelos, A.K.}, doi = {10.1109/JSAC.2003.815394}, issn = {0733-8716}, journal = {IEEE Journal on Selected Areas in Communications}, month = {dec}, number = {10}, pages = {1710--1720}, title = {{Joint source coding and data rate adaptation for energy efficient wireless video streaming}}, url = {http://ieeexplore.ieee.org/document/1254586/}, volume = {21}, year = {2003} }
@article{wang2003efficient, abstract = {In this paper, we present a new shape-coding approach, which decouples the shape information into two independent signal data sets; the skeleton and the boundary distance from the skeleton. The major benefit of this approach is that it allows for a more flexible tradeoff between approximation error and bit budget. Curves of arbitrary order can be utilized for approximating both the skeleton and distance signals. For a given bit budget for a video frame, we solve the problem of choosing the number and location of the control points for all skeleton and distance signals of all boundaries within a frame, so that the overall distortion is minimized. An operational rate-distortion (ORD) optimal approach using Lagrangian relaxation and a four-dimensional Direct Acyclic Graph (DAG) shortest path algorithm is developed for solving the problem. To reduce the computational complexity from O(N5) to O(N3), where N is the number of admissible control points for a skeleton, a suboptimal greedy-trellis search algorithm is proposed and compared with the optimal algorithm. In addition, an even more efficient algorithm with computational complexity O(N2) that finds an ORD optimal solution using a relaxed distortion criterion is also proposed and compared with the optimal solution. Experimental results demonstrate that our proposed approaches outperform existing ORD optimal approaches, which do not follow the same decomposition of the source data.}, author = {{Haohong Wang} and Schuster, G.M. Guido M. and Katsaggelos, Aggelos K. A.K. and Pappas, T.N. Thrasyvoulos N. and Wang, Haohong and Schuster, G.M. Guido M. and Katsaggelos, Aggelos K. A.K. and Pappas, T.N. Thrasyvoulos N.}, doi = {10.1109/TIP.2003.816570}, issn = {1057-7149}, journal = {IEEE Transactions on Image Processing}, keywords = {Boundary coding,Object-based video compression,Rate-distortion optimization,Shape coding,Skeleton decomposition,Skeletonization}, month = {oct}, number = {10}, pages = {1181--1193}, publisher = {IEEE}, title = {{An Efficient Rate-Distortion Optimal Shape Coding Approach Utilizing a Skeleton-Based Decomposition}}, url = {http://ieeexplore.ieee.org/document/1233561/}, volume = {12}, year = {2003} }
@article{luna2003maximizing, abstract = {In this paper, we study some of the design tradeoffs of video streaming systems in networks with QoS guarantees. We approach this problem by using a utility function to quantify the benefit a user derives from the quality of the received video sequence. We also consider the cost to the network user for streaming the video sequence. We have formulated this utility maximization problem as a joint constrained optimization problem where we maximize the difference between the utility and the network cost, subject to the constraint that the decoder buffer does not underflow. In this manner, we can find the optimal tradeoff between video quality and network cost. We present a deterministic dynamic programming approach for both the constant bit rate and renegotiated constant bit rate service classes. Experimental results demonstrate the benefits and the performance of the proposed approach.}, author = {Luna, C.E. and Kondi, L.P. and Katsaggelos, A.K.}, doi = {10.1109/TCSVT.2002.808439}, issn = {1051-8215}, journal = {IEEE Transactions on Circuits and Systems for Video Technology}, keywords = {Quality of service (QoS),Renegotiated constant bit rate (RCBR),Renegotiated services,User utility,Video streaming}, month = {feb}, number = {2}, pages = {141--148}, publisher = {IEEE}, title = {{Maximizing user utility in video streaming applications}}, url = {http://ieeexplore.ieee.org/document/1186530/}, volume = {13}, year = {2003} }
@article{molina2003parameter, abstract = {In this paper, we consider the estimation of the unknown parameters for the problem of reconstructing a high-resolution image from multiple undersampled, shifted, degraded frames with subpixel displacement errors. We derive mathematical expressions for the iterative calculation of the maximum likelihood estimate of the unknown parameters given the low resolution observed images. These iterative procedures require the manipulation of block-semi circulant (BSC) matrices, that is block matrices with circulant blocks. We show how these BSC matrices can be easily manipulated in order to calculate the unknown parameters. Finally the proposed method is tested on real and synthetic images.}, author = {Molina, Rafael and Vega, Miguel and Abad, Javier and Katsaggelos, A.K.}, doi = {10.1109/TIP.2003.818117}, issn = {1057-7149}, journal = {IEEE Transactions on Image Processing}, keywords = {Bayesian methods,High-resolution image reconstruction,Parameter estimation}, month = {dec}, number = {12}, pages = {1655--1667}, publisher = {IEEE}, title = {{Parameter estimation in bayesian high-resolution image reconstruction with multisensors}}, url = {http://ieeexplore.ieee.org/document/1257401/}, volume = {12}, year = {2003} }
@article{Molina2003, author = {Molina, R. and Mateos, J. and Katsaggelos, A.K. and Vega, M.}, doi = {10.1109/TIP.2003.818015}, issn = {1057-7149}, journal = {IEEE Transactions on Image Processing}, month = {dec}, number = {12}, pages = {1642--1654}, title = {{Bayesian multichannel image restoration using compound gauss-markov random fields}}, url = {http://ieeexplore.ieee.org/document/1257400/}, volume = {12}, year = {2003} }
@article{Petar2003a, author = {Aleksic, Petar S and Katsaggelos, Aggelos K}, journal = {Works. Multimedia User Authentication, Santa Barbara, CA}, title = {{An audio-visual person identification and verification system using FAPs as visual features}}, url = {https://citeseerx.ist.psu.edu/document?repid=rep1&type=pdf&doi=fd43812e63659d50b2f96c6f5f361a1dc64f61fe#page=80}, year = {2003} }
@article{Kaaren2003, abstract = {Spatially adaptive intensity bounds on the image estimate are shown to be an effective means of regularising the ill-posed image restoration problem. For blind restoration, the local intensity constraints also help to further define the solution, thereby reducing the number of multiple solutions and local minima. The bounds are defined in terms of the local statistics of the image estimate and a control parameter which determines the scale of the bounds. Guidelines for choosing this parameter are developed in the context of classical (nonblind) image restoration. The intensity bounds are applied by means of the gradient projection method, and conditions for convergence are derived when the bounds are refined using the current image estimate. Based on this method, a new alternating constrained minimisation approach is proposed for blind image restoration. On the basis of the experimental results provided, it is found that local intensity bounds offer a simple, flexible method of constraining both the nonblind and blind restoration problems.}, author = {May, Kaaren L. and Stathaki, Tania and Katsaggelos, Aggelos K.}, doi = {10.1155/S1110865703308066}, issn = {1687-6180}, journal = {EURASIP Journal on Advances in Signal Processing}, keywords = {Blind image restoration,Blur identification,Image resolution,Set-theoretic estimation}, month = {dec}, number = {12}, pages = {250181}, title = {{Spatially Adaptive Intensity Bounds for Image Restoration}}, url = {https://asp-eurasipjournals.springeropen.com/articles/10.1155/S1110865703308066}, volume = {2003}, year = {2003} }
@article{segall2003high, author = {Segall, C.A. and Molina, Rafael and Katsaggelos, A.K.}, doi = {10.1109/MSP.2003.1203208}, issn = {1053-5888}, journal = {IEEE Signal Processing Magazine}, month = {may}, number = {3}, pages = {37--48}, publisher = {IEEE}, title = {{High-resolution images from low-resolution compressed video}}, url = {http://ieeexplore.ieee.org/document/1203208/}, volume = {20}, year = {2003} }
@article{SedaOgrenci2003, abstract = {Programmable logic is emerging as an attractive solution for many digital signal processing applications. In this work, we have investigated issues arising due to the resource constraints of FPGA-based systems. Using an iterative image restoration algorithm as an example we have shown how to manipulate the original algorithm to suit it to an FPGA implementation. Consequences of such manipulations have been estimated, such as loss of quality in the output image. We also present performance results from an actual implementation on a Xilinx FPGA. Our experiments demonstrate that, for different criteria, such as result quality or speed, the best implementation is different as well.}, author = {Memik, S.O. and Katsaggelos, A.K. and Sarrafzadeh, Majid}, doi = {10.1109/TC.2003.1183952}, issn = {0018-9340}, journal = {IEEE Transactions on Computers}, keywords = {FPGA,Image restoration,Image segmentation}, month = {mar}, number = {3}, pages = {390--399}, title = {{Analysis and FPGA implementation of image restoration under resource constraints}}, url = {http://ieeexplore.ieee.org/document/1183952/}, volume = {52}, year = {2003} }
@article{Eisenberg2002, author = {Eisenberg, Y. and Luna, C.E. and Pappas, T.N. and Berry, R. and Katsaggelos, A.K.}, doi = {10.1109/TCSVT.2002.800309}, issn = {1051-8215}, journal = {IEEE Transactions on Circuits and Systems for Video Technology}, month = {jun}, number = {6}, pages = {411--424}, title = {{Joint source coding and transmission power management for energy efficient wireless video communications}}, url = {http://ieeexplore.ieee.org/document/1013849/}, volume = {12}, year = {2002} }
@article{hong2002iterative, author = {Hong, Min-Cheol and Stathaki, Tania and Katsaggelos, Aggelos K.}, doi = {10.1117/1.1503072}, issn = {0091-3286}, journal = {Optical Engineering}, month = {oct}, number = {10}, pages = {2515}, publisher = {Society of Photo-Optical Instrumentation Engineers}, title = {{Iterative regularized least-mean mixed-norm image restoration}}, url = {http://opticalengineering.spiedigitallibrary.org/article.aspx?doi=10.1117/1.1503072}, volume = {41}, year = {2002} }
@article{Petar2002, abstract = {We describe an audio-visual automatic continuous speech recognition system, which significantly improves speech recognition performance over a wide range of acoustic noise levels, as well as under clean audio conditions. The system utilizes facial animation parameters (FAPs) supported by the MPEG-4 standard for the visual representation of speech. We also describe a robust and automatic algorithm we have developed to extract FAPs from visual data, which does not require hand labeling or extensive training procedures. The principal component analysis (PCA) was performed on the FAPs in order to decrease the dimensionality of the visual feature vectors, and the derived projection weights were used as visual features in the audio-visual automatic speech recognition (ASR) experiments. Both single-stream and multistream hidden Markov models (HMMs) were used to model the ASR system, integrate audio and visual information, and perform a relatively large vocabulary (approximately 1000 words) speech recognition experiments. The experiments performed use clean audio data and audio data corrupted by stationary white Gaussian noise at various SNRs. The proposed system reduces the word error rate (WER) by 20% to 23% relatively to audio-only speech recognition WERs, at various SNRs (0-30 dB) with additive white Gaussian noise, and by 19% relatively to audio-only speech recognition WER under clean audio conditions.}, author = {Aleksic, Petar S. and Williams, Jay J. and Wu, Zhilin and Katsaggelos, Aggelos K.}, doi = {10.1155/S1110865702206162}, issn = {1687-6180}, journal = {EURASIP Journal on Advances in Signal Processing}, keywords = {Audio-visual speech recognition,Facial animation parameters,Snake}, month = {dec}, number = {11}, pages = {150948}, publisher = {Springer International Publishing}, title = {{Audio-Visual Speech Recognition Using MPEG-4 Compliant Visual Features}}, url = {https://asp-eurasipjournals.springeropen.com/articles/10.1155/S1110865702206162}, volume = {2002}, year = {2002} }
@article{kondi2002joint, abstract = {In this paper, we develop an approach toward joint source-channel coding for motion-compensated DCT-based scalable video coding and transmission. A framework for the optimal selection of the source and channel coding rates over all scalable layers is presented such that the overall distortion is minimized. The algorithm utilizes universal rate distortion characteristics which are obtained experimentally and show the sensitivity of the source encoder and decoder to channel errors. The proposed algorithm allocates the available bit rate between scalable layers and, within each layer, between source and channel coding. We present the results of this rate allocation algorithm for video transmission over a wireless channel using the H.263 Version 2 signal-to-noise ratio (SNR) scalable codec for source coding and rate-compatible punctured convolutional (RCPC) codes for channel coding. We discuss the performance of the algorithm with respect to the channel conditions, coding methodologies, layer rates, and number of layers.}, author = {Kondi, L.P. and Ishtiaq, Faisal and Katsaggelos, A.K.}, doi = {10.1109/TIP.2002.802507}, issn = {1057-7149}, journal = {IEEE Transactions on Image Processing}, keywords = {Joint source-channel coding,Scalable video,Wireless video}, month = {sep}, number = {9}, pages = {1043--1052}, publisher = {IEEE}, title = {{Joint source-channel coding for motion-compensated DCT-based SNR scalable video}}, url = {http://ieeexplore.ieee.org/document/1036052/}, volume = {11}, year = {2002} }
@article{segall2002super, address = {Boston}, author = {Segall, C Andrew and Katsaggelos, Aggelos K and Molina, Rafael and Mateos, Javier}, doi = {10.1007/0-306-47004-7_9}, journal = {Super-Resolution Imaging}, pages = {211--242}, publisher = {Kluwer Academic Publishers}, title = {{Super-Resolution from Compressed Video}}, url = {http://link.springer.com/10.1007/0-306-47004-7_9}, year = {2002} }
@article{Jay2002, author = {Williams, J.J. and Katsaggelos, A.K.}, doi = {10.1109/TNN.2002.1021891}, issn = {1045-9227}, journal = {IEEE Transactions on Neural Networks}, month = {jul}, number = {4}, pages = {900--915}, title = {{An HMM-based speech-to-video synthesizer}}, url = {http://ieeexplore.ieee.org/document/1021891/}, volume = {13}, year = {2002} }
@article{Antonio2002, abstract = {We propose a new iterative method for Maximum a Posteriori (MAP) reconstruction of SPECT (Single Photon Emission Computed Tomography) images. The method uses Compound Gauss Markov Random Fields (CGMRF) as prior model and is stochastic for the line process and deterministic for the reconstruction. Synthetic and real images are used to compare the new method with existing ones.}, author = {L{\'{O}}PEZ, ANTONIO and MOLINA, RAFAEL and MATEOS, JAVIER and KATSAGGELOS, AGGELOS K.}, doi = {10.1142/S0218001402001708}, issn = {0218-0014}, journal = {International Journal of Pattern Recognition and Artificial Intelligence}, keywords = {Bayesian reconstruction,Compound Gauss Markov random fields,Deterministic image reconstruction,SPECT imaging,Simulated annealing}, month = {may}, number = {03}, pages = {317--330}, title = {{SPECT IMAGE RECONSTRUCTION USING COMPOUND PRIOR MODELS}}, url = {https://www.worldscientific.com/doi/abs/10.1142/S0218001402001708}, volume = {16}, year = {2002} }
@article{Gerry2002, abstract = {In this paper a hybrid fractal and Discrete Cosine transform (DCT) coder is developed. Drawing on the ability of DCT to remove inter-pixel redundancies and on the ability of fractal transforms to capitalize on long-range correlations within the image, the hybrid coder performs an operationally optimal, in the rate-distortion sense, bit allocation among coding parameters. An orthogonal basis framework is used within which an image segmentation and a hybrid block-based transform are selected jointly. The selection of coefficients in the DCT component of the overall block transform is made a part of the optimization procedure. A Lagrangian multiplier approach is used to optimize the hybrid transform parameters together with the segmentation. Differential encoding of the DC coefficient is employed, with the scanning path based on a 3rd-order Hilbert curve. Simulation results show a significant improvement in quality with respect to the JPEG standard, an approach based on optimization of DCT basis vectors, as well as, the purely fractal techniques.}, author = {Melnikov, Gerry and Katsaggelos, A.K.}, doi = {10.1109/TMM.2002.806531}, issn = {1520-9210}, journal = {IEEE Transactions on Multimedia}, month = {dec}, number = {4}, pages = {413--422}, title = {{A jointly optimal fractal/DCT compression scheme}}, url = {http://ieeexplore.ieee.org/document/1176940/}, volume = {4}, year = {2002} }
@article{galatsanos2002hyperparameter, abstract = {This work is motivated by the observation that it is not possible to reliably estimate simultaneously all the necessary hyperparameters in an image restoration problem when the point-spread function is assumed to be the sum of a known deterministic and an unknown random component. To solve this problem we propose to use gamma hyperpriors for the unknown hyperparameters. Two iterative algorithms that simultaneously restore the image and estimate the hyperparameters are derived, based on the application of evidence analysis within the hierarchical Bayesian framework. Numerical experiments are presented that show the benefits of introducing hyperpriors for this problem. {\textcopyright} 2002 Society of Photo-Optical Instrumentation Engineers.}, author = {Galatsanos, Nikolas P. and Mesarovic, Vladimir Z. and Molina, Rafael and Katsaggelos, Aggelos K. and Mateos, Javier}, doi = {10.1117/1.1487850}, issn = {0091-3286}, journal = {Optical Engineering}, month = {aug}, number = {8}, pages = {1845}, publisher = {Society of Photo-Optical Instrumentation Engineers}, title = {{Hyperparameter estimation in image restoration problems with partially known blurs}}, url = {http://opticalengineering.spiedigitallibrary.org/article.aspx?doi=10.1117/1.1487850}, volume = {41}, year = {2002} }
@article{Lisimachos2001a, abstract = {In this paper, we introduce a new methodology for single pass signal-to-noise ratio (SNR) video scalability based on the partitioning of the DCT coefficients. The DCT coefficients of the displaced frame difference (DFD) for inter-blocks or the intensity for intra-blocks are partitioned into a base layer and one or more enhancement layers, thus, producing an embedded bitstream. Subsets of this bitstream can be transmitted with increasing video quality as measured by the SNR. Given a bit budget for the base and enhancement layers the partitioning of the DCT coefficients is done in a way that is optimal in the operational rate-distortion sense. The optimization is performed using Lagrangian relaxation and dynamic programming (DP). Experimental results are presented and conclusions are drawn.}, author = {Kondi, L.P. and Katsaggelos, A.K.}, doi = {10.1109/83.967389}, issn = {10577149}, journal = {IEEE Transactions on Image Processing}, keywords = {Layered coding,Operational rate-distortion theory,Scalable video coding}, number = {11}, pages = {1613--1620}, title = {{An operational rate-distortion optimal single-pass SNR scalable video coder}}, url = {http://ieeexplore.ieee.org/document/967389/}, volume = {10}, year = {2001} }
@article{tom2001high, author = {Tom, B C and Galatsanos, N P and Katsaggelos, A K}, journal = {KLUWER INTERNATIONAL SERIES IN ENGINEERING AND COMPUTER SCIENCE}, pages = {73--106}, publisher = {KLUWER ACADEMIC PUBLISHERS GROUP}, title = {{High Resolution Image from Low Resolution Images}}, year = {2001} }
@article{Aggelos2001a, author = {Katsaggelos, A.K.}, doi = {10.1109/MSP.2001.924881}, issn = {1053-5888}, journal = {IEEE Signal Processing Magazine}, month = {may}, number = {3}, pages = {2--5}, title = {{Getting into vitual reality}}, url = {https://ieeexplore.ieee.org/document/924881/}, volume = {18}, year = {2001} }
@article{lopez2001spect, author = {Lopez, A. and Molina, R and Katsaggelos, A.K. and Mateos, J}, doi = {10.1109/ICASSP.2001.941318}, isbn = {0-7803-7041-4}, journal = {2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221)}, number = {6-7}, pages = {1909--1912}, publisher = {IEEE}, title = {{SPECT image reconstruction using compound models}}, url = {http://ieeexplore.ieee.org/document/941318/}, volume = {3}, year = {2001} }
@article{nygaard2001rate, abstract = {Signal compression is an important problem encountered in many applications. Various techniques have been proposed over the years for addressing the problem. In this paper, we present a time domain algorithm based on the coding of line segments which are used to approximate the signal. These segments are fit in a way that is optimal in the rate distortion sense. Although the approach is applicable to any type of signal, we focus, in this paper, on the compression of electrocardiogram (ECG) signals. ECG signal compression has traditionally been tackled by heuristic approaches. However, it has been demonstrated [1] that exact optimization algorithms outperform these heuristic approaches by a wide margin with respect to reconstruction error. By formulating the compression problem as a graph theory problem, known optimization theory can be applied in order to yield optimal compression. In this paper, we present an algorithm that will guarantee the smallest possible distortion among all methods applying linear interpolation given an upper bound on the available number of bits. Using a varied signal test set, extensive coding experiments are presented. We compare the results from our coding method to traditional time domain ECG compression methods, as well as, to more recently developed frequency domain methods. Evaluation is based both on percentage root-mean-square difference (PRD) performance measure and visual inspection of the reconstructed signals. The results demonstrate that the exact optimization methods have superior performance compared to both traditional ECG compression methods and the frequency domain methods.}, author = {Nygaard, R. and Melnikov, G. and Katsaggelos, A.K.}, doi = {10.1109/10.900246}, issn = {00189294}, journal = {IEEE Transactions on Biomedical Engineering}, keywords = {Compression,ECG,Rate-distortion optimization,Shortest path}, number = {1}, pages = {28--40}, pmid = {11235588}, publisher = {IEEE}, title = {{A rate distortion optimal ECG coding algorithm}}, url = {http://ieeexplore.ieee.org/document/900246/}, volume = {48}, year = {2001} }
@article{tom2001resolution, abstract = {In this paper, we propose an iterative algorithm for enhancing the resolution of monochrome and color image sequences. Various approaches toward motion estimation are investigated and compared. Improving the spatial resolution of an image sequence critically depends upon the accuracy of the motion estimator. The problem is complicated by the fact that the motion field is prone to significant errors since the original high-resolution images are not available. Improved motion estimates may be obtained by using a more robust and accurate motion estimator, such as a pel-recursive scheme instead of block matching. In processing color image sequences, there is the added advantage of having more flexibility in how the final motion estimates are obtained, and further improvement in the accuracy of the motion field is therefore possible. This is because there are three different intensity fields (channels) conveying the same motion information. In this paper, the choice of which motion estimator to use versus how the final estimates are obtained is weighed to see which issue is more critical in improving the estimated high-resolution sequences. Toward this end, an iterative algorithm is proposed, and two sets of experiments are presented. First, several different experiments using the same motion estimator but three different data fusion approaches to merge the individual motion fields were performed. Second, estimated high-resolution images using the block matching estimator were compared to those obtained by employing a pel recursive scheme. Experiments were performed on a real color image sequence, and performance was measured by the peak signal to noise ratio (PSNR).}, author = {Tom, B.C. and Katsaggelos, A.K.}, doi = {10.1109/83.902292}, issn = {10577149}, journal = {IEEE Transactions on Image Processing}, number = {2}, pages = {278--287}, publisher = {IEEE}, title = {{Resolution enhancement of monochrome and color video using motion compensation}}, url = {http://ieeexplore.ieee.org/document/902292/}, volume = {10}, year = {2001} }
@article{mateos2000nonlinear, abstract = {With block-based compression approaches for both still images and sequences of images annoying blocking artifacts are exhibited, primarily at high compression ratios. They are due to the independent processing (quantization) of the block transformed values of the intensity or the displaced frame difference. In this paper, we propose the application of the hierarchical Bayesian paradigm to the reconstruction of block discrete cosine transform (BDCT) compressed images and the estimation of the required parameters. We derive expressions for the iterative evaluation of these parameters applying the evidence analysis within the hierarchical Bayesian paradigm. The proposed method allows for the combination of parameters estimated at the coder and decoder. The performance of the proposed algorithms is demonstrated experimentally. {\textcopyright} 2000 IEEE.}, author = {Mateos, Javier and Katsaggelos, A.K. and Molina, Rafael}, doi = {10.1109/83.847833}, issn = {10577149}, journal = {IEEE Transactions on Image Processing}, keywords = {Bayesian models,Evidence analysis,Image coding,Post-processing,Reconstruction}, month = {jul}, number = {7}, pages = {1200--1215}, publisher = {New York, NY: Institute of Electrical and Electronics Engineers, 1992-}, title = {{A Bayesian approach for the estimation and transmission of regularization parameters for reducing blocking artifacts}}, url = {http://ieeexplore.ieee.org/document/847833/}, volume = {9}, year = {2000} }
@article{Chun-Jen2000, abstract = {Binocular camera systems are commonly used to construct 3-D-based scene description. However, there is a tradeoff between the length of the camera baseline and the difficulty of the matching problem and the extent of the field of view of the 3-D scene. A large baseline system provides better depth resolution than a smaller baseline system at the expense of a narrower field of view. To increase the depth resolution without increasing the difficulty of the matching problem and decreasing the field of view of the 3-D scene, a sequential 3-D based scene description technique is proposed in this paper. Multiple small-baseline 3-D scene descriptions from a single moving camera or an array of cameras are used to sequentially construct a large baseline 3-D scene description while maintaining the field of view of a small-baseline system. A Bayesian framework using a disparity-space image (DSI) technique for disparity estimation is presented. The cost function for large baseline image matching is designed based not only on the photometric matching error, the smoothness constraint, and the ordering constraint, but also on the previous disparity estimates from smaller baseline stereo image pairs as a prior model. Texture information is registered along the scan path of the camera(s). Experimental results demonstrate the effectiveness of this technique in visual communication applications.}, author = {{Chun-Jen Tsai} and Katsaggelos, Aggelos K A.K. and Tsai, Chun-Jen and Katsaggelos, Aggelos K A.K.}, doi = {10.1109/76.845002}, issn = {10518215}, journal = {IEEE Transactions on Circuits and Systems for Video Technology}, month = {jun}, number = {4}, pages = {576--584}, publisher = {IEEE}, title = {{Sequential construction of 3-D-based scene description}}, url = {http://ieeexplore.ieee.org/document/845002/}, volume = {10}, year = {2000} }
@article{Vladimir1998, abstract = {In this paper, we examine the restoration problem when the point-spread function (PSF) of the degradation system is partially known. For this problem, the PSF is assumed to be the sum of a known deterministic and an unknown random component. This problem has been examined before; however, in most previous works the problem of estimating the parameters that define the restoration filters was not addressed. In this paper, two iterative algorithms that simultaneously restore the image and estimate the parameters of the restoration filter are proposed using evidence analysis (EA) within the hierarchical Bayesian framework. We show that the restoration step of the first of these algorithms is in effect almost identical to the regularized constrained total leastsquares (RCTLS) filter, while the restoration step of the second is identical to the linear minimum mean square-error (LMMSE) filter for this problem. Therefore, in this paper we provide a solution to the parameter estimation problem of the RCTLS filter. We further provide an alternative approach to the expectation-maximization (EM) framework to derive a parameter estimation algorithm for the LMMSE filter. These iterative algorithms are derived in the discrete Fourier transform (DFT) domain; therefore, they are computationally efficient even for large images. Numerical experiments are presented that test and compare the proposed algorithms.}, author = {Galatsanos, N.P. and Mesarovic, V.Z. and Molina, Rafael and Katsaggelos, A.K.}, doi = {10.1109/83.869189}, issn = {10577149}, journal = {IEEE Transactions on Image Processing}, number = {10}, pages = {1784--1797}, title = {{Hierarchical Bayesian image restoration from partially known blurs}}, url = {http://ieeexplore.ieee.org/document/869189/}, volume = {9}, year = {2000} }
@article{Fabian2000, abstract = {A major problem in object-oriented video coding is the efficient encoding of the shape information of arbitrarily shaped objects. Efficient shape coding schemes are also needed in encoding the shape information of video object (VO) in the upcoming MPEG-4 standard. Furthermore, there are many applications where only the shape needs to be encoded, such as CAD, 3D modeling and signature encoding. In this paper, we present an efficient method for the lossy encoding of object shapes which are given as 8-connect chain codes using a mathematical model. We approximate a boundary by a second-order B-spline curve and consider the problem of finding the curve with the lowest bit-rate for a given distortion. The presented scheme is optimal, efficient and offers complete control over the trade-off between bit-rate and distortion. It is an extension of our previous research where we used polygons to approximate a boundary. The main reason for using curves rather than polygons is that curves have a more natural appearance than polygons and can give better coding efficiencies. We present results of the proposed scheme using objects boundaries in different shapes and sizes as well as an MPEG-4 test sequence.}, author = {Meier, Fabian W. and Schuster, Guido M. and Katsaggelos, Aggelos K.}, doi = {10.1016/S0923-5965(99)00045-4}, issn = {09235965}, journal = {Signal Processing: Image Communication}, month = {may}, number = {7-8}, pages = {685--701}, title = {{A mathematical model for shape coding with B-splines}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S0923596599000454}, volume = {15}, year = {2000} }
@article{Yao2000, abstract = {Encoder error resilient (ER) mechanisms adopted by coding standards, and decoder-based error concealment techniques and some closed loop methods are discussed. These techniques provide a complete overview of low latency, low bit-rate video transmission methods for error prone environments. It is found that video coding standards, H.263 and MPEG-4 by including a wide variety of ER tools, can lead to acceptable video quality in highly error prone environment.}, author = {Wang, Yao and Wenger, Stephan and Wen, Jiangtao and Katsaggelos, Aggelos K. A.K. and {Yao Wang} and Wenger, Stephan and {Jiantao Wen} and Katsaggelos, Aggelos K. A.K.}, chapter = {61}, doi = {10.1109/79.855913}, isbn = {10535888}, issn = {10535888}, journal = {IEEE Signal Processing Magazine}, month = {jul}, number = {4}, pages = {61--82}, publisher = {IEEE}, title = {{Error resilient video coding techniques}}, url = {http://ieeexplore.ieee.org/document/855913/}, volume = {17}, year = {2000} }
@article{Gerry2000, abstract = {This paper investigates ways to explore the between frame correlation of shape information within the framework of an operationally rate-distortion (ORD) optimized coder. Contours are approximated both by connected second-order spline segments, each defined by three consecutive control points, and by segments of the motion-compensated reference contours. Consecutive control points are then encoded predictively using angle and run temporal contexts or by tracking the reference contour. We utilize a novel criterion for selecting global object motion vectors, which improves efficiency. The problem is formulated as Lagrangian minimization and solved using dynamic programming. Furthermore, we employ an iterative technique to remove dependency on a particular variable length code and jointly arrive at the ORD globally optimal solution and an optimized conditional parameter distribution.}, author = {Melnikov, Gerry and Schuster, G.M. and Katsaggelos, A.K.}, doi = {10.1109/76.856451}, issn = {10518215}, journal = {IEEE Transactions on Circuits and Systems for Video Technology}, number = {5}, pages = {744--754}, title = {{Shape coding using temporal correlation and joint VLC optimization}}, url = {http://ieeexplore.ieee.org/document/856451/}, volume = {10}, year = {2000} }
@article{Laura1999, author = {Drake, Laura A. and Rutledge, Janet C. and Katsaggelos, Aggelos}, doi = {10.1121/1.427622}, issn = {0001-4966}, journal = {The Journal of the Acoustical Society of America}, month = {oct}, number = {4}, pages = {2238--2238}, title = {{Computational auditory scene analysis‐constrained array processing for sound source separation}}, url = {http://asa.scitation.org/doi/10.1121/1.427622}, volume = {106}, year = {1999} }
@article{Schuster1999, author = {Schuster, G.M. and Melnikov, G. and Katsaggelos, A.K.}, doi = {10.1109/6046.748167}, issn = {15209210}, journal = {IEEE Transactions on Multimedia}, month = {mar}, number = {1}, pages = {3--17}, title = {{A review of the minimum maximum criterion for optimal bit allocation among dependent quantizers}}, url = {http://ieeexplore.ieee.org/document/748167/}, volume = {1}, year = {1999} }
@article{Laura1999a, author = {Drake, Laura A. and Katsaggelos, Aggelos and Zhang, Jun}, doi = {10.1121/1.427787}, issn = {0001-4966}, journal = {The Journal of the Acoustical Society of America}, month = {oct}, number = {4}, pages = {2277--2278}, title = {{Normalizing inter‐band scaling in minimum variance (MV) beamformer estimates of variable‐bandwidth filtered wideband signals}}, url = {http://asa.scitation.org/doi/10.1121/1.427787}, volume = {106}, year = {1999} }
@article{bandyopadhyay2001video, abstract = {Although the transmission of video images over telephone lines has a long history, new technology, particularly video compression techniques, now makes video telephony affordable. The technology is practical, and it can be successful if systems maintain high quality and ease of use. The results of behavioral science studies of visual communication indicate that adding video to voice calls increases the effectiveness of human communication. Human factors and behavioral science techniques can evaluate the quality of visual communication systems and make such systems easy for customers to use. {\textcopyright} 1993 AT&T Technical Journal}, address = {Hoboken, NJ, USA}, author = {Bandyopadhyay, Saurav K. and Kondi, Lisimachos P. and Schuster, Guido M. and Katsaggelos, Aggelos K.}, doi = {10.1002/047134608X.W1919}, issn = {15387305}, journal = {Wiley Encyclopedia of Electrical and Electronics Engineering}, month = {dec}, number = {3}, pages = {7--20}, publisher = {John Wiley & Sons, Inc.}, title = {{Video Telephony}}, url = {https://onlinelibrary.wiley.com/doi/10.1002/047134608X.W1919}, volume = {72}, year = {1999} }
@article{Aggelosf, abstract = {Many optical flow estimation techniques are based on the differential optical flow equation. For these techniques, a locally constant flow model is typically used to allow the construction of an over-determined system of constraint equations. In this paper, the problem of solving the system of optical flow equations using a constraint total least squares (CTLS) approach is investigated. It is shown that by modifying the CTLS approach it becomes identical to a maximum likelihood (ML) approach to the problem. This modification improves the CTLS estimates especially when the estimation window size is small, as is demonstrated experimentally.}, author = {Tsai, C and Galatsanos, N P and Katsaggelos, A K}, journal = {Nsip}, keywords = {&account &address &adjacency &age &composed &const}, pages = {53--56}, title = {{Maximum-likelihood optical flow estimation using differential constraints}}, year = {1999} }
@article{Hong1999, author = {Hong, Min-Cheol and Schwab, Harald and Kondi, Lisimachos P. and Katsaggelos, Aggelos K.}, doi = {10.1016/S0923-5965(98)00061-7}, issn = {09235965}, journal = {Signal Processing: Image Communication}, month = {may}, number = {6-8}, pages = {473--492}, title = {{Error concealment algorithms for compressed video}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S0923596598000617}, volume = {14}, year = {1999} }
@article{Aggelos1999, author = {Katsaggelos, A.K. and Jamieson, L.H.}, doi = {10.1109/MSP.1999.799931}, issn = {1053-5888}, journal = {IEEE Signal Processing Magazine}, month = {nov}, number = {6}, pages = {2--6}, title = {{So Simple evan a child can do it}}, url = {http://ieeexplore.ieee.org/document/799931/}, volume = {16}, year = {1999} }
@article{molina1999bayesian, abstract = {In this paper, we propose the application of the hierarchical Bayesian paradigm to the image restoration problem. We derive expressions for the iterative evaluation of the two hyperparameters applying the evidence and maximum a posteriori (MAP) analysis within the hierarchical Bayesian paradigm. We show analytically that the analysis provided by the evidence approach is more realistic and appropriate than the MAP approach for the image restoration problem. We furthermore study the relationship between the evidence and an iterative approach resulting from the set theoretic regularization approach for estimating the two hyperparameters, or their ratio, defined as the regularization parameter. Finally the proposed algorithms are tested experimentally. {\textcopyright} 1999 IEEE.}, author = {Molina, Rafael and Katsaggelos, A.K. and Mateos, Javier}, doi = {10.1109/83.743857}, issn = {10577149}, journal = {IEEE Transactions on Image Processing}, keywords = {Hierarchical bayesian models,Image restoration,Parameter estimation,Regularization}, number = {2}, pages = {231--246}, publisher = {IEEE}, title = {{Bayesian and regularization methods for hyperparameter estimation in image restoration}}, url = {http://ieeexplore.ieee.org/document/743857/}, volume = {8}, year = {1999} }
@article{Chun-Jen1999c, abstract = {A new divide-and-conquer technique for disparity estimation is proposed in this paper. This technique performs feature matching following the high confidence first principle, starting with the strongest feature point in the stereo pair of scanlines. Once the first matching pair is established, the ordering constraint in disparity estimation allows the original intra-scanline matching problem to be divided into two smaller subproblems. Each subproblem can then be solved recursively until there is no reliable feature point within the subintervals. This technique is very efficient for dense disparity map estimation for stereo images with rich features. For general scenes, this technique can be paired up with the disparity-space image (DSI) technique to compute dense disparity maps with integrated occlusion detection. In this approach, the divide-and-conquer part of the algorithm handles the matching of stronger features and the DSI-based technique handles the matching of pixels in between feature points and the detection of occlusions. An extension to the standard disparity-space technique is also presented to compliment the divide-and-conquer algorithm. Experiments demonstrate the effectiveness of the proposed divide-and-conquer DSI algorithm. {\textcopyright} 1999 IEEE.}, author = {Tsai, Chun Jen and Katsaggelos, Aggelos K. A.K. and {Chun-Jen Tsai} and Katsaggelos, Aggelos K. A.K.}, chapter = {18}, doi = {10.1109/6046.748168}, isbn = {15209210}, issn = {15209210}, journal = {IEEE Transactions on Multimedia}, keywords = {Depth map,Disparity estimation,Disparity-space image,Divide-and-conquer stereo matching}, month = {mar}, number = {1}, pages = {18--29}, publisher = {IEEE}, title = {{Dense disparity estimation with a divide-and-conquer disparity space image technique}}, url = {http://ieeexplore.ieee.org/document/748168/}, volume = {1}, year = {1999} }
@article{Brian1998, abstract = {In this article, the problem of detecting and removing anomalies in digitized animation film is addressed. The impetus of this article comes from the motion picture industry, where several studios are rereleasing vintage film to the public which are often accompanied by visual degradation in the film color, grain, and overall quality. These degradations, or anomalies, can be seen as unwanted visual artifacts that are usually larger than one pixel in size and appear in only one frame. One of the novelties of this article is that the restoration of animation film, as opposed to "real-world" image sequences, is investigated. It often contains additional artifacts and raises other issues not found in most sequences. These artifacts are first defined, and the appropriate steps for their detection and removal are described. Experiments with the proposed algorithm were performed using scenes from the animation film Fantasia, courtesy of Walt Disney Feature Animations, and are discussed in detail. Although our algorithm was developed for the removal of artifacts on animation film, aspects of it can be applied to nonanimated film. {\textcopyright} 1998 John Wiley & Sons, Inc.}, author = {Tom, Brian C. and Kang, Moon Gi and Hong, Min-Cheol and Katsaggelos, Aggelos K.}, doi = {10.1002/(SICI)1098-1098(1998)9:4<283::AID-IMA10>3.0.CO;2-Y}, issn = {0899-9457}, journal = {International Journal of Imaging Systems and Technology}, number = {4}, pages = {283--293}, title = {{Detection and removal of anomalies in digitized animation film}}, url = {https://onlinelibrary.wiley.com/doi/10.1002/(SICI)1098-1098(1998)9:4%3C283::AID-IMA10%3E3.0.CO;2-Y}, volume = {9}, year = {1998} }
@article{Chellappa1998, author = {Chellappa, R and Fukushima, K and Katsaggelos, A.K. and {Sun-Yuan Kung} and LeCun, Y and Nasrabadi, N.M. and Poggio, T.A.}, chapter = {1093}, doi = {10.1109/TIP.1998.704303}, isbn = {1057-7149 1941-0042}, issn = {1057-7149}, journal = {IEEE Transactions on Image Processing}, month = {aug}, number = {8}, pages = {1093--1096}, title = {{Guest Editorial Applications Of Artificial Neural Networks To Image Processing}}, url = {http://ieeexplore.ieee.org/document/704303/}, volume = {7}, year = {1998} }
@article{schuster1998optimal, abstract = {In this paper, we propose an optimal quadtree (QT)-based motion estimator for video compression. It is optimal in the sense that for a given bit budget for encoding the displacement vector field (DVF) and the QT segmentation, the scheme finds a DVF and a QT segmentation which minimizes the energy of the resulting displaced frame difference (DFD). We find the optimal QT decomposition and the optimal DVF jointly using the Lagrangian multiplier method and a multilevel dynamic program. We introduce a new, very fast convex search for the optimal Lagrangian multiplier $\lambda$*, which results in a very fast convergence of the Lagrangian multiplier method. The resulting DVF is spatially inhomogeneous, since large blocks are used in areas with simple motion and small blocks in areas with complex motion. We also propose a novel motion-compensated interpolation scheme which uses the same mathematical tools developed for the QT-based motion estimator. One of the advantages of this scheme is the globally optimal control of the tradeoff between the interpolation error energy and the DVF smoothness. Another advantage is that no interpolation of the DVF is required since we directly estimate the DVF and the QT-segmentation for the frame which needs to be interpolated. We present results with the proposed QT-based motion estimator which show that for the same DFD energy the proposed estimator uses about 25% fewer bits than the commonly used block matching algorithm. We also experimentally compare the interpolated frames using the proposed motion compensated interpolation scheme with the reconstructed original frames. This comparison demonstrates the effectiveness of the proposed interpolation scheme. {\textcopyright} 1998 IEEE.}, author = {Schuster, G.M. and Katsaggelos, A.K.}, doi = {10.1109/83.725359}, issn = {10577149}, journal = {IEEE Transactions on Image Processing}, keywords = {Dynamic programming,Lagrangian relaxation,Motion estimation,Motion-compensated interpolation,Optimal bit allocation,Rate distortion theory,Video compression}, number = {11}, pages = {1505--1523}, publisher = {IEEE}, title = {{An optimal quadtree-based motion estimation and motion-compensated interpolation scheme for video compression}}, url = {http://ieeexplore.ieee.org/document/725359/}, volume = {7}, year = {1998} }
@article{haris1998hybrid, abstract = {A hybrid multidimensional image segmentation algorithm is proposed, which combines edge and region-based techniques through the morphological algorithm of watersheds. An edge-preserving statistical noise reduction approach is used as a preprocessing stage in order to compute an accurate estimate of the image gradient. Then, an initial partitioning of the image into primitive regions is produced by applying the watershed transform on the image gradient magnitude. This initial segmentation is the input to a computationally efficient hierarchical (bottom-up) region merging process that produces the final segmentation. The latter process uses the region adjacency graph (RAG) representation of the image regions. At each step, the most similar pair of regions is determined (minimum cost RAG edge), the regions are merged and the RAG is updated. Traditionally, the above is implemented by storing all RAG edges in a priority queue. We propose a significantly faster algorithm, which additionally maintains the so-called nearest neighbor graph, due to which the priority queue size and processing time are drastically reduced. The final segmentation provides, due to the RAG, one-pixel wide, closed, and accurately localized contours/surfaces. Experimental results obtained with two-dimensional/three-dimensional (2-D/3-D) magnetic resonance images are presented. {\textcopyright} 1998 IEEE.}, author = {Haris, Kostas and Efstratiadis, S.N. and Maglaveras, Nicos and Katsaggelos, A.K.}, doi = {10.1109/83.730380}, issn = {10577149}, journal = {IEEE Transactions on Image Processing}, keywords = {Image segmentation,Nearest neighbor region merging,Noise reduction,Watershed transform}, number = {12}, pages = {1684--1699}, publisher = {IEEE}, title = {{Hybrid image segmentation using watersheds and fast region merging}}, url = {http://ieeexplore.ieee.org/document/730380/}, volume = {7}, year = {1998} }
@article{schuster1998optimal, abstract = {In this paper, we present fast and efficient methods for the lossy encoding of object boundaries that are given as eight-connect chain codes. We approximate the boundary by a polygon, and consider the problem of finding the polygon which leads to the smallest distortion for a given number of bits. We also address the dual problem of finding the polygon which leads to the smallest bit rate for a given distortion. We consider two different classes of distortion measures. The first class is based on the maximum operator and the second class is based on the summation operator. For the first class, we derive a fast and optimal scheme that is based on a shortest path algorithm for a weighted directed acyclic graph. For the second class we propose a solution approach that is based on the Lagrange multiplier method, which uses the above-mentioned shortest path algorithm. Since the Lagrange multiplier method can only find solutions on the convex hull of the operational rate distortion function, we also propose a tree-pruning-based algorithm that can find all the optimal solutions. Finally, we present results of the proposed schemes using objects from the Miss America sequence. {\textcopyright} 1998 IEEE.}, author = {Schuster, G.M. and Katsaggelos, A.K.}, doi = {10.1109/83.650847}, issn = {10577149}, journal = {IEEE Transactions on Image Processing}, keywords = {Boundary encoding,Dynamic programming,Min-max optimization,Object-oriented video compression,Operational rate distortion theory,Shape encoding,Tree pruning}, number = {1}, pages = {13--26}, publisher = {IEEE}, title = {{An optimal polygonal boundary encoding scheme in the rate distortion sense}}, url = {http://ieeexplore.ieee.org/document/650847/}, volume = {7}, year = {1998} }
@article{Guido1998, abstract = {A framework for the rate-distortion operationally optimal encoding of shape information in the intra mode is presented. It is shown that each curve approximation has a natural order. If the control-point encoding scheme is matched to this order and the distortion is carefully defined, then the optimal approximation can be found using a directed acyclic graph (DAG)-shortest-path algorithm. The minimum-maximum distortion optimization problem and the minimum total (average) distortion optimization problem can be both solved by similar means, using an appropriate definition of the DAG weight function.}, author = {Schuster, G.M. and Melnikov, Gerry and Katsaggelos, A.K.}, doi = {10.1109/79.733498}, issn = {10535888}, journal = {IEEE Signal Processing Magazine}, number = {6}, pages = {91--108}, publisher = {IEEE}, title = {{Operationally optimal vertex-based shape coding}}, url = {http://ieeexplore.ieee.org/document/733498/}, volume = {15}, year = {1998} }
@article{schuster1997video, abstract = {In this paper, we present a theory for the optimal bit allocation among quadtree (QT) segmentation, displacement vector field (DVF), and displaced frame difference (DFD). The theory is applicable to variable block size motion-compensated video coders (VBSMCVC), where the variable block sizes are encoded using the QT structure, the DVF is encoded by first-order differential pulse code modulation (DPCM), the DFD is encoded by a block-based scheme, and an additive distortion measure is employed. We derive an optimal scanning path for a QT that is based on a Hilbert curve. We consider the case of a lossless VBSMCVC first, for which we develop the optimal bit allocation algorithm using dynamic programming (DP). We then consider a lossy VBSMCVC, for which we use Lagrangian relaxation, and show how an iterative scheme, which employs the DP-based solution, can be used to find the optimal solution. We finally present a VBSMCVC, which is based on the proposed theory, which employs a DCT-based DFD encoding scheme. We compare the proposed coder with H.263. The results show that it outperforms H.263 significantly in the rate distortion sense, as well as in the subjective sense. {\textcopyright} 1997 IEEE.}, author = {Schuster, G.M. and Katsaggelos, A.K.}, doi = {10.1109/83.641410}, issn = {1057-7149}, journal = {IEEE Transactions on Image Processing}, keywords = {Dynamic programming,Lagrangian relaxation,Optimal bit allocation,Rate distortion theory,Video compression}, month = {nov}, number = {11}, pages = {1487--1502}, publisher = {IEEE}, title = {{A video compression scheme with optimal bit allocation among segmentation, motion, and residual error}}, url = {https://ieeexplore.ieee.org/document/641410/}, volume = {6}, year = {1997} }
@article{kang1997simultaneous, abstract = {In this correspondence, a constrained least-squares multichannel image restoration approach is proposed, in which no prior knowledge of the noise variance at each channel or the degree of smoothness of the original image is required. The regularization functional for each channel is determined by incorporating both within-channel and cross-channel information. It is shown that the proposed smoothing functional has a global minimizer. {\textcopyright} 1997 IEEE.}, author = {{Moon Gi Kang} and Katsaggelos, Aggelos K. A.K. and Kang, Moon Gi and Katsaggelos, Aggelos K. A.K.}, doi = {10.1109/83.568936}, issn = {1057-7149}, journal = {IEEE Transactions on Image Processing}, month = {may}, number = {5}, pages = {774--778}, publisher = {IEEE}, title = {{Simultaneous multichannel image restoration and estimation of the regularization parameters}}, url = {https://ieeexplore.ieee.org/document/568936/}, volume = {6}, year = {1997} }
@article{schuster1997theory, abstract = {In this paper, we address the fundamental problem of optimally splitting a video sequence into two sources of information, the displaced frame difference (DFD) and the displacement vector field (DVF). We first consider the case of a lossless motion-compensated video coder (MCVC), and derive a general dynamic programming (DP) formulation which results in an optimal tradeoff between the DVF and the DFD. We then consider the more important case of a lossy MCVC, and present an algorithm which solves the tradeoff between the rate and the distortion. This algorithm is based on the Lagrange multiplier method and the DP approach introduced for the lossless MCVC. We then present an H.263-based MCVC which uses the proposed optimal bit allocation, and compare its results to H.263. As expected, the proposed coder is superior in the rate-distortion sense. In addition to this, it offers many advantages for a rate control scheme. The presented theory can be applied to build new optimal coders, and to analyze the heuristics employed in existing coders. In fact, whenever one changes an existing coder, the proposed theory can be used to evaluate how the change affects its performance.}, author = {Schuster, G.M. and Katsaggelos, A.K.}, doi = {10.1109/49.650047}, issn = {07338716}, journal = {IEEE Journal on Selected Areas in Communications}, keywords = {Motion estimation,Optimal bit allocation,Quantizer selection,Rate-distortion theory,Video compression}, number = {9}, pages = {1739--1751}, publisher = {IEEE}, title = {{A theory for the optimal bit allocation between displacement vector field and displaced frame difference}}, url = {http://ieeexplore.ieee.org/document/650047/}, volume = {15}, year = {1997} }
@article{banham1997digital, author = {Banham, M.R. and Katsaggelos, A.K.}, doi = {10.1109/79.581363}, issn = {10535888}, journal = {IEEE Signal Processing Magazine}, month = {mar}, number = {2}, pages = {24--41}, publisher = {IEEE}, title = {{Digital image restoration}}, url = {http://ieeexplore.ieee.org/document/581363/}, volume = {14}, year = {1997} }
@article{chellappa1997audio, author = {Chellappa, Rama and {Tsuhan Chen} and Katsaggelos, A.}, doi = {10.1109/79.598590}, issn = {10535888}, journal = {IEEE Signal Processing Magazine}, month = {jul}, number = {4}, pages = {37--38}, publisher = {IEEE}, title = {{Audio-visual interaction in multimodal communication}}, url = {http://ieeexplore.ieee.org/document/598590/}, volume = {14}, year = {1997} }
@article{woods1997rukf, author = {Woods, J W and Hsiang, S T and Banham, M and Katsaggelos, A}, journal = {Ieee Signal Processing Magazine}, number = {6}, pages = {12}, title = {{RUKF performance revisited}}, volume = {14}, year = {1997} }
@article{Taner1997c, abstract = {There are a large number of applications requiring the compression of video at Very Low Bit Rates (VLBR). Such applications include wireless video conferencing, video over the internet, multimedia database retrieval and remote sensing and monitoring. Recently, the MPEG-4 standardization effort has been a motivating factor to find a solution to this challenging problem. The existing approaches to this problem can generally be grouped into block-based, model-based, and object-oriented. Block-based approaches follow the traditional strategy of decoupling the image sequence into blocks, model-based approaches rely on complex 3-D models for specific objects that are encoded, and object-oriented approaches rely on analyzing the scene into differently moving objects. All three approaches exhibit potential problems. Block-based approaches tend to generate artifacts at the boundaries of the blocks, as well as to limit the minimum achievable bit-rate due to the fixed analysis structure of the scene. Model-based codecs are limited by the complex 3-D models of the objects to be encoded. On the other hand, object-oriented codecs can generate a significant overhead due to the analysis of the scene which needs to be transmitted, which in turn can be the limiting factor in achieving the target bit-rates. In this paper, we propose a hybrid object-oriented codec in which the correlations among the three information fields, e.g., motion, segmentation and intensity fields, are exploited both spatially and temporally. In the proposed method, additional intelligence is given to the decoder, resulting in a reduction of the required bandwidth. The residual information is analyzed into three different categories, i.e., occlusion, model failures, and global refinement. The residual information is encoded and transmitted across the channel with other side information. Experimental results are presented which demonstrate the effectiveness of the proposed approach.}, author = {{\"{O}}zcelik, Taner and Katsaggelos, Aggelos K.}, doi = {https://doi.org/10.1023/A:1007946721546}, issn = {13875485}, journal = {Journal of VLSI Signal Processing Systems for Signal, Image, and Video Technology}, number = {2-3}, pages = {137--161}, title = {{A Hybrid Object-Oriented Very Low Bit Rate Video Codec}}, url = {https://link.springer.com/article/10.1023/A:1007946721546}, volume = {17}, year = {1997} }
@article{Guido1997d, abstract = {In this paper we propose an algorithm for the optimal bit allocation among dependent quantizers for the minimum-maximum (MINMAX) distortion criterion. We compare this algorithm to the well-known Lagrange multiplier method for the minimum-average (MINAVE) distortion criterion. We point out the differences between these two distortion criteria, and their implications for coding applications. We argue that even though the MINAVE criterion is more popular, in many cases, the MINMAX criterion is more appropriate. We introduce the algorithms for solving the optimal bit allocation problem among dependent quantizers for both criteria and highlight the similarities and differences. We present the two algorithms using the same frame-work, which sheds new light on the relationship between the MINAVE and the MINMAX criteria. We point out that any problem which can be solved with the MINAVE criterion can also be solved with the MINMAX criterion, since both approaches are based on the same assumptions. {\textcopyright} 1997 Elsevier Science Ltd. All rights reserved.}, author = {Schuster, Guido M. and Katsaggelos, Aggelos K.}, doi = {10.1016/S0083-6656(97)00048-2}, issn = {00836656}, journal = {Vistas in Astronomy}, month = {jan}, number = {3}, pages = {427--437}, title = {{The minimum-average and minimum-maximum criteria in lossy compression}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S0083665697000482}, volume = {41}, year = {1997} }
@article{MunGi1996, abstract = {Restoration of image sequences is an important problem that can be encountered in many image processing applications, such as visual communications, robot guidance, and target tracking. The independent restoration of each frame in an image sequence is a suboptimal approach because the between-frame correlations are not explicitly taken into consideration. In this paper we address this problem by proposing a multichannel restoration approach. The multiple time-frames (channels) of the image sequence are restored simultaneously by using a multichannel regularized least-squares formulation of the problem. The regularization operator captures both within- and between-frame (channel) properties of the image sequence with the explicit use of the displacement vector field. We propose a number of different approaches to obtain the multichannel regularization operator, as well as an algorithm to iteratively compute the restored images. We present experiments that demonstrate the value of the proposed multichannel approach. {\textcopyright} 1996 Academic Press, Inc.}, author = {Choi, Mun Gi and Galatsanos, Nikolas P. and Katsaggelos, Aggelos K.}, doi = {10.1006/jvci.1996.0022}, issn = {10473203}, journal = {Journal of Visual Communication and Image Representation}, month = {sep}, number = {3}, pages = {244--258}, title = {{Multichannel Regularized Iterative Restoration of Motion Compensated Image Sequences}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S104732039690022X}, volume = {7}, year = {1996} }
@article{tull1996iterative, author = {Tull, Damon L. and Katsaggelos, Aggelos K.}, doi = {10.1117/1.601108}, issn = {0091-3286}, journal = {Optical Engineering}, month = {dec}, number = {12}, pages = {3460}, publisher = {SPIE}, title = {{Iterative restoration of fast‐moving objects in dynamic image sequences}}, url = {http://opticalengineering.spiedigitallibrary.org/article.aspx?doi=10.1117/1.601108}, volume = {35}, year = {1996} }
@article{molina1996compound, abstract = {Over the last few years, a growing number of researchers from varied disciplines have been utilizing Markov random fields (MRF) models for developing optimal, robust algorithms for various problems, such as texture analysis, image synthesis, image restoration, classification and segmentation, surface reconstruction, integration of several low level vision modules and sensor fusion. While linear-shift invariant (LSI) models have been generally used for image restoration in astronomy, no much work has been reported on the use of more complex models in this area. In this paper we examine the use of Compound Gaussian Markov Random Fields, (CGMRF), a non LSI model that preserves image discontinuities, to restore astronomical images. Problems on the application of the model arising from the high dynamic range and severe blurring of astronomical images are addressed and two new methods to estimate the real underlying image are proposed. The methods are tested on real astronomical images. Copyright {\textcopyright} 1996 Elsevier Science Ltd.}, author = {Molina, R. and Katsaggelos, A.K. and Mateos, J. and Abad, J.}, doi = {10.1016/S0083-6656(96)00039-6}, issn = {00836656}, journal = {Vistas in Astronomy}, month = {jan}, number = {4}, pages = {539--546}, publisher = {North-Holland}, title = {{Compound Gauss-Markov random fields for astronomical image restoration}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S0083665696000396}, volume = {40}, year = {1996} }
@article{tom1996multichannel, abstract = {Previous work has demonstrated the effectiveness of the expectation-maximization algorithm to restore noisy and blurred single- channel images and simultaneously identify its blur. In addition, a gen- eral framework for processing multichannel images using single-channel techniques has been developed. The authors combine and extend the two approaches to the simultaneous blur identification and restoration of multichannel images. Explicit equations for that purpose are developed for the general case when cross-channel degradations are present. An important difference from the single-channel problem is that the cross power spectra are complex quantities, which further complicates the analysis of the algorithm. The proposed algorithm is very effective at restoring multichannel images, as is demonstrated experimentally.}, author = {Tom, Brian C. and Lay, Kuen-Tsair and Katsaggelos, Aggelos K.}, doi = {10.1117/1.600876}, issn = {0091-3286}, journal = {Optical Engineering}, month = {jan}, number = {1}, pages = {241}, publisher = {SPIE}, title = {{Multichannel image identification and restoration using the expectation‐maximization algorithm}}, url = {http://opticalengineering.spiedigitallibrary.org/article.aspx?doi=10.1117/1.600876}, volume = {35}, year = {1996} }
@article{banham1996spatially, abstract = {In this paper, we present a new spatially adaptive approach to the restoration of noisy blurred images, which is particularly effective at producing sharp deconvolution while suppressing the noise in the flat regions of an image. This is accomplished through a multiscale Kalman smoothing filter applied to a prefiltered observed image in the discrete, separable, 2-D wavelet domain. The prefiltering step involves constrained least-squares filtering based on optimal choices for the regularization parameter. This leads to a reduction in the support of the required state vectors of the multiscale restoration filter in the wavelet domain and improvement in the computational efficiency of the multiscale filter. The proposed method has the benefit that the majority of the regularization, or noise suppression, of the restoration is accomplished by the efficient multiscale filtering of wavelet detail coefficients ordered on quadtrees. Not only does this lead to potential parallel implementation schemes, but it permits adaptivity to the local edge information in the image. In particular, this method changes filter parameters depending on scale, local signal-to-noise ratio (SNR), and orientation. Because the wavelet detail coefficients are a manifestation of the multiscale edge information in an image, this algorithm may be viewed as an "edge-adaptive" multiscale restoration approach. {\textcopyright} 1996 IEEE.}, author = {Banham, M.R. and Katsaggelos, A.K.}, doi = {10.1109/83.491338}, issn = {10577149}, journal = {IEEE Transactions on Image Processing}, month = {apr}, number = {4}, pages = {619--634}, publisher = {IEEE}, title = {{Spatially adaptive wavelet-based multiscale image restoration}}, url = {http://ieeexplore.ieee.org/document/491338/}, volume = {5}, year = {1996} }
@article{chah1995linear, author = {Chah, C.L. and Katsaggelos, A.K. and Sahakian, A.V.}, doi = {10.1109/83.413179}, issn = {10577149}, journal = {IEEE Transactions on Image Processing}, number = {9}, pages = {1328--1333}, publisher = {IEEE}, title = {{Linear-quadratic noise-smoothing filters for quantum-limited images}}, url = {http://ieeexplore.ieee.org/document/413179/}, volume = {4}, year = {1995} }
@article{zhu1995regularized, abstract = {Multichannel images are the multiple image planes (channels) obtained by imaging the same scene using multiple sensors. The validity of multichannel restoration where both within- and between-channel relations are incorporated has already been established using both stochastic and deterministic restoration filters. However, it has been demonstrated that stochastic multichannel filters are extremely sensitive to the estimates of the between-channel statistics. In this paper we avoid the problems associated with multichannel stochastic filters by proposing deterministic multichannel filters that do not require any prior knowledge about either the statistics of the multichannel image or the noise. Regularization based on the multichannel cross-validation function is used to obtain these filters. We examine their relation to multichannel linear minimum mean square error restoration filters and we propose a technique to estimate the variance of the noise. Finally, we show experiments where we test the proposed filters and noise variance estimator using color images. {\textcopyright} 1994 Academic Press. All rights reserved.}, author = {Zhu, W.W. and Galatsanos, N.P. and Katsaggelos, A.K.}, doi = {10.1006/gmip.1995.1005}, institution = {SPIE INTERNATIONAL SOCIETY FOR OPTICAL}, issn = {10773169}, journal = {Graphical Models and Image Processing}, month = {jan}, number = {1}, pages = {38--54}, publisher = {Academic Press}, title = {{Regularized Multichannel Restoration Using Cross-Validation}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S1077316985710052}, volume = {57}, year = {1995} }
@article{brailean1995noise, abstract = {In this paper, a thorough review is presented of noise reduction filters for digital image sequences. Detailed descriptions of several spatiotemporal and temporal noise reduction algorithms are provided. To aid in comparing between these different algorithms, we classify them based on their support (i.e., 3-D or 1-D filter) and whether or not motion compensation is employed. Several algorithms from each of the four categories are implemented and tested on real sequences degraded to various signal-to-noise ratios. These experimental results are discussed and analyzed to determine the overall advantages and disadvantages of the four general classifications, as well as, the individual filters. {\textcopyright} 1995 IEEE}, author = {Brailean, J.C. and Kleihorst, R.P. and Efstratiadis, Serafim and Katsaggelos, A.K. and Lagendijk, R.L.}, doi = {10.1109/5.406412}, issn = {00189219}, journal = {Proceedings of the IEEE}, number = {9}, pages = {1272--1292}, publisher = {IEEE}, title = {{Noise reduction filters for dynamic image sequences: a review}}, url = {http://ieeexplore.ieee.org/document/406412/}, volume = {83}, year = {1995} }
@article{Michael1995, abstract = {This paper considers the concept of robust esti- mation in regularized image restoration. Robust functionals are employed for the representation of both the noise and the signal statistics. Such functionals allow the efficient suppression of a wide variety of noise processes and permit the reconstruction of sharper edges than their quadratic counterparts. A new class of robust entropic functionals is introduced, which operates only on the high-frequency content of the signal and reflects sharp deviations in the signal distribution. This class of functionals can also incorporate prior structural information regarding the original image, in a way similar to the maximum information principle. The convergence properties of robust iterative algorithms are studied for continuously and noncontinuously differentiable functionals. The definition of the robust approach is completed by introducing a method for the optimal selection of the regularization parameter. This method utilizes the structure of robust estimators that lack analytic specification. The properties of robust algorithms are demonstrated through restoration examples in different noise environments. {\textcopyright} 1995 IEEE.}, author = {Zervakis, M.E. and Katsaggelos, A.K. and Kwon, T.M.}, doi = {10.1109/83.388078}, issn = {10577149}, journal = {IEEE Transactions on Image Processing}, month = {jun}, number = {6}, pages = {752--773}, title = {{A class of robust entropic functionals for image restoration}}, url = {http://ieeexplore.ieee.org/document/388078/}, volume = {4}, year = {1995} }
@article{James1995, abstract = {In this paper, we develop a recursive model-based maximum a posteriori (MAP) estimator that simultaneously estimates the displacement vector field (DVF) and the intensity field from a noisy-blurred image sequence. Current motion-compensated spatio-temporal noise filters treat the estimation of the DVF as a preprocessing step. Generally, no attempt is made to verify the accuracy of these estimates prior to their use in the filter. By simultaneously estimating these two fields, we establish a link between the two estimators. It is through this link that the DVF estimate and its corresponding accuracy information are shared with the other intensity estimator, and vice versa. To model the DVF and the intensity field, we use coupled Gauss-Markov (CGM) models. A CGM model consists of two levels: An upper level, which is made up of several submodels with various characteristics, and a lower level or line field, which governs the transitions between the submodels. The CGM models are well suited for estimating the displacement and intensity fields since the resulting estimates preserve the boundaries between the stationary areas present in both fields. Detailed line fields are proposed for the modeling of these boundaries, which also take into account the correlations that exist between these two fields. A Kalman-type estimator results, followed by a decision criterion for choosing the appropriate set of line fields. Several experiments using noisy and noisy-blurred image sequences demonstrate the superior performance of the proposed algorithm with respect to prediction error and mean-square error. {\textcopyright} 1995 IEEE.}, author = {Brailean, J.C. and Katsaggelos, A.K.}, doi = {10.1109/83.413168}, issn = {10577149}, journal = {IEEE Transactions on Image Processing}, number = {9}, pages = {1236--1251}, title = {{Simultaneous recursive displacement estimation and restoration of noisy-blurred image sequences}}, url = {http://ieeexplore.ieee.org/document/413168/}, volume = {4}, year = {1995} }
@article{kang1995general, abstract = {The determination of the regularization parameter is an important issue in regularized image restoration, since it controls the trade-off between fidelity to the data and smoothness of the solution. A number of approaches have been developed in determining this parameter. In this paper, a new paradigm is adopted, according to which the required prior information is extracted from the available data at the previous iteration step, i.e., the partially restored image at each step. We propose the use of a regularization functional instead of a constant regularization parameter. The properties such a regularization functional should satisfy are investigated, and two specific forms of it are proposed. An iterative algorithm is proposed for obtaining a restored image. The regularization functional is defined in terms of the restored image at each iteration step, therefore allowing for the simultaneous determination of its value and the restoration of the degraded image. Both proposed iteration adaptive regularization functionals are shown to result in a smoothing functional with a global minimum, so that its iterative optimization does not depend on the initial conditions. The convergence of the algorithm is established and experimental results are shown. {\textcopyright} 1995 IEEE.}, author = {Katsaggelos, Aggelos K. A.K. and {Moon Gi Kang} and Katsaggelos, Aggelos K. A.K.}, doi = {10.1109/83.382494}, issn = {19410042}, journal = {IEEE Transactions on Image Processing}, month = {may}, number = {5}, pages = {594--602}, publisher = {IEEE}, title = {{General choice of the regularization functional in regularized image restoration}}, url = {http://ieeexplore.ieee.org/document/382494/}, volume = {4}, year = {1995} }
@article{brailean1995recursive, abstract = {In this paper, a recursive model-based algorithm for obtaining the maximum a posteriori (MAP) estimate of the displacement vector field (DVF) from successive image frames of an image sequence is presented. To model the DVF, we develop a nonstationary vector field model called the vector coupled Gauss-Markov (VCGM) model. The VCGM model consists of two levels: an upper level, which is made up of several submodels with various characteristics, and a lower level or line process, which governs the transitions between the submodels. A detailed line process is proposed. The VCGM model is well suited for estimating the DVF since the resulting estimates preserve the boundaries between the differently moving areas in an image sequence. A Kalman type estimator results, followed by a decision criterion for choosing the appropriate line process. Several experiments demonstrate the superior performance of the proposed algorithm with respect to prediction error, interpolation error, and robustness to noise. {\textcopyright} 1995 IEEE}, author = {Brailean, J.C. and Katsaggelos, A.K.}, doi = {10.1109/83.370672}, issn = {10577149}, journal = {IEEE Transactions on Image Processing}, month = {apr}, number = {4}, pages = {416--429}, publisher = {IEEE}, title = {{A recursive nonstationary MAP displacement vector field estimation algorithm}}, url = {http://ieeexplore.ieee.org/document/370672/}, volume = {4}, year = {1995} }
@article{chan1993maximum, abstract = {In this paper, we develop an algorithm for obtain- ing the maximum likelihood (ML) estimate of the displacement vector field (DVF) from two consecutive image frames of an image sequence acquired under quantum-limited conditions. The estimation of the DVF has applications in temporal filtering, object tracking, stereo matching, and frame registration in low-light level image sequences as well as low-dose clinical x-ray image sequences. In the latter case, a controlled x-ray dosage reduction may be utilized to lower the radiation exposure to the patient and the medical staff. The quantum-limited effect is modeled as an undesirable, Poisson-distributed, signal-dependent noise artifact. A Fisher-Bayesian formulation is used in this paper to estimate the DVF and a block component search algorithm is employed in obtaining the solution. Several experiments involving a phantom sequence and a teleconferencing image sequence with realistic motion demonstrate the effectiveness of this estimator in obtaining the DVF under severe quantum noise conditions (20-25 events/pixel). {\textcopyright} 1995 IEEE.}, author = {Chan, C.L. and Katsaggelos, A.K.}, doi = {10.1109/83.388077}, institution = {SPIE}, issn = {10577149}, journal = {IEEE Transactions on Image Processing}, month = {jun}, number = {6}, pages = {743--751}, title = {{Iterative maximum likelihood displacement field estimation in quantum-limited image sequences}}, url = {http://ieeexplore.ieee.org/document/388077/}, volume = {4}, year = {1995} }
@article{yang1995projection, abstract = {At the present time, block-transform coding is probably the most popular approach for image compression. For this approach, the compressed images are decoded using only the transmitted transform data. In this paper, we formulate image decoding as an image recovery problem. According to this approach, the decoded image is reconstructed using not only the transmitted data but, in addition, the prior knowledge that images before compression do not display between-block discontinuities. A spatially adaptive image recovery algorithm is proposed based on the theory of projections onto convex sets. Apart from the data constraint set, this algorithm uses another new constraint set that enforces between-block smoothness. The novelty of this set is that it captures both the local statistical properties of the image and the human perceptual characteristics. A simplified spatially adaptive recovery algorithm is also proposed, and the analysis of its computational complexity is presented. Numerical experiments are shown that demonstrate that the proposed algorithms work better than both the JPEG deblocking recommendation and our previous projection-based image decoding approach. {\textcopyright} 1995 IEEE}, author = {{Yongyi Yang} and Galatsanos, Nikolas P. N.P. and Katsaggelos, Aggelos K. A.K. and Yang, Yongyi and Galatsanos, Nikolas P. N.P. and Katsaggelos, Aggelos K. A.K.}, doi = {10.1109/83.392332}, institution = {SPIE INTERNATIONAL SOCIETY FOR OPTICAL}, issn = {19410042}, journal = {IEEE Transactions on Image Processing}, month = {jul}, number = {7}, pages = {896--908}, publisher = {IEEE}, title = {{Projection-Based Spatially Adaptive Reconstruction of Block-Transform Compressed Images}}, url = {http://ieeexplore.ieee.org/document/392332/}, volume = {4}, year = {1995} }
@article{katsaggelos1995spatially, abstract = {This article develops an iterative spatially adaptive regularized image restoration algorithm. The proposed algorithm is based on the minimization of a weighted smoothing functional. The weighting matrices are defined as functions of the partially restored image at each iteration step. As a result, no prior knowledge about the image and the noise is required, but the weighting matrices as well as the regularization parameter are updated based on the restored image at every step. Conditions for the convexity of the weighted smoothing functional and for the convergence of the iterative algorithm are established for a unique global solution which does not depend on initial conditions. Experimental results are shown with astronomical images which demonstrate the effectiveness of the proposed algorithm. Copyright {\textcopyright} 1995 Wiley Periodicals, Inc., A Wiley Company}, author = {Katsaggelos, Aggelos K. and Kang, Moon Gi}, doi = {10.1002/ima.1850060404}, issn = {08999457}, journal = {International Journal of Imaging Systems and Technology}, number = {4}, pages = {305--313}, publisher = {John Wiley \& Sons, Inc. New York}, title = {{Spatially adaptive iterative algorithm for the restoration of astronomical images}}, url = {https://onlinelibrary.wiley.com/doi/10.1002/ima.1850060404}, volume = {6}, year = {1995} }
@article{banham1994low, abstract = {In this paper, we present a novel coding technique that makes use of the nonstationary characteristics of an image sequence displacement field to estimate and encode motion information. We utilize an MPEG style codec in which the anchor frames in a sequence are encoded with a hybrid approach using quadtree, DCT, and wavelet-based coding techniques. A quadtree structured approach is also utilized for the interframe information. The main objective of the overall design is to demonstrate the coding potential of a newly developed motion estimator called the coupled linearized MAP (CLMAP) estimator. This estimator can be used as a means for producing motion vectors that may be regenerated at the decoder with a coarsely quantized error term created in the encoder. The motion estimator generates highly accurate motion estimates from this coarsely quantized data. This permits the elimination of a separately coded displaced frame difference (DFD) and coded motion vectors. For low bit rate applications, this is especially important because the overhead associated with the transmission of motion vectors may become prohibitive. We exploit both the advantages of the nonstationary motion estimator and the effective compression of the anchor frame coder to improve the visual quality of reconstructed QCIF format color image sequences at low bit rates. Comparisons are made with other video coding methods, including the H.261 and MPEG standards and a pel-recursive-based codec. {\textcopyright} 1994 IEEE}, author = {Banham, M.R. and Brailean, J.C. and Chan, C.L. and Katsaggelos, A.K.}, doi = {10.1109/83.334979}, issn = {10577149}, journal = {IEEE Transactions on Image Processing}, number = {5}, pages = {652--665}, publisher = {IEEE}, title = {{Low bit rate video coding using robust motion vector regeneration in the decoder}}, url = {http://ieeexplore.ieee.org/document/334979/}, volume = {3}, year = {1994} }
@article{Mark1994, abstract = {In this paper, we present a new matrix vector formulation of a wavelet-based subband decomposition. This formulation allows for the decomposition of both the convolution operator and the signal in the subband domain. With this approach, any single channel linear space-invariant filtering problem can be cast into a multichannel framework. We apply this decomposition to the linear space-invariant image restoration problem and propose a family of multichannel linear minimum mean square error (LMMSE) restoration ffiters. These filters explicitly incorporate both within and between subband (channel) relations of the decomposed image. Since only within channel stationarity is assumed in the image model, this approach presents a new method for modeling the nonstationarity of images. Experimental results are presented which test the proposed multichannel LMMSE filters. These experiments show that if accurate estimates of the subband statistics are available, the proposed multichannel filters provide major improvements over the traditional single channel filters. {\textcopyright} 1994 IEEE}, author = {Banham, M.R. and Galatsanos, N.P. and Gonzalez, H.L. and Katsaggelos, A.K.}, doi = {10.1109/83.336250}, issn = {10577149}, journal = {IEEE Transactions on Image Processing}, number = {6}, pages = {821--833}, publisher = {IEEE}, title = {{Multichannel restoration of single channel images using a wavelet-based subband decomposition}}, url = {http://ieeexplore.ieee.org/document/336250/}, volume = {3}, year = {1994} }
@article{tom1994motion, abstract = {In this paper an approach for estimating the motion of arteries in digital angiographic image sequences is proposed. Binary skeleton images are registered using an elastic registration algorithm in order to estimate the motion of the corresponding arteries. This algorithm operates recursively on the skeleton images by considering an autoregressive (AR) model of the deformation in conjunction with a dynamic programming (DP) algorithm. The AR model is used at the pixel level and provides a suitable cost function to DP through the innovation process. In addition, a moving average (MA) model for the motion of the entire skeleton is used in combination with the local AR model for improved registration results. The performance of this motion estimation method is demonstrated on simulated and real digital angiographic image sequences. It is shown that motion estimation using elastic registration of skeletons is very successful especially with low contrast and noisy angiographic images. {\textcopyright} 1994 IEEE}, author = {Tom, B.C.S. and Efstratiadis, S.N. and Katsaggelos, A.K.}, doi = {10.1109/42.310876}, issn = {02780062}, journal = {IEEE Transactions on Medical Imaging}, number = {3}, pages = {450--460}, publisher = {IEEE}, title = {{Motion estimation of skeletonized angiographic images using elastic registration}}, url = {http://ieeexplore.ieee.org/document/310876/}, volume = {13}, year = {1994} }
@article{goyette1994improving, abstract = {In this article the point spread function of autoradiography is experimentally measured and used with digital image restoration techniques to improve the resolution of autoradiographs. We compare two regularized iterative image restoration algorithms applied to autoradiography. A nonlinear filter is used for the removal of film grain noise prior to restoration. Our results indicate a 27 percent improvement in resolution.}, author = {Goyette, J. A. and Lapin, G. D. and Kang, M. G. and Katsaggelos, A. K.}, issn = {07395175}, journal = {IEEE Engineering in Medicine and Biology Magazine}, number = {4}, pages = {571--574}, publisher = {Institute of Electrical and Electronics Engineers Inc.}, title = {{Improving autoradiograph resolution using image restoration techniques}}, volume = {13}, year = {1994} }
@article{kang1994frequency, author = {Kang, Moon Gi and Katsaggelos, Aggelos K.}, doi = {10.1117/12.181245}, issn = {0091-3286}, journal = {Optical Engineering}, month = {oct}, number = {10}, pages = {3222}, publisher = {SPIE}, title = {{Frequency-domain adaptive iterative image restoration and evaluation of the regularization parameter}}, url = {http://opticalengineering.spiedigitallibrary.org/article.aspx?doi=10.1117/12.181245}, volume = {33}, year = {1994} }
@article{Michael1993, abstract = {The pel-recursive approach to motion estimation has been widely studied for compensating progressively scanned, moderate-resolution video. Although pel-recursive algorithms may not be suitable for application to interlaced high-definition television (HDTV), the underlying principle of backward motion compensation, upon which pel-recursive algorithms are based, can be exploited to improve the existing motion compensation algorithms. This paper proposes applying a backward approach to motion compensation to improve the performance of standard block-based algorithms for motion-compensated interlaced HDTV sequences. First, we describe a framework for motion compensation in which motion information is parameterized by a motion operator and a domain for that operator. Within this framework, we characterize the type of motion information represented by forward (e.g. block-based) and backward approaches to motion compensation. We propose a method for combining these two sources of motion information to form an optimal motion-compensated prediction. Simulations on two interlaced HDTV sequences demonstrate performance improvements between 1 and 2 dB over standard block-based methods. {\textcopyright} 1993.}, author = {Orchard, Michael T. and Katsaggelos, Aggelos K.}, doi = {10.1016/0923-5965(93)90012-I}, issn = {09235965}, journal = {Signal Processing: Image Communication}, keywords = {Motion compensation,interlaced HDTV,pel-recursive motion estimation}, month = {dec}, number = {5-6}, pages = {487--501}, title = {{Backward motion compensation for interlaced HDTV}}, url = {https://linkinghub.elsevier.com/retrieve/pii/092359659390012I}, volume = {5}, year = {1993} }
@article{katsaggelos1993two, author = {Katsaggelos, A K}, journal = {Newsl. STScI's Image Restoration Proj}, pages = {30--37}, title = {{Two possible approaches to restoration of HST images.}}, volume = {1}, year = {1993} }
@article{chan1993image, abstract = {Clinical angiography—the procedure of acquiring radiographic (fluoroscopic) image sequences of patients from x-ray based medical systems—has unquestionably aided cardiologists in their assessment of coronary disease. During such trials, however, literally hundreds of x-ray images are gathered, thereby putting these patients and particularly the medical staff at risk. It is desirable to lower the clinical dosages in use to abate this potential danger. With the dosage reduction, however, comes an inevitable sacrifice in image quality. In this paper, the latter problem is addressed by first modeling the noise that arises as a result of this dosage reduction. It is welLKnown that this noise is signal-dependent and PoissoNDistributed. A model for this type of noise in image sequences is formulated and the commonly utilized noise model for single images is shown to be obtainable from the new model. We propose stochastic temporal filtering techniques to enhance clinical fluorosocopy sequences corrupted by quantum mottle. The temporal versions of these niters as developed in this paper are more suitable for filtering image sequences, as correlations along the time axis can be utilized. For these dynamic sequences, the problem of displacement field estimation is treated in conjunction with the filtering stage to ensure that the temporal correlations are taken along the direction of motion to prevent object blur. {\textcopyright} 1993 IEEE}, author = {Chan, C.L. and Katsaggelos, A.K. and Sahakian, A.V.}, doi = {10.1109/42.241890}, issn = {02780062}, journal = {IEEE Transactions on Medical Imaging}, number = {3}, pages = {610--621}, publisher = {IEEE}, title = {{Image sequence filtering in quantum-limited noise with applications to low-dose fluoroscopy}}, url = {http://ieeexplore.ieee.org/document/241890/}, volume = {12}, year = {1993} }
@article{Serafim1993, abstract = {In this paper, an adaptive regularized recursive displacement estimation algorithm is presented. An estimate of the displacement vector field (DVF) is obtained by minimizing the linearized displaced frame difference (DFD) using v subsets (submasks) of a set of points that belong to a causal neighborhood (mask) around the working point. Assuming that the displacement vector is constant at all points inside the mask, v systems of equations are formed based on the corresponding submasks. A set theoretic regularization approach is followed for solving this system of equations by using information about the noise and the solution. An expression for the variance of the linearization error is derived in quantifying the information about the noise. Prior information about the solution is incorporated into the algorithm using a causal oriented smoothness constraint (OSC) which also provides a spatially adaptive prediction model for the estimated DVF. It is shown that certain existing regularized recursive algorithms are special cases of the proposed algorithm, if a single mask is considered. Based on experiments with typical videoconferencing scenes, the improved performance of the proposed algorithm with respect to accuracy, robustness to occlusion and smoothness of the estimated DVF is demonstrated. {\textcopyright} 1993 IEEE}, author = {Efstratiadis, S.N. and Katsaggelos, A.K.}, doi = {10.1109/83.236533}, issn = {10577149}, journal = {IEEE Transactions on Image Processing}, month = {jul}, number = {3}, pages = {341--352}, title = {{An adaptive regularized recursive displacement estimation algorithm}}, url = {http://ieeexplore.ieee.org/document/236533/}, volume = {2}, year = {1993} }
@article{chan1993recursive, abstract = {Quantum noise in image sequences arises in a wide array of applications including medical and astronomical images and remote sensing. It is an undesirable artifact caused by the unavailability or intentional depletion of X-ray and/or light photons necessary for imaging. In this paper, we develop a recursive sliding window, locally linear minimum mean squared error motion-compensated temporal filter for the enhancement of image sequences corrupted by this type of noise. The filter is derived from the formulation of a noise model which describes the underlying physical processes of quantum noise. The recursive implementation of this filter will provide an intuitive manner for addressing subsequent image frames as new observations when acquired under quantum-limited conditions. Experimental results are provided which show the effectiveness of the proposed estimator on both sequences simulated with quantum noise and on real clinical sequences containing natural quantum mottle. {\textcopyright} 1993 Academic Press. All rights reserved.}, author = {Chan, Cheuk L. and Katsaggelos, Aggelos K. and Sahakian, Alan V.}, doi = {10.1006/jvci.1993.1032}, issn = {10473203}, journal = {Journal of Visual Communication and Image Representation}, month = {dec}, number = {4}, pages = {349--363}, publisher = {Academic Press}, title = {{Recursive Locally Linear MMSE Motion-Compensated Image Sequence Filtering under Quantum-Limited Conditions}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S1047320383710321}, volume = {4}, year = {1993} }
@article{yang1993regularized, abstract = {The block discrete cosine transform (BDCT) is by far the most widely used transform for the compression of both still and sequences of images. High compression ratios are usually achieved by discarding information about the BDCT coefficients that is considered unimportant and yield images that exhibit the visually annoying blocking artifact. In this paper reconstruction of images from incomplete BDCT data is examined. The problem is formulated as one of regularized image recovery. According to this formulation, the image in the decoder is reconstructed by using not only the transmitted data but also prior knowledge about the smoothness of the original image, which complements the transmitted data. Two methods are proposed for solving this regularized recovery problem. The first is based on the theory of projections onto convex sets (POCS) while the second is based on the constrained least squares (CLS) approach. For the POCS-based method, a new constraint set is defined that conveys smoothness information not captured by the transmitted BDCT coefficients, and the projection onto it is computed. For the CLS method an objective function is proposed that captures the smoothness properties of the original image. Iterative algorithms are introduced for its minimization. Experimental results are presented that demonstrate that with the regularized reconstruction it is possible to drastically reduce the blocking artifact and improve the performance using both subjective and objective metrics of traditional decoders, which use the transmitted BDCT coefficients only. {\textcopyright} 1993 IEEE}, author = {{Yongyi Yang} and Galatsanos, Nikolas P. N.P. and Katsaggelos, Aggelos K. A.K. and Yang, Yongyi and Galatsanos, Nikolas P. N.P. and Katsaggelos, Aggelos K. A.K.}, chapter = {421}, doi = {10.1109/76.260198}, isbn = {10518215}, issn = {15582205}, journal = {IEEE Transactions on Circuits and Systems for Video Technology}, number = {6}, pages = {421--432}, publisher = {IEEE}, title = {{Regularized Reconstruction to Reduce Blocking Artifacts of Block Discrete Cosine Transform Compressed Images}}, url = {http://ieeexplore.ieee.org/document/260198/}, volume = {3}, year = {1993} }
@article{katsaggelos1993general, abstract = {In this paper, we provide a general framework for performing linear shift-invariant within channel and shift varying across channels processing of stationary multi-channel (MC) signals. Emphasis is given on the restoration of degraded signals. We show that, by utilizing the special structure of semi-block circulant and block diagonal matrices, MC signal processing can be easily carried out in the frequency domain. The generalization of many frequency domain single-channel (SC) signal processing techniques to the MC case is presented. We show that in MC signal processing each frequency component of a signal and system is respectively represented by a small vector and a matrix (of size equal to the number of channels), while in SC signal processing each frequency component in both cases is a scalar. {\textcopyright} 1993 IEEE}, author = {Katsaggelos, A.K. and Lay, K.T. and Galatsanos, N.P.}, doi = {10.1109/83.236528}, issn = {10577149}, journal = {IEEE Transactions on Image Processing}, month = {jul}, number = {3}, pages = {417--420}, publisher = {IEEE}, title = {{A general framework for frequency domain multi-channel signal processing}}, url = {http://ieeexplore.ieee.org/document/236528/}, volume = {2}, year = {1993} }
@article{Aggelos1992, abstract = {In this paper mesh, pyramid, and mesh of pyramids implementations of an iterative image restoration algorithm are proposed. These implementations are based on a single step regularized iterative restoration algorithm. Area-time bounds on the proposed implementations are established. The efficiency of the proposed VLSI algorithms is evaluated by comparing the established bounds against lower bounds on AT 2 , where A is the area of the VLSI chip and T is its computation time.}, author = {KATSAGGELOS, A.K. and KUMAR, S.P.R. and SARRAFZADEH, M.}, doi = {10.1142/S0218126692000179}, issn = {0218-1266}, journal = {Journal of Circuits, Systems and Computers}, month = {sep}, number = {03}, pages = {265--280}, title = {{VLSI ARCHITECTURES FOR ITERATIVE IMAGE RESTORATION}}, url = {https://www.worldscientific.com/doi/abs/10.1142/S0218126692000179}, volume = {02}, year = {1992} }
@article{Kang1992, author = {Kang, M.G. and Katsaggelos, A.K.}, doi = {10.1109/78.157234}, issn = {1053587X}, journal = {IEEE Transactions on Signal Processing}, number = {9}, pages = {2329--2334}, title = {{Simultaneous iterative image restoration and evaluation of the regularization parameter}}, url = {http://ieeexplore.ieee.org/document/157234/}, volume = {40}, year = {1992} }
@article{galatsanos1992methods, abstract = {The application of regularization to ill-conditioned problems necessitates the choice of a regularization parameter which trades fidelity to the data with smoothness of the solution. The value of the regularization parameter depends on the variance of the noise in the data. In this paper the problem of choosing the regularization parameter and estimating the noise variance in image restoration is examined. An error analysis based on an objective mean square error (MSE) criterion is used to motivate regularization. Two new approaches for choosing the regularization parameter and estimating the noise variance are proposed. The proposed and existing methods are compared and their relation to linear minimum mean square error (LMMSE) filtering is examined. Experiments are presented that verify the theoretical results. {\textcopyright} 1992 IEEE}, author = {Galatsanos, N.P. and Katsaggelos, A.K.}, doi = {10.1109/83.148606}, issn = {10577149}, journal = {IEEE Transactions on Image Processing}, month = {jul}, number = {3}, pages = {322--336}, title = {{Methods for choosing the regularization parameter and estimating the noise variance in image restoration and their relation}}, url = {http://ieeexplore.ieee.org/document/148606/}, volume = {1}, year = {1992} }
@article{Joon1992, abstract = {An edge detection algorithm using multi-state adaptive linear neurons (ADALINES) is presented. Although the tri-state ADALINE is only considered in this work, general multi-state input vectors with extreme values are shown to be linearly separable from the rest of the vectors with the same dimension. The input state of each ADALINE is defined using the local mean in a predefined mask. In addition to the binary input states ± 1, the 0 input state is introduced for controlling the noise effect. If the input pattern matches one of the predefined edge patterns, the corresponding pixel is detected as an edge pixel. Experimental results are shown where the proposed detector is compared with both the Canny and LOG edge detectors. {\textcopyright} 1992.}, author = {Paik, Joon K. and Brailean, James C. and Katsaggelos, Aggelos K.}, doi = {10.1016/0031-3203(92)90122-Y}, issn = {00313203}, journal = {Pattern Recognition}, keywords = {Edge detection,Linear neural networks,Pattern recognition}, month = {dec}, number = {12}, pages = {1495--1504}, title = {{An edge detection algorithm using multi-state adalines}}, url = {https://linkinghub.elsevier.com/retrieve/pii/003132039290122Y}, volume = {25}, year = {1992} }
@article{Serafim1992, abstract = {In this paper, an approach for the constrained recursive estimation of the displacement vector field (DVF) in image sequences is presented. An estimate of the displacement vector at the working point is obtained by minimizing the linearized displaced frame difference based on a set of observations that belong to a causal neighborhood (mask). An expression for the variance of the linearization error (noise) is obtained. Because the estimation of the DVF is an ill-posed problem, the solution is constrained by considering an autoregressive (AR) model for the DVF. This AR model is first considered stationary, according to which the two components of the DVF are uncorrelated and each component is modeled by a 2-D discrete Markov sequence. A nonstationary AR model of the DVF is also considered by spatially adapting the model coefficients using a weighted LMS algorithm. Additional information about the solution is incorporated into the algorithm using a causal “oriented smoothness” constraint. Based on the above formulation, a set theoretic regularization approach is followed that results in a weighted constrained least-squares estimation of the DVF. The proposed algorithm shows an improved performance with respect to accuracy, robustness to occlusion, and smoothness of the estimated DVF when applied to typical videoconferencing scenes. {\textcopyright} 1992 IEEE}, author = {Efstratiadis, Serafim N. and Efstratiadis, Serafim N. and Katsaggelos, Aggelos K.}, doi = {10.1109/76.168901}, issn = {15582205}, journal = {IEEE Transactions on Circuits and Systems for Video Technology}, number = {4}, pages = {334--346}, title = {{Nonstationary AR modeling and constrained recursive estimation of the displacement field}}, volume = {2}, year = {1992} }
@article{Aggelos1992a, author = {Aggelos, K Katsaggelos and Richard, J Mammone}, journal = {Journal of Visual Communication and Image Representation}, pages = {305--306 , publisher = Academic Press}, title = {{Image restoration and reconstruction Guest Editors' comments}}, volume = {3}, year = {1992} }
@article{paik1992image, abstract = {In this paper a modified Hopfield neural network model for regularized image restoration is presented. The proposed network allows negative autoconnections for each neuron. A set of algorithms using the proposed neural network model is presented, with various updating modes: i) sequential updates, ii) n-simultaneous updates, and iii) partially asynchronous updates. The sequential algorithm is shown to converge to a local minimum of the energy function after a finite number of iterations. This local minimum is defined in terms of a unit distance neighborhood in the discrete intensity value space. Since an algorithm which updates all n neurons simultaneously is not guaranteed to converge, a modified algorithm is presented, which is called a greedy algorithm. Although the greedy algorithm is not guaranteed to converge to a local minimum, the 1<inf>1</inf> norm of the residual at a fixed point is bounded. It is also shown that the upper bound on the 1<inf>1</inf> norm of the residual can be made arbitrarily small by using an appropriate step size. Finally, a partially asynchronous algorithm is presented, which allows a neuron to have a bounded time delay to communicate with other neurons. Such an algorithm can eliminate the synchronization overhead of synchronous algorithms. It is shown that the /<inf>1</inf> norm of the residual at the fixed point of this algorithm increases as the upper bound on the delay increases. Experimental results are shown testing and comparing the proposed algorithms. {\textcopyright} 1992 IEEE}, author = {Paik, J.K. and Katsaggelos, A.K.}, doi = {10.1109/83.128030}, issn = {10577149}, journal = {IEEE Transactions on Image Processing}, number = {1}, pages = {49--63}, publisher = {IEEE}, title = {{Image restoration using a modified Hopfield network}}, url = {http://ieeexplore.ieee.org/document/128030/}, volume = {1}, year = {1992} }
@article{katsaggelos1992iterative, abstract = {In this paper a nonlinear regularized iterative image restoration algorithm is proposed, according to which no prior knowledge about the noise variance is assumed. The algorithm results from a set-theoretic regularization approach, where bounds of the stabilizing functional and the noise variance, which determine the regularization parameter, are updated at each iteration step. Sufficient conditions for the convergence of the algorithm, as well as an optimality criterion for the regularization parameter, are derived and experimental results are shown. {\textcopyright} 1992.}, author = {Katsaggelos, A.K. and Kang, M.G.}, doi = {10.1016/1047-3203(92)90045-U}, issn = {10473203}, journal = {Journal of Visual Communication and Image Representation}, month = {dec}, number = {4}, pages = {446--455}, publisher = {Academic Press}, title = {{Iterative evaluation of the regularization parameter in regularized image restoration}}, url = {https://linkinghub.elsevier.com/retrieve/pii/104732039290045U}, volume = {3}, year = {1992} }
@article{katsaggelos1991introduction, author = {Katsaggelos, A K}, journal = {Digital Image Restoration}, pages = {1--20}, publisher = {Springer-Verlag}, title = {{Introduction: Review of Image Restoration Algorithms}}, year = {1991} }
@article{Katsaggelos1989, abstract = {This correspondence describes an algorithm for the identification of the blur and the restoration of a noisy blurred image. The original image and the additive noise are modeled as zero-mean Gaussian random processes. Their covariance matrices are unknown parameters. The blurring process is specified by its point spread function, which is also unknown. Maximum likelihood estimation is used to find these unknown parameters. In turn, the EM algorithm is exploited in computing the maximum likelihood estimates. In applying the EM algorithm, the original image is part of the complete data; its estimate is computed in the E-step of the EM iterations. Explicit iterative expressions are derived for the estimation. Experimental results on simulated and photographically blurred images are shown. {\textcopyright} 1991 IEEE}, author = {Katsaggelos, A.K. K. and Lay, K.T. T.}, doi = {10.1109/78.80894}, editor = {Pearlman, William A.}, issn = {1053587X}, journal = {IEEE Transactions on Signal Processing}, month = {mar}, number = {3}, pages = {729--733}, title = {{Maximum likelihood blur identification and image restoration using the EM algorithm}}, url = {http://ieeexplore.ieee.org/document/80894/ http://proceedings.spiedigitallibrary.org/proceeding.aspx?doi=10.1117/12.970155}, volume = {39}, year = {1991} }
@article{MoonGi1991a, author = {Kang, Moon Gi}, doi = {10.1117/12.55893}, issn = {00913286}, journal = {Optical Engineering}, number = {7}, pages = {976}, title = {{Phase estimation using the bispectrum and its application to image restoration}}, url = {https://ivpl.northwestern.edu/wp-content/uploads/2019/02/1991_optical3.pdf http://opticalengineering.spiedigitallibrary.org/article.aspx?doi=10.1117/12.55893}, volume = {30}, year = {1991} }
@article{Galatsanos1991, author = {Galatsanos, N.P. and Katsaggelos, A.K. and Chin, R.T. and Hillery, A.D.}, doi = {10.1109/78.91180}, issn = {1053587X}, journal = {IEEE Transactions on Signal Processing}, number = {10}, pages = {2222--2236}, title = {{Least squares restoration of multichannel images}}, url = {http://ieeexplore.ieee.org/document/91180/}, volume = {39}, year = {1991} }
@article{katsaggelos1996regularized, abstract = {This paper introduces a regularized iterative image restoration algorithm. The development of the algorithm is based on a set theoretic approach to regularization. Deterministic and/or statistical information about the undistorted image and statistical information about the noise are directly incorporated into the iterative procedure. The restored image is the center of an ellipsoid bounding the intersection of two ellipsoids. The proposed algorithm, which has the constrained least squares algorithm as a special case, is also extended into an adaptive iterative restoration algorithm. The spatial adaptivity is introduced to incorporate properties of the human visual system. Convergence of the proposed iterative algorithms is established. For the experimental results which are shown, the adaptively restored images have better quality than the nonadaptively restored ones based on visual observations and on an objective criterion of merit which accounts for the noise masking property of the visual system. {\textcopyright} 1991 IEEE}, author = {Katsaggelos, A.K. and Biemond, Jan and Schafer, R.W. and Mersereau, R.M.}, doi = {10.1109/78.80914}, issn = {1053587X}, journal = {IEEE Transactions on Signal Processing}, month = {apr}, number = {4}, pages = {914--929}, title = {{A regularized iterative image restoration algorithm}}, url = {http://ieeexplore.ieee.org/document/80914/}, volume = {39}, year = {1991} }
@article{katsaggelos1990class, abstract = {In this paper, a class of iterative signal restoration algorithms is derived based on a representation theorem for the general-zed inverse of a matrix. These algorithms exhibit a first or higher order of convergence, and some of them consist of an on-line and an offline computational part. The onditions for convergence, the rate ofconvergence of these algorithms, and the computational load required to achieve the same restoration results are erived. A new iterative algorithm is also presented which exhibits a higher rate of convergence than the standard quadratic algorithm with no extra omputational load. These algorithms can be applied to the restoration of signals of any dimensionality. Iterative restoration algorithms that have appeared in he literature represent special cases of the class of algorithms described here. Therefore, the approach presented here unifies a large number of iterative estoration algorithms. Furthermore, based on the convergence properties of these algorithms, combined algorithms are proposed that incorporate a priori now ledge about the solution in the form of constraints and converge faster than the previously used algorithms. {\textcopyright} 1990 IEEE}, author = {Katsaggelos, A.K. and Efstratiadis, S.N.}, doi = {10.1109/29.56022}, issn = {00963518}, journal = {IEEE Transactions on Acoustics, Speech, and Signal Processing}, month = {may}, number = {5}, pages = {778--786}, publisher = {IEEE}, title = {{A class of iterative signal restoration algorithms}}, url = {http://ieeexplore.ieee.org/document/56022/}, volume = {38}, year = {1990} }
@article{Serafim1990b, author = {Katsaggelos, Aggelos K.}, doi = {10.1117/12.55748}, issn = {00913286}, journal = {Optical Engineering}, number = {12}, pages = {1458}, title = {{Adaptive iterative image restoration with reduced computational load}}, url = {http://opticalengineering.spiedigitallibrary.org/article.aspx?doi=10.1117/12.55748}, volume = {29}, year = {1990} }
@article{efstratiadis1990formula, abstract = {A formula for the direct computation of the steady-state gain of a recursive estimator is derived. The estimator is presented as a general 3-D recursive filter for noise smoothing of 3-D wide-sense Markov fields. The 1-D and 2-D estimators are special cases of the general filter presented. The filter with its steady-state gain computed from the derived formula is very useful because of its computational efficiency. {\textcopyright} 1990, The Institution of Electrical Engineers. All rights reserved.}, author = {Efstratiadis, S.N. and Katsaggelos, A.K.}, doi = {10.1049/el:19901076}, issn = {00135194}, journal = {Electronics Letters}, keywords = {Image processing,Markov fields,Recursive estimation}, number = {20}, pages = {1682}, publisher = {IET Digital Library}, title = {{Formula for the steady-state gain of a recursive estimator}}, url = {https://digital-library.theiet.org/content/journals/10.1049/el_19901076}, volume = {26}, year = {1990} }
@article{lay1990image, author = {Katsaggelos, Aggelos K.}, doi = {10.1117/12.55612}, issn = {00913286}, journal = {Optical Engineering}, number = {5}, pages = {436}, publisher = {SPIE}, title = {{Image identification and restoration based on the expectation-maximization algorithm}}, url = {http://opticalengineering.spiedigitallibrary.org/article.aspx?doi=10.1117/12.55612}, volume = {29}, year = {1990} }
@article{katsaggelos1990multiple, abstract = {In this paper image restoration applications, where multiple distorted versions of the same original image are available, are considered. A general adaptive restoration algorithm is derived on the basis of a set theoretic regularization technique. The adaptivity of the algorithm is introduced in two ways: (a) by a constraint operator which incorporates properties of the response of the human visual system into the restoration process and (b) by a weight matrix which assigns greater importance for the deconvolution process to areas of high spatial activity than to areas of low spatial activity. Different degrees of trust are assigned to the various distorted images depending on the amounts of noise. The proposed algorithm is general and can be used for any type of linear distortion and constraint operators. It can also be used to restore signals other than images. Experimental results obtained by an iterative implementation of the proposed algorithms are presented. {\textcopyright} 1990.}, author = {Katsaggelos, Aggelos K.}, doi = {10.1016/1047-3203(90)90019-R}, issn = {10473203}, journal = {Journal of Visual Communication and Image Representation}, month = {sep}, number = {1}, pages = {93--103}, publisher = {Academic Press}, title = {{A multiple input image restoration approach}}, url = {https://linkinghub.elsevier.com/retrieve/pii/104732039090019R}, volume = {1}, year = {1990} }
@article{sullivan1990new, author = {Katsaggelos, Aggelos K.}, doi = {10.1117/12.55615}, issn = {00913286}, journal = {Optical Engineering}, number = {5}, pages = {471}, publisher = {SPIE}, title = {{New termination rule for linear iterative image restoration algorithms}}, url = {http://opticalengineering.spiedigitallibrary.org/article.aspx?doi=10.1117/12.55615}, volume = {29}, year = {1990} }
@article{Katsaggelos1989a, author = {Katsaggelos, Aggelos K.}, doi = {10.1117/12.7977030}, issn = {0091-3286}, journal = {Optical Engineering}, month = {jul}, number = {7}, title = {{Iterative Image Restoration Algorithms}}, url = {http://opticalengineering.spiedigitallibrary.org/article.aspx?doi=10.1117/12.7977030}, volume = {28}, year = {1989} }
@article{Aggelos1989a, abstract = {A synchronous VLSI implementation of an iterative image restoration algorithm is described in this paper. This implementation is based on a single-step, as well as on a multistep iterative algorithm derived from the single-step regularized iterative restoration algorithm. One processor is assigned to each picture element, with local memory depending on the support of the restoration filter. The implementation, which consists of interprocessor communication and intraprocessor computations, is provided and convergence issues are discussed. {\textcopyright} 1989.}, author = {Katsaggelos, A.K and Kumar, S.P.R}, doi = {10.1016/0165-1684(89)90111-4}, issn = {01651684}, journal = {Signal Processing}, keywords = {Single step/multistep iterative image restoration,synchronous VLSI implementation}, month = {jan}, number = {1}, pages = {29--40}, title = {{Single and multistep iterative image restoration and VLSI implementation}}, url = {https://linkinghub.elsevier.com/retrieve/pii/0165168489901114}, volume = {16}, year = {1989} }
@article{Aggelos1984, author = {Katsaggelos, A. K. and Biemond, J. and Mersereau, R. M. and Schafer, R. W.}, doi = {10.1007/BF01599212}, issn = {0278-081X}, journal = {Circuits, Systems, and Signal Processing}, month = {jun}, number = {2}, pages = {139--160}, title = {{An iterative method for restoring noisy blurred images}}, url = {http://link.springer.com/10.1007/BF01599212}, volume = {3}, year = {1984} }
@book{Reza2022a, address = {Cham}, author = {Borhani, Reza and Borhani, Soheila and Katsaggelos, Aggelos K.}, booktitle = {Fundamentals of Machine Learning and Deep Learning in Medicine}, doi = {10.1007/978-3-031-19502-0}, isbn = {978-3-031-19501-3}, publisher = {Springer International Publishing}, title = {{Fundamentals of Machine Learning and Deep Learning in Medicine}}, url = {https://link.springer.com/10.1007/978-3-031-19502-0}, year = {2022} }
@book{Jeremy2019, author = {Watt, Jeremy and Borhani, Reza and Katsaggelos, Aggelos}, doi = {10.1017/9781108690935}, isbn = {9781108690935}, month = {jan}, publisher = {Cambridge University Press}, title = {{Machine Learning Refined}}, url = {https://www.cambridge.org/highereducation/books/machine-learning-refined/0A64B2370C2F7CE3ACF535835E9D7955#contents}, year = {2020} }
@book{Zhai2007a, address = {Cham}, author = {Zhai, Fan and Katsaggelos, Aggelos}, doi = {10.1007/978-3-031-02244-9}, isbn = {978-3-031-01116-0}, publisher = {Springer International Publishing}, series = {Synthesis Lectures on Image, Video, and Multimedia Processing}, title = {{Joint Source-Channel Video Transmission}}, url = {https://link.springer.com/10.1007/978-3-031-02244-9}, year = {2007} }
@book{Katsaggelos2007a, abstract = {This book focuses on the super resolution of images and video. The authors' use of the term super resolution (SR) is used to describe the process of obtaining a high resolution (HR) image, or a sequence of HR images, from a set of low resolution (LR) observations. This process has also been referred to in the literature as resolution enhancement (RE). SR has been applied primarily to spatial and temporal RE, but also to hyperspectral image enhancement. This book concentrates on motion based spatial RE, although the authors also describe motion free and hyperspectral image SR problems. Also examined is the very recent research area of SR for compression, which consists of the intentional downsampling, during pre-processing, of a video sequence to be compressed and the application of SR techniques, during post-processing, on the compressed sequence. It is clear that there is a strong interplay between the tools and techniques developed for SR and a number of other inverse problems encountered in signal processing (e.g., image restoration, motion estimation). SR techniques are being applied to a variety of fields, such as obtaining improved still images from video sequences (video printing), high definition television, high performance color Liquid Crystal Display (LCD) screens, improvement of the quality of color images taken by one CCD, video surveillance, remote sensing, and medical imaging. The authors believe that the SR/RE area has matured enough to develop a body of knowledge that can now start to provide useful and practical solutions to challenging real problems and that SR techniques can be an integral part of an image and video codec and can drive the development of new coder-decoders (codecs) and standards. Copyright {\textcopyright} 2007 by Morgan & Claypool.}, address = {Cham}, author = {Katsaggelos, Aggelos K. and Molina, Rafael and Mateos, Javier}, booktitle = {Synthesis Lectures on Image, Video, and Multimedia Processing}, doi = {10.1007/978-3-031-02243-2}, isbn = {978-3-031-01115-3}, issn = {15598136}, keywords = {,High resolution,Image compression,Image enhancement,Image processing,LR,RE,Resolution enhancement,SR,Super resolution,Video processing}, number = {1}, pages = {1--146}, publisher = {Springer International Publishing}, series = {Synthesis Lectures on Image, Video, and Multimedia Processing}, title = {{Super Resolution of Images and Video}}, url = {https://link.springer.com/10.1007/978-3-031-02243-2}, volume = {7}, year = {2007} }
@book{Aggelos1998g, abstract = {Signal Recovery Techniques for Image and Video Compression and Transmission establishes a bridge between the fields of signal recovery and image and video compression. Traditionally these fields have developed separately because the problems they examined were regarded as very different, and the techniques used appear unrelated. Recently, though, there is growing consent among the research community that the two fields are quite closely related. Indeed, in both fields the objective is to reconstruct the best possible signal from limited information. The field of signal recovery, which is relatively mature, has long been associated with a wealth of powerful mathematical techniques such as Bayesian estimation and the theory of projects onto convex sets (to name just two). This book illustrates for the first time in a complete volume how these techniques can be brought to bear on the very important problems of image and video compression and transmission. Signal Recovery Techniques for Image and Video Compression and Transmission, which is written by leading practitioners in both fields, is one of the first references that addresses this approach and serves as an excellent information source for both researchers and practicing engineers.}, address = {Boston, MA}, author = {Katsaggelos, Aggelos K. and Galatsanos, Nick P.}, booktitle = {Signal Recovery Techniques for Image and Video Compression and Transmission , publisher = Kluwer academic publishers}, doi = {10.1007/978-1-4757-6514-4}, isbn = {978-1-4419-5063-5}, publisher = {Springer US}, title = {{Signal Recovery Techniques for Image and Video Compression and Transmission}}, url = {https://link.springer.com/10.1007/978-1-4757-6514-4}, year = {1998} }
@book{schuster2013rate, address = {Boston, MA}, author = {Schuster, Guido M. and Katsaggelos, Aggelos K.}, doi = {10.1007/978-1-4757-2566-7}, isbn = {978-1-4419-5172-4}, publisher = {Springer US}, title = {{Rate-Distortion Based Video Compression}}, url = {http://link.springer.com/10.1007/978-1-4757-2566-7}, year = {1997} }
@book{Ed1991, abstract = {The field of image restoration is concerned with the estimation of uncorrupted im ages from noisy, blurred ones. These blurs might be caused by optical distortions, object motion during imaging, or atmospheric turbulence. In many scientific and en gineering applications, such as aerial imaging, remote sensing, electron microscopy, and medical imaging, there is active or potential work in image restoration. The purpose of this book is to provide in-depth treatment of some recent ad vances in the field of image restoration. A survey of the field is provided in the introduction. Recent research results are presented, regarding the formulation of the restoration problem as a convex programming problem, the implementation of restoration algorithms using artificial neural networks, the derivation of non stationary image models (compound random fields) and their application to image estimation and restoration, the development of algorithms for the simultaneous image and blur parameter identification and restoration, and the development of algorithms for restoring scanned photographic images. Special attention is directed to issues of numerical implementation. A large number of pictures demonstrate the performance of the restoration approaches. This book provides a clear understanding of the past achievements, a detailed description of the very important recent developments and the limitations of existing approaches, in the rapidly growing field of image restoration. It will be useful both as a reference book for working scientists and engineers and as a supplementary textbook in courses on image processing.}, author = {{Aggelos K. Katsaggelos (Ed)}}, booktitle = {Digital Image Restoration}, isbn = {978-3-540-53292-7}, pages = {1}, title = {{Digital Image Restoration}}, url = {https://link.springer.com/book/9783642635052}, year = {1991} }
@incollection{Reza2022c, address = {Cham}, author = {Borhani, Reza and Borhani, Soheila and Katsaggelos, Aggelos K.}, booktitle = {Fundamentals of Machine Learning and Deep Learning in Medicine}, doi = {10.1007/978-3-031-19502-0_6}, pages = {111--129}, publisher = {Springer International Publishing}, title = {{From Feature Engineering to Deep Learning}}, url = {https://link.springer.com/10.1007/978-3-031-19502-0_6}, year = {2022} }
@incollection{Reza2022, address = {Cham}, author = {Borhani, Reza and Borhani, Soheila and Katsaggelos, Aggelos K.}, booktitle = {Fundamentals of Machine Learning and Deep Learning in Medicine}, doi = {10.1007/978-3-031-19502-0_2}, pages = {25--46}, publisher = {Springer International Publishing}, title = {{Mathematical Encoding of Medical Data}}, url = {https://link.springer.com/10.1007/978-3-031-19502-0_2}, year = {2022} }
@incollection{Borhani2022a, abstract = {Convolutional Neural Networks are very similar to ordinary Neural Networks from the previous chapter: they are made up of neurons that have learnable weights and biases. Each neuron receives some inputs, performs a dot product and optionally follows it with a non-linearity. The whole network still expresses a single differentiable score function: from the raw image pixels on one end to class scores at the other. And they still have a loss function (e.g. SVM/Softmax) on the last (fully-connected) layer and all the tips/tricks we developed for learning regular Neural Networks still apply. So what does change? ConvNet architectures make the explicit assumption that the inputs are images, which allows us to encode certain properties into the architecture. These then make the forward function more efficient to implement and vastly reduce the amount of parameters in the network.}, address = {Cham}, author = {Borhani, Reza and Borhani, Soheila and Katsaggelos, Aggelos K.}, booktitle = {Fundamentals of Machine Learning and Deep Learning in Medicine}, doi = {10.1007/978-3-031-19502-0_5}, pages = {89--110}, publisher = {Springer International Publishing}, title = {{Linear Classification}}, url = {https://link.springer.com/10.1007/978-3-031-19502-0_5}, year = {2022} }
@incollection{Borhani2022b, abstract = {{\ldots} We test four models proposed in the speech emotion recognition (SER) literature on 15 public and academic licensed datasets in speaker-independent cross-validation. Results indicate differences in the performance of the models which is partly dependent on the dataset and {\ldots}}, address = {Cham}, author = {Borhani, Reza and Borhani, Soheila and Katsaggelos, Aggelos K.}, booktitle = {Fundamentals of Machine Learning and Deep Learning in Medicine}, doi = {10.1007/978-3-031-19502-0_7}, pages = {131--163}, publisher = {Springer International Publishing}, title = {{Convolutional and Recurrent Neural Networks}}, url = {https://link.springer.com/10.1007/978-3-031-19502-0_7}, year = {2022} }
@incollection{Reza2022b, address = {Cham}, author = {Borhani, Reza and Borhani, Soheila and Katsaggelos, Aggelos K.}, booktitle = {Fundamentals of Machine Learning and Deep Learning in Medicine}, doi = {10.1007/978-3-031-19502-0_3}, pages = {47--67}, publisher = {Springer International Publishing}, title = {{Elementary Functions and Operations}}, url = {https://link.springer.com/10.1007/978-3-031-19502-0_3}, year = {2022} }
@incollection{Borhani2022, abstract = {The fundamental idea behind the linear regression algorithm is that it assumes a linear relationship between the features of the dataset. As a result of the pre-defined structure that is imposed on the parameters of the model, it is also called a parametric learning algorithm. Linear regression is used to predict targets that contain real values. As we will see later in Chapter 20on logistic regression, the linear regression model is not adequate to deal with learning problems whose targets are categorical.}, address = {Cham}, author = {Borhani, Reza and Borhani, Soheila and Katsaggelos, Aggelos K.}, booktitle = {Fundamentals of Machine Learning and Deep Learning in Medicine}, doi = {10.1007/978-3-031-19502-0_4}, pages = {69--87}, publisher = {Springer International Publishing}, title = {{Linear Regression}}, url = {https://link.springer.com/10.1007/978-3-031-19502-0_4}, year = {2022} }
@incollection{borhani2022reinforcement, address = {Cham}, author = {Borhani, Reza and Borhani, Soheila and Katsaggelos, Aggelos K.}, booktitle = {Fundamentals of Machine Learning and Deep Learning in Medicine}, doi = {10.1007/978-3-031-19502-0_8}, isbn = {9788494090257}, pages = {165--189}, publisher = {Springer International Publishing}, title = {{Reinforcement Learning}}, url = {https://link.springer.com/10.1007/978-3-031-19502-0_8}, year = {2022} }
@incollection{Brent2019, abstract = {We present an automatic method to estimate flow rate through the orifice in in-vitro 2D color-flow Doppler echocardiographic images. Flow rate properties are important for the assessment of pathologies like mitral regurgitation. We expect this method to be transferable to in-vivo patient data. The method consists of two main parts: (a) detecting a bounding box which encloses aliasing contours and its surroundings (namely a region representative of flow convergence area), (b) application of Convolutional Neural Networks for regression to estimate the flow convergence area. Best result achieved is the 5% mean error for validation data which is from other experiments that were used for training. Given the small number of training data, this method shows promising results.}, author = {Cheimariotis, Grigorios-Aris and Haris, Kostas and Lee, Jeesoo and White, Brent E. and Katsaggelos, Aggelos K. and Thomas, James D. and Maglaveras, Nikolaos}, booktitle = {IFMBE Proceedings}, doi = {10.1007/978-3-030-31635-8_34}, isbn = {9783030316341}, issn = {14339277}, keywords = {Color flow doppler,Deep learning,Flow rate,Mitral regurgitation}, pages = {285--291}, title = {{Flow Convergence Area Estimation on In Vitro Color Flow Doppler Images Using Deep Learning}}, url = {http://link.springer.com/10.1007/978-3-030-31635-8_34}, volume = {76}, year = {2020} }
@incollection{Johanna2019, abstract = {A significant number of oil paintings produced by Georgia O'Keeffe (1887-1986) show surface protrusions of varying width, up to several hundreds of microns. These protrusions are similar to those described in the art conservation literature as metallic soaps. Since the presence of these protrusions raises questions about the state of conservation and long-term prospects for deterioration of these artworks, a 3D-imaging technique, photometric stereo using ultraviolet illumination, was developed for the long-term monitoring of the surface-shape of the protrusions and the surrounding paint. Because the UV fluorescence response of painting materials is isotropic, errors typically caused by non-Lambertian (anisotropic) specularities when using visible reflected light can be avoided providing a more accurate estimation of shape. As an added benefit, fluorescence provides additional contrast information contributing to materials characterization. The developed methodology aims to detect, characterize, and quantify the distribution of micro-protrusions and their development over the surface of entire artworks. Combined with a set of analytical in-situ techniques, and computational tools, this approach constitutes a novel methodology to investigate the selective distribution of protrusions in correlation with the composition of painting materials at the macro-scale. While focused on O'Keeffe's paintings as a case study, we expect the proposed approach to have broader significance by providing a non-invasive protocol to the conservation community to probe topological changes for any relatively flat painted surface of an artwork, and more specifically to monitor the dynamic formation of protrusions, in relation to paint composition and modifications of environmental conditions, loans, exhibitions and storage over the long-term.}, archivePrefix = {arXiv}, arxivId = {1711.08103}, author = {Salvant, Johanna and Walton, Marc and Kronkright, Dale and Yeh, Chia-Kai and Li, Fengqiang and Cossairt, Oliver and Katsaggelos, Aggelos K.}, booktitle = {Metal soaps in art: conservation and research}, doi = {10.1007/978-3-319-90617-1_22}, eprint = {1711.08103}, pages = {375--391}, title = {{Photometric Stereo by UV-Induced Fluorescence to Detect Protrusions on Georgia O'Keeffe's Paintings}}, url = {http://link.springer.com/10.1007/978-3-319-90617-1_22}, year = {2019} }
@incollection{Bishop2017, author = {Bishop, Tom E. and Babacan, S. Derin and Amizic, Bruno and Katsaggelos, Aggelos K. and Chan, Tony and Molina, Rafael}, booktitle = {Blind Image Deconvolution}, doi = {10.1201/9781420007299-5}, month = {dec}, pages = {21--62}, publisher = {CRC Press}, title = {{Blind Image Deconvolution: Problem Formulation and Existing Approaches}}, url = {https://www.taylorfrancis.com/books/9781420007299/chapters/10.1201/9781420007299-5}, year = {2017} }
@incollection{Arun2016, abstract = {The authors present two methods for examining video quality using the Structural Similarity (SSIM) index: Iterative Distortion Estimate (IDE) and Cumulative Distortion using SSIM (CDSSIM). In the first method, three types of slices are iteratively reconstructed frame-by-frame for three different combinations of packet loss and the resulting distortions are combined using their probabilities to give the total expected distortion. In the second method, a cumulative measure of the overall distortion is computed by summing the inter-frame propagation impact to all frames affected by a slice loss. Furthermore, the authors develop a No-Reference (NR) sparse regression framework for predicting the CDSSIM metric to circumvent the real-time computational complexity in streaming video applications. The two methods are evaluated in resource allocation and packet prioritization schemes and experimental results show improved performance and better end-user quality. The accuracy of the predicted CDSSIM values is studied using standard performance measures and a Quartile-Based Prioritization (QBP) scheme.}, author = {Sankisa, Arun and Pandremmenou, Katerina and Pahalawatta, Peshala V. and Kondi, Lisimachos P. and Katsaggelos, Aggelos K.}, booktitle = {Biometrics}, doi = {10.4018/978-1-5225-0983-7.ch028}, isbn = {9781522509844}, pages = {690--709}, publisher = {IGI Global}, title = {{SSIM-Based Distortion Estimation for Optimized Video Transmission over Inherently Noisy Channels}}, url = {http://services.igi-global.com/resolvedoi/resolve.aspx?doi=10.4018/978-1-5225-0983-7.ch028}, volume = {7}, year = {2017} }
@incollection{Zhaofu2016, address = {Taylor & Francis Group, 6000 Broken Sound Parkway NW, Suite 300, Boca Raton, FL 33487-2742}, author = {Chen, Zhaofu and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {Handbook of Robust Low-Rank and Sparse Matrix Decomposition}, doi = {10.1201/b20190-15}, isbn = {9781498724630}, month = {jul}, pages = {14--1--14--19}, publisher = {CRC Press}, title = {{A Variational Approach for Sparse Component Estimation and Low-Rank Matrix Recovery}}, url = {http://www.crcnetbase.com/doi/10.1201/b20190-15}, year = {2016} }
@incollection{katsaggelos2003image, author = {Katsaggelos, Aggelos K and Segall, Andrew and Galatsanos, N P and Driggers, R and Segall, C Andrew and Katsaggelos, Aggelos K}, booktitle = {Encyclopedia of Optical and Photonic Engineering, Second Edition}, doi = {10.1081/E-EOE2-120009511}, month = {sep}, number = {1}, pages = {1--16}, publisher = {CRC Press}, title = {{Digital Image Restoration: Classical}}, url = {https://www.taylorfrancis.com/books/9781351247177/chapters/10.1081/E-EOE2-120009511}, volume = {1}, year = {2015} }
@incollection{Nikolas2015, abstract = {This entry presents a tutorial survey of image enhancement methods. Although this entry concentrates on grayscale images, most of the approaches can be extended to enhance color images by processing separately each of the planes used for the representation of the color image. On the other hand, the correlation among color planes can be used to develop additional enhancement techniques.}, author = {Galatsanos, Nikolas P and Segall, C Andrew and Katsaggelos, Aggelos K}, booktitle = {Encyclopedia of Optical and Photonic Engineering, Second Edition}, doi = {10.1081/E-EOE2-120009510}, isbn = {9781351247184}, month = {sep}, pages = {1--15}, publisher = {CRC Press}, title = {{Digital Images: Enhancement}}, url = {https://www.taylorfrancis.com/books/9781351247177/chapters/10.1081/E-EOE2-120009510}, year = {2015} }
@incollection{Angel2013, abstract = {This chapter presents two multimodal prototypes for remote sensing image classification where user interaction is an important part of the system. The first one applies pansharpening techniques to fuse a panchromatic image and a multispectral image of the same scene to obtain a high resolution (HR) multispectral image. Once the HR image has been classified the user can interact with the system to select a class of interest. The pansharpening parameters are then modified to increase the system accuracy for the selected class without deteriorating the performance of the classifier on the other classes. The second prototype utilizes Bayesian modeling and inference to implement active learning and parameter estimation in a binary kernel-based multispectral classification schemes. In the prototype we developed three different strategies for selecting the more informative pixel to be included in the training set. In the experimental section, the prototypes are described and applied to two real multispectral image classification problems. {\textcopyright} Springer-Verlag Berlin Heidelberg 2013.}, author = {Ruiz, Pablo and Mateos, Javier and Camps-Valls, Gustavo and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {Intelligent Systems Reference Library}, doi = {10.1007/978-3-642-35932-3_5}, isbn = {9783642359316}, issn = {18684394}, pages = {67--81}, title = {{Interactive Pansharpening and Active Classification in Remote Sensing}}, url = {http://link.springer.com/10.1007/978-3-642-35932-3_5}, volume = {48}, year = {2013} }
@incollection{Haomian2013, abstract = {Video content analysis and understanding are active research topics in modern visual computing and communication. In this context, a particular challenging problem that attracts much attention is human action recognition. In this chapter, we propose a new methodology to solve the problem using geometric statistical information. Two new approaches, Differential Luminance Field Trajectory (DLFT) and Luminance Aligned Projection Distance (LAPD), are proposed. Instead of extracting the object or using interest points as a representation, we treat each video clip as a trajectory in a very high dimensionality space and extract the useful statistical geometric information for action recognition. For DLFT, we take advantage of the differential signals which preserve both the temporal and spatial information, and then classify the action by supervised learning. For the LAPD approach, we generate a trajectory for each video clip and compute a distance metric to describe the similarity for classification. Decision is made by applying a K-Nearest Neighbor classifier. Since DLFT is more sensitive in the temporal domain while the LAPD approach can handle more variance in appearance luminance field, a potential fusion of the two methods would yield more desirable properties. Experimental results demonstrate that the methods work effectively and efficiently. The performance is comparable or better and more robust than conventional methods. {\textcopyright} 2013 Elsevier B.V.}, author = {Zheng, Haomian and Li, Zhu and Fu, Yun and Katsaggelos, Aggelos K. and You, Jane}, booktitle = {Handbook of Statistics}, doi = {10.1016/B978-0-444-53859-8.00012-6}, issn = {01697161}, keywords = {Action recognition,Differential luminance field trajectory,Gesture recognition,Luminance aligned projection distance}, pages = {300--325}, title = {{Video Activity Recognition by Luminance Differential Trajectory and Aligned Projection Distance}}, url = {https://linkinghub.elsevier.com/retrieve/pii/B9780444538598000126}, volume = {31}, year = {2013} }
@incollection{Pablo2011, abstract = {In this paper we present an active learning procedure for the two-class supervised classification problem. The utilized methodology exploits the Bayesian modeling and inference paradigm to tackle the problem of kernel-based data classification. This Bayesian methodology is appropriate for both finite and infinite dimensional feature spaces. Parameters are estimated, using the kernel trick, following the evidence Bayesian approach from the marginal distribution of the observations. The proposed active learning procedure uses a criterion based on the entropy of the posterior distribution of the adaptive parameters to select the sample to be included in the training set. A synthetic dataset as well as a real remote sensing classification problem are used to validate the followed approach. {\textcopyright} 2012 Springer-Verlag.}, author = {Ruiz, Pablo and Mateos, Javier and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)}, doi = {10.1007/978-3-642-32436-9_4}, isbn = {9783642324352}, issn = {03029743}, pages = {42--53}, title = {{A Bayesian Active Learning Framework for a Two-Class Classification Problem}}, url = {http://link.springer.com/10.1007/978-3-642-32436-9_4}, volume = {7252 LNCS}, year = {2012} }
@incollection{ruiz2012interactive, author = {RUIZ, P. and TALENTS, J.V. and MATEOS, J. and MOLINA, R. and KATSAGGELOS, A.K.}, booktitle = {Science: Image in Action}, doi = {10.1142/9789814383295_0006}, isbn = {978-981-4383-28-8}, month = {dec}, pages = {77--85}, publisher = {WORLD SCIENTIFIC}, title = {{INTERACTIVE CLASSIFICATION ORIENTED SUPERRESOLUTION OF MULTISPECTRAL IMAGES}}, url = {http://www.worldscientific.com/doi/abs/10.1142/9789814383295_0006}, year = {2011} }
@incollection{Sotirios2010c, author = {Tsaftaris, Sotirios A and Katsaggelos, Aggelos K}, isbn = {9780300155273}, title = {{Contribution to" Matisse: radical invention, 1913-1917"}}, url = {http://eprints.imtlucca.it/787/}, year = {2010} }
@incollection{Serhan2010, abstract = {Modern video encoding systems employ block-based,multi-mode, spatio-temporal prediction methods in order to achieve high compression efficiency. A common practice is to transform, quantize and encode the difference between the prediction and the original along with the system parameters. Obviously, it's crucial to design better prediction and residual encoding methods to obtain higher compression gains. In this work, we examine two such systems which utilize subsampled representations of the sequence and residual data. In the first system, we consider a method for reorganizing, downsampling and interpolating the residual data. In the second system, we propose a new method that employs lower resolution intensity values for spatial and motion-compensated prediction. Both of these methods are macroblock adaptive in the rate-distortion sense. Our experiments show that implementing these methods brings additional compression efficiency compared to the state-of-the-art video encoding standard H.264/AVC. {\textcopyright} 2010 Springer-Verlag Berlin Heidelberg.}, author = {Uslubas, Serhan and Maani, Ehsan and Katsaggelos, Aggelos K.}, booktitle = {Studies in Computational Intelligence}, doi = {10.1007/978-3-642-11686-5_5}, isbn = {9783642116858}, issn = {1860949X}, pages = {167--194}, title = {{A Resolution Adaptive Video Compression System}}, url = {http://link.springer.com/10.1007/978-3-642-11686-5_5}, volume = {280}, year = {2010} }
@incollection{Fan2009, author = {Zhai, Fan and Pahalawatta, Peshala and Katsaggelos, Aggelos K.}, booktitle = {The Essential Guide to Video Processing}, doi = {10.1016/B978-0-12-374456-2.00021-9}, pages = {571--618}, publisher = {Elsevier}, title = {{Wireless Video Streaming}}, url = {https://linkinghub.elsevier.com/retrieve/pii/B9780123744562000219}, year = {2009} }
@incollection{katsaggelos1998image, abstract = {The purpose of this chapter is to demonstrate the application of the EM algorithm in some typical image recovery problems and survey the latest research work that addresses some of the fundamental problems described above. The chapter is organized as follows. In section 29.2, the EM algorithm is reviewed and demonstrated through a simple example. In section 29.3, recent work in convergence, expectation calculation, and the selection of auxiliary functions is discussed. In section 29.4, more complicated applications are demonstrated, followed by a summary in section 29.5. Most of the examples in this chapter are related to image restoration. This choice is motivated by two considerations — the mathematical formulations for image reconstruction are often similar to that of image restoration and a good account on image reconstruction is available in Snyder and Miller [6].}, author = {Zhang, Jun and Katsaggelos, Aggelos}, booktitle = {DSP Handbook}, doi = {10.1201/9781420046076-c29}, month = {nov}, pages = {1--26}, publisher = {CRC Press/IEEE Press}, title = {{Image Recovery Using the EM Algorithm}}, url = {http://www.crcnetbase.com/doi/abs/10.1201/9781420046076-c29}, year = {2009} }
@incollection{Salvador2009, abstract = {This paper deals with the problem of high-resolution (HR) image reconstruction, from a set of degraded, under-sampled, shifted and rotated images, utilizing the variational approximation within the Bayesian paradigm. The proposed inference procedure requires the calculation of the covariance matrix of the HR image given the LR observations and the unknown hyperparameters of the probabilistic model. Unfortunately the size and complexity of such matrix renders its calculation impossible, and we propose and compare three alternative approximations. The estimated HR images are compared with images provided by other HR reconstruction methods. {\textcopyright} 2009 Springer Berlin Heidelberg.}, author = {Villena, Salvador and Vega, Miguel and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)}, doi = {10.1007/978-3-642-04697-1_18}, isbn = {3642046967}, issn = {03029743}, keywords = {Bayesian paradigm,Covariance matrix calculation,High resolution images,Variational inference}, pages = {188--199}, title = {{Parameter Estimation in Bayesian Super-Resolution Image Reconstruction from Low Resolution Rotated and Translated Images}}, url = {http://link.springer.com/10.1007/978-3-642-04697-1_18}, volume = {5807 LNCS}, year = {2009} }
@incollection{KATSAGGELOS2009349, abstract = {Publisher Summary This chapter describes the class of iterative algorithms to the problem of restoring a noisy and blurred image. Iterative algorithms form an important part of optimization theory and numerical analysis. The basic idea behind such an algorithm is that the solution to the problem of recovering a signal, which satisfies certain constraints from its degraded observation, can be found by the alternate implementation of the degradation and the constraint operator. Problems that can be solved with such an iterative algorithm are the phase-only recovery problem, the magnitude-only recovery problem, the band-limited extrapolation problem, the image restoration problem, and the filter design problem. There are a number of advantages associated with iterative restoration algorithms, among which: there is no need to determine or implement the inverse of an operator, knowledge about the solution can be incorporated into the restoration process in a relatively straightforward manner, the solution process can be monitored as it progresses, and the partially restored signal can be utilized in determining unknown parameters pertaining to the solution.}, address = {Boston}, author = {Katsaggelos, Aggelos K and Babacan, S Derin and Chun-Jen, Tsai}, booktitle = {The Essential Guide to Image Processing}, doi = {10.1016/B978-0-12-374457-9.00015-9}, editor = {Bovik, Al}, isbn = {978-0-12-374457-9}, pages = {349--383}, publisher = {Elsevier}, title = {{Iterative Image Restoration}}, url = {https://www.sciencedirect.com/science/article/pii/B9780123744579000159 https://linkinghub.elsevier.com/retrieve/pii/B9780123744579000159}, year = {2009} }
@incollection{Petar2009, abstract = {There has been significant work on investigating the relationship between articulatory movements and vocal tract shape and speech acoustics (Fant, 1960; Flanagan, 1965; Narayanan & Alwan, 2000; Schroeter & Sondhi, 1994). It has been shown that there exists a strong correlation between face motion, and vocal tract shape and speech acoustics (Grant & Braida, 1991; Massaro & Stork, 1998; Summerfield, 1979, 1987, 1992; Williams & Katsaggelos, 2002; Yehia, Rubin, & Vatikiotis-Bateson, 1998). In particular, dynamic lip information conveys not only correlated but also complimentary information to the acoustic speech information. Its integration into an automatic speech recognition (ASR) system, resulting in an audio-visual (AV) system, can potentially increase the system's performance. Although visual speech information is usually used together with acoustic information, there are applications where visual-only (V-only) ASR systems can be employed achieving high recognition rates. Such include small vocabulary ASR (digits, small number of commands, etc.) and ASR in the presence of adverse acoustic conditions. The choice and accurate extraction of visual features strongly affect the performance of AV and V-only ASR systems. The establishment of lip features for speech recognition is a relatively new research topic. Although a number of approaches can be used for extracting and representing visual lip information, unfortunately, limited work exists in the literature in comparing the relative performance of different features. In this chapter, the authors describe various approaches for extracting and representing important visual features, review existing systems, evaluate their relative performance in terms of speech and speaker recognition rates, and discuss future research and development directions in this area. {\textcopyright} 2009, IGI Global.}, author = {Aleksic, Petar S. and Katsaggelos, Aggelos K.}, booktitle = {Visual Speech Recognition}, doi = {10.4018/978-1-60566-186-5.ch002}, isbn = {9781605661865}, pages = {39--69}, publisher = {IGI Global}, title = {{Lip Feature Extraction and Feature Evaluation in the Context of Speech and Speaker Recognition}}, url = {http://services.igi-global.com/resolvedoi/resolve.aspx?doi=10.4018/978-1-60566-186-5.ch002}, year = {2009} }
@incollection{Aleksic2009, author = {Aleksic, Petar S and Potamianos, Gerasminos and Katsaggelos, Aggelos K}, booktitle = {The Essential Guide to Video Processing}, doi = {10.1016/B978-0-12-374456-2.00024-4}, pages = {689--737}, publisher = {Elsevier}, title = {{Audiovisual Speech Processing}}, url = {https://linkinghub.elsevier.com/retrieve/pii/B9780123744562000244}, year = {2009} }
@incollection{Zhu2009, abstract = {The rapid advances in multimedia capture, storage and communication technologies and capabilities have ushered an era of unprecedented growth of digital media content, in audio, visual, and synthetic forms, and both individually and commercially produced. How to manage these data to make them more accessible and searchable to users is a key challenge in current multimedia computing research. In this chapter, the authors discuss the problems and challenges in multimedia data management, and review the state of the art in data structures and algorithms for multimedia indexing, media feature space management and organization, and applications of these techniques in multimedia data management. {\textcopyright} 2009, IGI Global.}, author = {Li, Zhu and Fu, Yun and Yuan, Junsong and Wu, Ying and Katsaggelos, Aggelos and Huang, Thomas S.}, booktitle = {Semantic Mining Technologies for Multimedia Databases}, doi = {10.4018/978-1-60566-188-9.ch019}, isbn = {9781605661889}, pages = {449--475}, publisher = {IGI Global}, title = {{Multimedia Data Indexing}}, url = {http://services.igi-global.com/resolvedoi/resolve.aspx?doi=10.4018/978-1-60566-188-9.ch019}, year = {2009} }
@incollection{Derek2009, abstract = {The information imbedded in the visual dynamics of speech has the potential to improve the performance of speech and speaker recognition systems. The information carried in the visual speech signal compliments the information in the acoustic speech signal, which is particularly beneficial in adverse acoustic environments. Non-invasive methods using low-cost sensors can be used to obtain acoustic and visual biometric signals, such as a person's voice and lip movement, with little user cooperation. These types of unobtrusive biometric systems are warranted to promote widespread adoption of biometric technology in today's society. In this chapter, the authors describe the main components and theory of audio-visual and visual-only speech and speaker recognition systems. Audio-visual corpora are described and a number of speech and speaker recognition systems are reviewed. Finally, various open issues about the system design and implementation, and present future research and development directions in this area are discussed. {\textcopyright} 2009, IGI Global.}, author = {Shiell, Derek J. and Terry, Louis H. and Aleksic, Petar S. and Katsaggelos, Aggelos K.}, booktitle = {Visual Speech Recognition}, doi = {10.4018/978-1-60566-186-5.ch001}, isbn = {9781605661865}, pages = {1--38}, publisher = {IGI Global}, title = {{Audio-Visual and Visual-Only Speech and Speaker Recognition}}, url = {http://services.igi-global.com/resolvedoi/resolve.aspx?doi=10.4018/978-1-60566-186-5.ch001}, year = {2009} }
@incollection{Vega2008, address = {Berlin, Heidelberg}, author = {Vega, Miguel and Mateos, Javier and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {Knowledge-Based Intelligent Information and Engineering Systems}, doi = {10.1007/978-3-540-85567-5_51}, pages = {408--415}, publisher = {Springer Berlin Heidelberg}, title = {{Super Resolution of Multispectral Images Using TV Image Models}}, url = {http://link.springer.com/10.1007/978-3-540-85567-5_51}, year = {2008} }
@incollection{Fan2007d, author = {Zhai, Fan and Katsaggelos, Aggelos}, booktitle = {Joint Source-Channel Video Transmission}, doi = {10.1007/978-3-031-02244-9_3}, pages = {29--45}, title = {{Joint Source-Channel Coding}}, url = {https://link.springer.com/10.1007/978-3-031-02244-9_3}, year = {2007} }
@incollection{Aggelos2007a, author = {Katsaggelos, Aggelos K. and Molina, Rafael and Mateos, Javier}, booktitle = {Super Resolution of Images and Video}, doi = {10.1007/978-3-031-02243-2_6}, pages = {77--90}, title = {{Bayesian Inference Models in Super Resolution}}, url = {https://link.springer.com/10.1007/978-3-031-02243-2_6}, year = {2007} }
@incollection{Aggelos2007b, author = {Katsaggelos, Aggelos K and Molina, Rafael and Mateos, Javier}, booktitle = {Super Resolution of Images and Video}, doi = {10.1007/978-3-031-02243-2_5}, pages = {57--76}, title = {{Estimation of High-Resolution Images}}, url = {https://link.springer.com/10.1007/978-3-031-02243-2_5}, year = {2007} }
@incollection{Fan2007f, author = {Zhai, Fan and Katsaggelos, Aggelos}, booktitle = {Joint Source-Channel Video Transmission}, doi = {10.1007/978-3-031-02244-9_2}, pages = {11--27}, title = {{Elements of a Video Communication System}}, url = {https://link.springer.com/10.1007/978-3-031-02244-9_2}, year = {2007} }
@incollection{Aggelos2007c, author = {Katsaggelos, Aggelos K. and Molina, Rafael and Mateos, Javier}, booktitle = {Super Resolution of Images and Video}, doi = {10.1007/978-3-031-02243-2_4}, pages = {39--56}, title = {{Motion Estimation in Super Resolution}}, url = {https://link.springer.com/10.1007/978-3-031-02243-2_4}, year = {2007} }
@incollection{Katsaggelos2007, author = {Katsaggelos, Aggelos K. and Molina, Rafael and Mateos, Javier}, booktitle = {Super Resolution of Images and Video}, doi = {10.1007/978-3-031-02243-2_2}, pages = {13--18}, title = {{Bayesian Formulation of Super-Resolution Image Reconstruction}}, url = {https://link.springer.com/10.1007/978-3-031-02243-2_2}, year = {2007} }
@incollection{Zhai2007, author = {Zhai, Fan and Katsaggelos, Aggelos}, doi = {10.1007/978-3-031-02244-9_7}, pages = {93--116}, title = {{Wireless Video Transmission}}, url = {https://link.springer.com/10.1007/978-3-031-02244-9_7}, year = {2007} }
@incollection{Aggelos2007, author = {Katsaggelos, Aggelos K. and Molina, Rafael and Mateos, Javier}, booktitle = {Super Resolution of Images and Video}, doi = {10.1007/978-3-031-02243-2_3}, pages = {19--38}, title = {{Low-Resolution Image Formation Models}}, url = {https://link.springer.com/10.1007/978-3-031-02243-2_3}, year = {2007} }
@incollection{Fan2007e, author = {Zhai, Fan and Katsaggelos, Aggelos}, booktitle = {Joint Source-Channel Video Transmission}, doi = {10.1007/978-3-031-02244-9_4}, pages = {47--59}, title = {{Error-Resilient Video Coding}}, url = {https://link.springer.com/10.1007/978-3-031-02244-9_4}, year = {2007} }
@incollection{Aggelos2007d, author = {Katsaggelos, Aggelos K. and Molina, Rafael and Mateos, Javier}, booktitle = {Super Resolution of Images and Video}, doi = {10.1007/978-3-031-02243-2_7}, pages = {91--108}, title = {{Super-Resolution for Compression}}, url = {https://link.springer.com/10.1007/978-3-031-02243-2_7}, year = {2007} }
@incollection{Fan2007b, author = {Zhai, Fan and Katsaggelos, Aggelos}, booktitle = {Joint Source-Channel Video Transmission}, doi = {10.1007/978-3-031-02244-9_6}, pages = {73--92}, title = {{Internet Video Transmission}}, url = {https://link.springer.com/10.1007/978-3-031-02244-9_6}, year = {2007} }
@incollection{Fan2007c, author = {Zhai, Fan and Katsaggelos, Aggelos}, booktitle = {Joint Source-Channel Video Transmission}, doi = {10.1007/978-3-031-02244-9_5}, pages = {61--72}, title = {{Channel Modeling and Channel Coding}}, url = {https://link.springer.com/10.1007/978-3-031-02244-9_5}, year = {2007} }
@incollection{Zhu2005g, author = {Li, Zhu and Katsaggelos, Aggelos K. and Schuster, Guido M.}, booktitle = {Intelligent Multimedia Processing with Soft Computing}, doi = {10.1007/3-540-32367-8_9}, pages = {171--204}, publisher = {Springer Berlin Heidelberg}, title = {{Rate-Distortion Optimal Video Summarization and Coding}}, url = {http://link.springer.com/10.1007/3-540-32367-8_9}, year = {2006} }
@incollection{Antonio2006, abstract = {Emission tomography images are degraded due to the presence of noise and several physical factors, like attenuation and scattering. To remove the attenuation effect from the emission tomography reconstruction, attenuation correction factors (ACFs) are used. These ACFs are obtained from a transmission scan and it is well known that they are homogeneous within each tissue and present abrupt variations in the transition between tissues. In this paper we propose the use of compound Gauss Markov random fields (CGMRF) as prior distributions to model homogeneity within tissues and high variations between regions. In order to find the maximum a posteriori (MAP) estimate of the reconstructed image we propose a new iterative method, which is stochastic for the line process and deterministic for the reconstruction. We apply the ordered subsets (OS) principle to accelerate the image reconstruction. The proposed method is tested and compared with other reconstruction methods. {\textcopyright} Springer-Verlag Berlin Heidelberg 2006.}, author = {L{\'{o}}pez, A. and Mart{\'{i}}n, J. M. and Molina, R. and Katsaggelos, A. K.}, booktitle = {Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)}, doi = {10.1007/11867661_50}, isbn = {3540448942}, issn = {16113349}, pages = {559--569}, title = {{Transmission Tomography Reconstruction Using Compound Gauss-Markov Random Fields and Ordered Subsets}}, url = {http://link.springer.com/10.1007/11867661_50}, volume = {4142 LNCS}, year = {2006} }
@incollection{Sotirios2005b, abstract = {In this paper we propose a procedure for the storage and retrieval of digital signals utilizing DNA. Digital signals are encoded in DNA sequences that satisfy among other constraints the Noise Tolerance Constraint (NTC) that we have previously introduced. NTC takes into account the presence of noise in digital signals by exploiting the annealing between non-perfect complementary sequences. We discuss various issues arising from the development of DNA-based database solutions (i) in vitro (in test tubes, or other materials) for short-term storage and (ii) in vivo (inside organisms) for long-term storage. We discuss the benefits and drawbacks of each scheme and its effects on the codeword design problem and performance. We also propose a new way of constructing the database elements such that a short-term database can be converted into a long term one and vice versa without the need for a re-synthesis. The latter improves efficiency and reduces the cost of a long-term database. {\textcopyright} Springer-Verlag Berlin Heidelberg 2005.}, author = {Tsaftaris, Sotirios A. and Katsaggelos, Aggelos K.}, booktitle = {Lecture Notes in Computer Science}, doi = {10.1007/11539117_160}, issn = {03029743}, number = {PART II}, pages = {1192--1201}, title = {{On Designing DNA Databases for the Storage and Retrieval of Digital Signals}}, url = {http://link.springer.com/10.1007/11539117_160}, volume = {3611}, year = {2005} }
@incollection{Nikolas2000, abstract = {Multichannel images refer to collections of image channels that are not identical but exhibit strong between-channel correlations. Image recovery refers to the computation of an image from observed data that alone do not uniquely define the desired image. Important examples are image denoising, image deblurring, decoding of compressed images, and medical image reconstruction. This chapter focuses on the problem of image recovery as it applies specifically to multichannel images. It presents the multichannel observation model and reviews basic image recovery approaches. It also describes the explicit approach and illustrates it using an example of restoration of video image sequences. Further, the implicit approach is explained and is illustrated using an example of the reconstruction of time-varying medical images. {\textcopyright} 2005 Elsevier Inc. All rights reserved.}, author = {Galatsanos, Nikolas P. and Wernick, Miles N. and Katsaggelos, Aggelos K. and Molina, Rafael}, booktitle = {Handbook of Image and Video Processing}, doi = {10.1016/B978-012119792-6/50076-0}, isbn = {9780121197926}, pages = {203--217}, publisher = {Elsevier}, title = {{Multichannel Image Recovery}}, url = {https://linkinghub.elsevier.com/retrieve/pii/B9780121197926500760}, volume = {12}, year = {2005} }
@incollection{Antonio2005, abstract = {In this work we propose a new method to estimate the scale hyperparameter for transmission tomography in Nuclear Medicine image reconstruction problems. Within the Bayesian paradigm, Evidence Analysis and circulant preconditioners are used to obtain the scale hyperparameter. For the prior distribution, we use Generalized Gaussian Markov Random Fields (GGMRF), a nonquadratic function that preserves the edges in the reconstructed image. The experimental results indicate that the proposed method produces satisfactory reconstructions. {\textcopyright} Springer-Verlag Berlin Heidelberg 2005.}, author = {L{\'{o}}pez, Antonio and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {Lecture Notes in Computer Science}, doi = {10.1007/11492542_56}, issn = {03029743}, number = {II}, pages = {455--462}, title = {{Bayesian Reconstruction for Transmission Tomography with Scale Hyperparameter Estimation}}, url = {http://link.springer.com/10.1007/11492542_56}, volume = {3523}, year = {2005} }
@incollection{Petar2005, abstract = {This chapter focuses on how the joint processing of visual and audio signals, both generated by a talking person, can provide valuable speech information to benefit a number of audiovisual speech processing applications crucial to human-computer interactions. The analysis of visual signals has been done followed by a description of various possible ways of representing and extracting the speech information available in them. It has been shown in the chapter that the obtained visual features can complement features extracted from the acoustic signal and that the two modality representations can be fused together to allow joint audiovisual speech processing. The general bimodal integration framework is subsequently applied to three problems-automatic speech recognition, talking face synthesis, and speaker identification and authentication. In all three cases, issues specific to the particular application have been discussed, several relevant systems that have been reported in the literature have been reviewed, and the results using the implementations developed at IBM Research and Northwestern University have been presented. {\textcopyright} 2005 Elsevier Inc. All rights reserved.}, author = {Aleksic, Petar S. and Potamianos, Gerasimos and Katsaggelos, Aggelos K.}, booktitle = {Handbook of Image and Video Processing}, doi = {10.1016/B978-012119792-6/50134-0}, isbn = {9780121197926}, pages = {1263--XXXIX}, publisher = {Elsevier}, title = {{Exploiting Visual Information in Automatic Speech Processing}}, url = {https://linkinghub.elsevier.com/retrieve/pii/B9780121197926501340}, year = {2005} }
@incollection{Miguel2005, abstract = {Most of the available digital color cameras use a single Coupled Charge Device (CCD) with a Color Filter Array (CFA) in acquiring an image. In order to produce a visible color image a demosaicing process must be applied, which produces undesirable artifacts. This paper addresses the demosaicing problem from a superresolution point of view. Utilizing the Bayesian paradigm, an estimate of the reconstructed images and the model parameters is generated. {\textcopyright} Springer-Verlag Berlin Heidelberg 2005.}, author = {Vega, Miguel and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {Lecture Notes in Computer Science}, doi = {10.1007/11492429_42}, issn = {03029743}, number = {I}, pages = {343--350}, title = {{Bayesian Reconstruction of Color Images Acquired with a Single CCD}}, url = {http://link.springer.com/10.1007/11492429_42}, volume = {3522}, year = {2005} }
@incollection{yang2005recovery, abstract = {This chapter presents recovery-based techniques for compressed image postprocessing-that is, projections onto convex sets (POCS) and the maximum a posteriori (MAP) methodologies. This chapter also presents the basic theory of the POCS methodology and the application of POCS to the compressed image postprocessing problem. The application of the MAP methodology is also presented in the chapter. The objective of postprocessing is to improve the quality of the images produced in the decoder of a lossy image compression system. Such systems produce high compression ratios; however, to do so they also discard information, which is deemed not important, and thus introduce distortion to the original image. The distortions produced by lossy compression algorithms can be categorized into two classes. First, all lossy compression algorithms produce what is called "ringing" artifacts. Around sharp intensity transitions in the image, these oscillations have been classified to be of the Gibbs type. These artifacts appear at high compression ratios in all transform-based codecs because of the low-pass nature of such systems. Second, the classic JPEG compression algorithm at high compression ratios produces what is called the "blocking" artifact. This artifact originates from the independent quantization of the block discrete cosine transform coefficients, which is used in the classic JPEG algorithm. {\textcopyright} 2005 Elsevier Inc. All rights reserved.}, author = {Yang, Y. and Galatsanos, N.P. and Katsaggelos, A.K.}, booktitle = {Handbook of Image and Video Processing}, doi = {10.1016/B978-012119792-6/50108-X}, isbn = {9780121197926}, pages = {761--774}, publisher = {Elsevier}, title = {{Recovery Methods for Postprocessing of Compressed Images}}, url = {https://linkinghub.elsevier.com/retrieve/pii/B978012119792650108X}, year = {2005} }
@incollection{Salvador2004, abstract = {In this paper we consider the problem of reconstructing a high resolution image from a set of undersampled and degraded frames, all of them obtained from high resolution images with unknown shifting displacements between them. We derive an iterative method to estimate the unknown shifts and the high resolution image given the low resolution observations. Finally, the proposed method is tested on real images. {\textcopyright} Springer-Verlag 2004.}, author = {Villena, Salvador and Abad, Javier and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)}, doi = {10.1007/978-3-540-30463-0_64}, isbn = {3540235272}, issn = {16113349}, pages = {509--516}, title = {{Estimation of High Resolution Images and Registration Parameters from Low Resolution Observations}}, url = {http://link.springer.com/10.1007/978-3-540-30463-0_64}, volume = {3287}, year = {2004} }
@incollection{lei2004camera, author = {Lei, B J and Hendriks, E A and Katsaggelos, Aggelos K}, booktitle = {3D Modeling and Animation}, doi = {10.4018/978-1-59140-299-2.ch003}, pages = {70--129}, publisher = {IGI Global}, title = {{Camera Calibration for 3D Reconstruction and View Transformation}}, url = {http://services.igi-global.com/resolvedoi/resolve.aspx?doi=10.4018/978-1-59140-299-2.ch003}, year = {2004} }
@incollection{Aggelos2004, author = {Aggelos, K Katsaggelos}, booktitle = {Digital Image Sequence Processing, Compression, and Analysis}, doi = {10.1201/9780203486788-13}, month = {jul}, pages = {247--274}, publisher = {CRC Press}, title = {{High-resolution images from a sequence of low-resolution observations}}, url = {https://www.taylorfrancis.com/books/9780203486788/chapters/10.1201/9780203486788-13}, year = {2004} }
@incollection{Rafael2004, author = {Molina, Rafael and Katsaggelos, Aggelos and Alvarez, Luis}, booktitle = {Digital Image Sequence Processing, Compression and Analysis}, doi = {10.1201/9780203486788.ch9}, month = {jul}, pages = {233--259 , publisher = chapter}, title = {{High-resolution images from a sequence of low- resolution observations}}, url = {http://www.crcnetbase.com/doi/abs/10.1201/9780203486788.ch9}, volume = {9}, year = {2004} }
@incollection{Peshala2003, author = {Pahalawatta, P. V. and Depalov, D. and Pappas, T. N. and Katsaggelos, A. K.}, booktitle = {Information Processing in Sensor Networks: Second International Workshop, IPSN 2003, Palo Alto, CA, USA, April 22--23, 2003 Proceedings}, doi = {10.1007/3-540-36978-3_36}, pages = {529--544}, title = {{Detection, Classification, and Collaborative Tracking of Multiple Targets Using Video Sensors}}, url = {http://link.springer.com/10.1007/3-540-36978-3_36}, year = {2003} }
@incollection{Luis2003, abstract = {A framework for recovering high-resolution video sequences from sub-sampled and compressed observations is presented. Compression schemes that describe a video sequence through a combination of motion vectors and transform coefficients, e.g. the MPEG and ITU family of standards, are the focus of this paper. A multichannel Bayesian approach is used to incorporate both the motion vectors and transform coefficients in it. Results show a discernable improvement in resolution in the whole sequence, as compared to standard interpolation methods. {\textcopyright} Springer-Verlag Berlin Heidelberg 2003.}, author = {Alvarez, Luis D. and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)}, doi = {10.1007/978-3-540-24586-5_5}, pages = {46--53}, title = {{Multi-channel Reconstruction of Video Sequences from Low-Resolution and Compressed Observations}}, url = {http://link.springer.com/10.1007/978-3-540-24586-5_5}, volume = {2905}, year = {2003} }
@incollection{Antonio2003a, abstract = {In this work we propose a now method to estimate the scale hyperparameter for convex priors with scalable energy functions in Single Photon Emission Computed Tomography (SPECT) image reconstruction problems. Within the Bayesian paradigm, Evidence Analysis and circulant preconditioners are used to obtain the scale hyperparameter. The proposed method is tested on synthetic SPECT images using Generalized Gaussian Markov Random Fields (GGMRF) as scalable prior distributions. {\textcopyright} Springer-Verlag Berlin Heidelberg 2003.}, author = {L{\'{o}}pez, Antonio and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)}, doi = {10.1007/978-3-540-44871-6_52}, isbn = {3540402179}, issn = {16113349}, pages = {445--452}, title = {{Bayesian SPECT Image Reconstruction with Scale Hyperparameter Estimation for Scalable Prior}}, url = {http://link.springer.com/10.1007/978-3-540-44871-6_52}, volume = {2652}, year = {2003} }
@incollection{Brian2002, address = {Boston}, author = {Tom, Brian C. and Galatsanos, Nikolas P. and Katsaggelos, Aggelos K.}, booktitle = {Super-Resolution Imaging}, doi = {10.1007/0-306-47004-7_4}, pages = {73--105}, publisher = {Kluwer Academic Publishers}, title = {{Reconstruction of a High Resolution Image from Multiple Low Resolution Images}}, url = {http://link.springer.com/10.1007/0-306-47004-7_4}, year = {2002} }
@incollection{Aggelos2000a, author = {Katsaggelos, Agggelos K and Tsai, Chun-Jen}, booktitle = {Handbook of Image and Video Processing}, pages = {191--206}, title = {{Iterative image restoration}}, year = {2000} }
@incollection{Aggelos2001, author = {Melnikov, Gerry and Katsaggelos, Aggelos}, booktitle = {Multimedia Image and Video Processing}, doi = {10.1201/9781420037562.ch11}, month = {aug}, pages = {331--362 , publisher = CRC Press}, title = {{Rate-Distortion Techniques in Image and Video Coding}}, url = {http://www.crcnetbase.com/doi/abs/10.1201/9781420037562.ch11}, year = {2000} }
@incollection{Chun-Jen1998a, address = {London}, author = {Tsai, Chun-Jen and Katsaggelos, Aggelos K.}, booktitle = {Noblesse Workshop on Non-Linear Model Based Image Analysis}, doi = {10.1007/978-1-4471-1597-7_45}, pages = {289--294}, publisher = {Springer London}, title = {{Dense Disparity Estimation via Global and Local Matching}}, url = {http://link.springer.com/10.1007/978-1-4471-1597-7_45}, year = {1998} }
@incollection{Aggelos1998d, address = {Boston, MA}, author = {Banham, Mark R. and Brailean, James C.}, booktitle = {Signal Recovery Techniques for Image and Video Compression and Transmission}, doi = {10.1007/978-1-4757-6514-4_5}, pages = {133--174}, publisher = {Springer US}, title = {{Video Coding Standards: Error Resilience and Concealment}}, url = {http://link.springer.com/10.1007/978-1-4757-6514-4_5}, volume = {5}, year = {1998} }
@incollection{katsaggelos1998iterative, author = {Katsaggelos, A K}, booktitle = {DSP Handbook}, pages = {31--34}, publisher = {CRC Press/IEEE Press}, title = {{Iterative Approaches to Image Restoration}}, year = {1998} }
@incollection{Aggelos1998c, address = {Boston, MA}, author = {Molina, Rafael and Katsaggelos, Aggelos K. and Mateos, Javier}, booktitle = {Signal Recovery Techniques for Image and Video Compression and Transmission}, doi = {10.1007/978-1-4757-6514-4_1}, pages = {1--34}, publisher = {Springer US}, title = {{Removal of Blocking Artifacts Using a Hierarchical Bayesian Approach}}, url = {https://link.springer.com/10.1007/978-1-4757-6514-4_1}, year = {1998} }
@incollection{Aggelos1997, author = {Chan, Cheuk L. and Katsaggelos, A.K. and Sahakian, A.V.}, booktitle = {Medical Imaging Systems Techniques and Applications: Cardiovascular Systems}, isbn = {9781315078274}, pages = {93--145 , publisher = Gordon and Breach Publishers,}, title = {{Techniques in Image Sequence Filtering for Clinical Angiography: Cardiovascular Systems}}, year = {1997} }
@incollection{Guido1997a, address = {Boston, MA}, author = {Schuster, Guido M. and Katsaggelos, Aggelos K.}, booktitle = {Rate-Distortion Based Video Compression}, doi = {10.1007/978-1-4757-2566-7_4}, pages = {73--122}, publisher = {Springer US}, title = {{General Contributions}}, url = {http://link.springer.com/10.1007/978-1-4757-2566-7_4}, year = {1997} }
@incollection{Galatsanos1997, abstract = {In this chapter two new approaches are proposed that address two problems that are commonly encountered in the context of image restoration for medical imaging applications. First, we considered the problem of regularized image restoration when no prior information about the original image and the noise is available. A new paradigm, is adopted according to which the required information is extracted from the available data at the previous iteration step, ie, the partially restored image at each step.}, author = {Galatsanos, Nikolas P. and Mesarovi{\'{c}}, Vladimir Z. and {Moon Gi}, Kang and Katsasselos, Aggelos K.}, booktitle = {Medical Imaging Systems Techniques and Applications: Diagnosis Optimization Techniques}, pages = {1--68}, title = {{On Image Restoration Techniques for Medical Imaging}}, url = {https://www.academia.edu/2704286/On_Image_Restoration_Techniques_for_Medical_Imaging}, year = {1997} }
@incollection{Rafaet1997, abstract = {Over the last few years, a growing number of researchers from varied disciplines have been utilizing Markov random fields (MRF) models for developing optimal, robust algorithms for various problems, such as texture analysis, image synthesis, classification and segmentation, surface reconstruction, integration of several low level vision modules, sensor fusion and image restoration. However. not much work has been reported on the use of this model in image restoration. In this paper we examine the use of compound Gauss Markov random fields (CGMRF) to restore severely blurred high range images. For this deblurring problem, the convergence of the Simulated Annealing (SA) and Iterative Conditional Mode (ICM) algorithms has not been established. We propose two new iterative restoration algorithms which extend the classical SA and ICM approaches. Their convergence is established and they are tested on real and synthetic images.}, author = {Molina, Rafael and Katsaggelos, Aggelos K. and Mateos, Javier and Hermoso, Aurora}, booktitle = {Energy Minimization Methods in Computer Vision and Pattern Recognition}, doi = {10.1007/3-540-62909-2_76}, isbn = {3540629092 16113349 , issue = 4}, pages = {117--132}, title = {{Restoration of severely blurred high range images using stochastic and deterministic relaxation algorithms in compound gauss Markov random fields}}, url = {http://link.springer.com/10.1007/3-540-62909-2_76}, volume = {1223}, year = {1997} }
@incollection{Guido1997c, address = {Boston, MA}, author = {Schuster, Guido M. and Katsaggelos, Aggelos K.}, booktitle = {Rate-Distortion Based Video Compression}, doi = {10.1007/978-1-4757-2566-7_2}, pages = {13--42}, publisher = {Springer US}, title = {{Review of Lossy Video Compression}}, url = {http://link.springer.com/10.1007/978-1-4757-2566-7_2}, year = {1997} }
@incollection{Taner1997b, address = {Boston, MA}, author = {{\"{O}}zc̣elik, Taner and Katsaggelos, Aggelos K.}, booktitle = {Video Data Compression for Multimedia Computing}, doi = {10.1007/978-1-4615-6239-9_9}, pages = {313--353}, publisher = {Springer US}, title = {{Very Low Bit Rate Video Coding Based on Statistical Spatio-Temporal Prediction of Motion, Segmentation and Intensity Fields}}, url = {http://link.springer.com/10.1007/978-1-4615-6239-9_9}, year = {1997} }
@incollection{Guido1997, address = {Boston, MA}, author = {Schuster, Guido M. and Katsaggelos, Aggelos K.}, booktitle = {Rate-Distortion Based Video Compression}, doi = {10.1007/978-1-4757-2566-7_5}, pages = {123--150}, publisher = {Springer US}, title = {{Optimal Motion Estimation and Motion Compensated Interpolation for Video Compression}}, url = {http://link.springer.com/10.1007/978-1-4757-2566-7_5}, year = {1997} }
@incollection{James1992, author = {Brailean, James C. and Katsaggelos, Aggelos K.}, booktitle = {Signal Processing}, doi = {10.1016/B978-0-444-89587-5.50033-5}, pages = {1319--1322}, publisher = {Elsevier}, title = {{Displacement Field Estimation in Noisy Image Sequences}}, url = {https://linkinghub.elsevier.com/retrieve/pii/B9780444895875500335}, year = {1992} }
@incollection{Serafim1992a, author = {Efstratiadis, Serafim N. and Katsaggelos, Aggelos K.}, booktitle = {Signal Processing}, doi = {10.1016/B978-0-444-89587-5.50032-3}, pages = {1315--1318}, publisher = {Elsevier}, title = {{Motion Compensated Recursive Filtering of Noisy Displacement Fields}}, url = {https://linkinghub.elsevier.com/retrieve/pii/B9780444895875500323}, year = {1992} }
@incollection{Aggelos1991a, address = {Boston, MA}, author = {Sarrafzadeh, M. and Katsaggelos, Aggelos K and Kumar, S. P. R.}, booktitle = {Parallel Algorithms and Architectures for DSP Applications}, doi = {10.1007/978-1-4615-3996-4_1}, pages = {1--31}, publisher = {Springer US}, title = {{Parallel Architectures For Iterative Image Restoration}}, url = {http://link.springer.com/10.1007/978-1-4615-3996-4_1}, year = {1991} }
@incollection{brady1987computer, abstract = {Actual images of lightning are subdivided into cells. Changes in bolt direction across these cells form a sequence that is treated as a signal. The power spectrum of this signal is obtained and shown to be best characterized by 1/f noise. A Fourier-transform method for generating 1/f noise sequences from a random white-noise source is presented. Lightning branching is modeled by use of context-free L-systems and their graphical interpretation. Synthetic images of electrical discharge are generated using parallel rewriting graph grammars and a 1/f-noise tortuosity model.}, author = {Brady, P. K. and Katsaggelos, A.}, booktitle = {Unknown Host Publication Title}, pages = {127--131}, publisher = {IEEE}, title = {{Computer Graphic Simulation of Lightning Discharge}}, year = {1987} }
@inproceedings{Alharbi2023, abstract = {Smoking is the leading cause of preventable death worldwide. Cigarette smoke includes thousands of chemicals that are harmful and cause tobacco-related diseases. To date, the causality between human exposure to specific compounds and the harmful effects is unknown. A first step in closing the gap in knowledge has been measuring smoking topography, or how the smoker smokes the cigarette (puffs, puff volume, and duration). However, current gold-standard approaches to smoking topography involve expensive, bulky, and obtrusive sensor devices, creating unnatural smoking behavior and preventing their potential for real-time interventions in the wild. Although motion-based wearable sensors and their corresponding machine-learned models have shown promise in unobtrusively tracking smoking gestures, they are notorious for confounding smoking with other similar hand-to-mouth gestures such as eating and drinking. In this paper, we present SmokeMon, a chest-worn thermal-sensing wearable system that can capture spatial, temporal, and thermal information around the wearer and cigarette all day to unobtrusively and passively detect smoking events. We also developed a deep learning - based framework to extract puffs and smoking topography. We evaluate SmokeMon in both controlled and free-living experiments with a total of 19 participants, more than 110 hours of data, and 115 smoking sessions achieving an F1-score of 0.9 for puff detection in the laboratory and 0.8 in the wild. By providing SmokeMon as an open platform, we provide measurement of smoking topography in free-living settings to enable testing of smoking topography in the real world, with potential to facilitate timely smoking cessation interventions.}, author = {Alharbi, Rawan and Shahi, Soroush and Cruz, Stefany and Li, Lingfeng and Sen, Sougata and Pedram, Mahdi and Romano, Christopher and Hester, Josiah and Katsaggelos, Aggelos K. and Alshurafa, Nabil}, booktitle = {Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies}, chapter = {1}, doi = {10.1145/3569460}, isbn = {2474-9567}, issn = {24749567}, keywords = {HAR,Smoking,Thermal,Wearable}, number = {4}, pages = {1--25}, title = {{SmokeMon: Unobtrusive Extraction of Smoking Topography Using Wearable Energy-Efficient Thermal}}, volume = {6}, year = {2023} }
@inproceedings{dravid2022investigating, abstract = {Generative Adversarial Networks (GANs) have shown promise in augmenting datasets and boosting convolutional neural network (CNN) performance on image classification tasks. But they introduce more hyperparameters to tune as well as the need for additional time and computational power to train, supplementary to the CNN. In this work, we examine the potential for Auxiliary-Classifier GANs (AC-GANs) as a'one-stop-shop' architecture for image classification, particularly in low data regimes. Additionally, we explore modifications to the typical AC-GAN framework, changing the generator's latent space sampling scheme and employing a Wasserstein loss with gradient penalty to stabilize the simultaneous training of image synthesis and classification. Through experiments on images of varying resolutions and complexity, we demonstrate that AC-GANs show promise in image classification, achieving competitive performance with standard CNNs. These methods can be employed as an'all-in-one' framework with particular utility in the absence of large amounts of training data.}, archivePrefix = {arXiv}, arxivId = {2201.09120}, author = {Dravid, Amil and Schiffers, Florian and Wu, Yunan and Cossairt, Oliver and Katsaggelos, Aggelos K.}, booktitle = {ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, doi = {10.1109/ICASSP43922.2022.9747286}, eprint = {2201.09120}, isbn = {978-1-6654-0540-9}, issn = {15206149}, keywords = {Convolutional Neural Networks,Data Augmentation,Deep Learning,Generative Adversarial Networks,Image Classification}, month = {may}, organization = {IEEE}, pages = {3318--3322}, publisher = {IEEE}, title = {{Investigating the Potential of Auxiliary-Classifier Gans for Image Classification in Low Data Regimes}}, url = {https://ieeexplore.ieee.org/document/9747286/}, volume = {2022-May}, year = {2022} }
@inproceedings{Soroush2022, abstract = {Automated detection and validation of fine-grained human activities from egocentric vision has gained increased attention in recent years due to the rich information afforded by RGB images. However, it is not easy to discern how much rich information is necessary to detect the activity of interest reliably. Localization of hands and objects in the image has proven helpful to distinguishing between hand-related fine-grained activities. This paper describes the design of a hand-object-based mask obfuscation method (HOBM) and assesses its effect on automated recognition of fine-grained human activities. HOBM masks all pixels other than the hand and object in-hand, improving the protection of personal user information (PUI). We test a deep learning model trained with and without obfuscation using a public egocentric activity dataset with 86 class labels and achieve almost similar classification accuracies (2% decrease with obfuscation). Our findings show that it is possible to protect PUI at smaller image utility costs (loss of accuracy).}, author = {Shahi, Soroush and Alharbi, Rawan and Gao, Yang and Sen, Sougata and Katsaggelos, Aggelos K. and Hester, Josiah and Alshurafa, Nabil}, booktitle = {2022 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops)}, doi = {10.1109/PerComWorkshops53856.2022.9767447}, isbn = {978-1-6654-1647-4}, keywords = {Deep Learning,Human Activity Recognition,Image Obf,Image Obfuscation,Wearable Camera}, month = {mar}, pages = {341--346}, publisher = {IEEE}, title = {{Impacts of Image Obfuscation on Fine-grained Activity Recognition in Egocentric Video}}, url = {https://ieeexplore.ieee.org/document/9767447/}, year = {2022} }
@inproceedings{Lexiaozi, abstract = {Motion correction (MoCo) is an important pre-processing step for pixel-by-pixel myocardial blood flow (MBF) quantification from cardiac perfusion MRI. It may also improve throughput of visual evaluation of perfusion images. One commonly used method for MoCo is optical flow (OF), which requires a moderate level of computational demand. In this study, we sought to perform rapid MoCo of respiratory motion on cardiac perfusion images using deep learning (DL). Our results show that the proposed DL MoCo performs 418-times faster than the reference OF approach without loss in accuracy.}, author = {Fan, Lexiaozi and Yang, Huili and Hsu, Li-Yueh and Katsaggelos, Aggelos K and Allen, Bradley D and Lee, Daniel C and Kim, Daniel}, booktitle = {2022 Joint Annual Meeting ISMRM-ESMRMB & ISMRT 31st Annual Meeting}, title = {{Rapid Motion Correction with Deep Learning for First-Pass Cardiac Perfusion MRI}}, url = {https://archive.ismrm.org/2022/0805.html}, year = {2022} }
@inproceedings{Mehri, abstract = {Assessment of left atrial (LA) fibrosis in atrial fibrillation (AF) patients from 3D LGE MRI have shown promise in evaluating atrial myopathy for selecting patients for catheter ablation and to predict AF recurrence post intervention. Nevertheless, current methods for fibrosis quantification suffer from lack of standardization and reproducibility as they rely on different thresholds for defining fibrosis. Hence, limiting the clinical translation of 3D LA LGE MRI. Here, we propose the first threshold-free technique to quantify LA fibrosis burden using novel stochastic fibrosis signature technique. We demonstrated feasibility and correlations to four of the previously published methods for fibrosis quantification.}, author = {Mehrnia, Mehri and Kholmovski, Eugene and Passman, Rod and Katsaggelos, Aggelos and Nazarian, Saman and Kim, Daniel and Elbaz, Mohammed}, booktitle = {Joint Annual Meeting ISMRM-ESMRMB & ISMRT 31st Annual Meeting}, title = {{Stochastic Fibrosis Signatures from 3D LGE: Novel Threshold-Free Quantification of Left Atrial Fibrosis}}, url = {https://archive.ismrm.org/2022/4436.html}, year = {2022} }
@inproceedings{ballester2022comparison, abstract = {In this investigation, we compare two standard optical characterization methods to analyze the material properties of amorphous silicon thin films obtained from their transmission spectra.}, address = {Washington, D.C.}, author = {Ballester, Manuel and M{\'{a}}rquez, Almudena P. and Banerjee, Srutarshi and Ru{\'{i}}z-P{\'{e}}rez, Juan J. and Cossairt, Oliver and Katsaggelos, Aggelos K. and Willomitzer, Florian and M{\'{a}}rquez, Emilio}, booktitle = {Imaging and Applied Optics Congress 2022 (3D, AOA, COSI, ISA, pcAOP)}, doi = {10.1364/3D.2022.JW5D.4}, isbn = {978-1-957171-09-8}, organization = {Optica Publishing Group}, pages = {JW5D.4}, publisher = {Optica Publishing Group}, title = {{Comparison of Optical Characterization Methods for Transmission Spectroscopy}}, url = {https://opg.optica.org/abstract.cfm?URI=3D-2022-JW5D.4}, year = {2022} }
@inproceedings{Peng2022a, abstract = {The sense of touch is essential for a variety of daily tasks. New advances in event-based tactile sensors and Spiking Neural Networks (SNNs) spur the research in event-driven tactile learning. However, SNN -enabled event-driven tactile learning is still in its infancy due to the limited representative abilities of existing spiking neurons and high spatio-temporal complexity in the data. In this paper, to improve the representative capabilities of existing spiking neurons, we propose a novel neuron model called 'location spiking neuron', which enables us to extract features of event-based data in a novel way. Moreover, based on the classical Time Spike Response Model (TSRM), we develop a specific location spiking neuron model - Location Spike Response Model (LSRM) that serves as a new building block of SNNs11The TSRM is the classical SRM in the literature. We add the character 'T' to highlight its difference with the LSRM.• Furthermore, we propose a hybrid model which combines an SNN with TSRM neurons and an SNN with LSRM neurons to capture the complex spatio-temporal dependencies in the data. Extensive experiments demonstrate the significant improvements of our models over other works on event-driven tactile learning and show the superior energy efficiency of our models and location spiking neurons, which may unlock their potential on neuromorphic hardware.}, author = {Kang, Peng and Banerjee, Srutarshi and Chopp, Henry and Katsaggelos, Aggelos and Cossairt, Oliver}, booktitle = {2022 International Joint Conference on Neural Networks (IJCNN)}, doi = {10.1109/IJCNN55064.2022.9892074}, isbn = {978-1-7281-8671-9}, keywords = {Spiking Neural Networks,event-driven tactile learning,location spiking neurons,spiking neuron models}, month = {jul}, pages = {1--9}, publisher = {IEEE}, title = {{Event - Driven Tactile Learning with Location Spiking Neurons}}, url = {https://ieeexplore.ieee.org/document/9892074/}, volume = {2022-July}, year = {2022} }
@inproceedings{Amit2022, abstract = {Screen time is associated with several health risk behaviors including mindless eating, sedentary behavior, and decreased academic performance. Screen time behavior is traditionally assessed with self-report measures, which are known to be burdensome, inaccurate, and imprecise. Recent methods to automatically detect screen time are geared more towards detecting television screens from wearable cameras that record high-resolution video. Activity-oriented wearable cameras (i.e., cameras oriented towards the wearer with a fisheye lens) have recently been designed and shown to reduce privacy concerns, yet pose a greater challenge in capturing screens due to their orientation and fewer pixels on target. Methods that detect screens from low-power, low-resolution wearable camera video are needed given the increased adoption of such devices in longitudinal studies. We propose a method that leverages deep learning algorithms and lower-resolution images from an activity-oriented camera to detect screen presence from multiple types of screens with high variability of pixel on target (e.g., near and far TV, smartphones, laptops, and tablets). We test our system in a real-world study comprising 10 individuals, 80 hours of data, and 1.2 million low-resolution RGB frames. Our results outperform existing state-of-the-art video screen detection methods yielding an F1-score of 81%. This paper demonstrates the potential for detecting screen-watching behavior in longitudinal studies using activity-oriented cameras, paving the way for a nuanced understanding of screen time's relationship with health risk behaviors.}, author = {Adate, Amit and Shahi, Soroush and Alharbi, Rawan and Sen, Sougata and Gao, Yang and Katsaggelos, Aggelos K. and Alshurafa, Nabil}, booktitle = {2022 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops)}, doi = {10.1109/PerComWorkshops53856.2022.9767433}, isbn = {978-1-6654-1647-4}, keywords = {Egocentric Videos,Fisheye Lens,Object Detection,We,Wearable Camera}, month = {mar}, pages = {403--408}, publisher = {IEEE}, title = {{Detecting Screen Presence with Activity-Oriented RGB Camera in Egocentric Videos}}, url = {https://ieeexplore.ieee.org/document/9767433/}, year = {2022} }
@inproceedings{Amil2022, abstract = {Lack of explainability in artificial intelligence, specifically deep neural networks, remains a bottleneck for implementing models in practice. Popular techniques such as Gradient-weighted Class Activation Mapping (Grad-CAM) provide a coarse map of salient features in an image, which rarely tells the whole story of what a convolutional neural network(CNN) learned. Using COVID-19 chest X-rays, we present a method for interpreting what a CNN has learned by utilizing Generative Adversarial Networks (GANs). Our GAN framework disentangles lung structure from COVID-19 features. Using this GAN, we can visualize the transition of a pair of COVID negative lungs in a chest radiograph to a COVID positive pair by interpolating in the latent space of the GAN, which provides fine-grained visualization of how the CNN responds to varying features within the lungs.}, author = {Dravid, Amil and Katsaggelos, Aggelos K.}, booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence}, doi = {10.1609/aaai.v36i11.21606}, isbn = {1577358767}, issn = {2374-3468}, month = {jun}, number = {11}, pages = {12939--12940}, title = {{Visual Explanations for Convolutional Neural Networks via Latent Traversal of Generative Adversarial Networks (Student Abstract)}}, url = {https://ojs.aaai.org/index.php/AAAI/article/view/21606}, volume = {36}, year = {2022} }
@inproceedings{Yunan2022a, abstract = {Functional MRI offers unique insights for the characterization and presurgical evaluation of people with epilepsy (PWE). In this paper, we develop a graph-based variational auto-encoder (gVAEs) to 1) learn the patterns of resting state functional MRI (rsfMRI) within the brain's subcortical structures in healthy subjects and 2) reconstruct it in PWE to identify findings unique to patients with epilepsy. The gVAE was enriched with Sequential Long Short Term Memory (LSTM) and perceptual loss to learn temporal rsfMRI features and smooth the reconstructed signals. Using a cross-validation approach on healthy controls, our best model yielded an average spatial correlation of 0.791 and an average temporal correlation of 0.793. When applied to PWE, the average and spatial correlation decreased to 0.752 and 0.750 respectively. Our findings pave the path to the development of a whole brain data-driven tool that may be valuable for the characterization of abnormalities within the epileptic brain. This may advance our understanding as to how these abnormalities are related to the location of seizure onset and can inform the care of patients with epilepsy. The code is available at: GitHub}, author = {Wu, Yunan and Besson, Pierre and Azcona, Emanuel A. and {Kathleen Bandt}, S. and Parrish, Todd B. and Katsaggelos, Aggelos K.}, booktitle = {2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI)}, doi = {10.1109/ISBI52829.2022.9761430}, isbn = {978-1-6654-2923-8}, issn = {19458452}, keywords = {LSTM,epilepsy,graph-based Variational auto-encoder,rsfMRI reconstruction}, month = {mar}, pages = {1--5}, publisher = {IEEE}, title = {{Reconstruction of Resting State FMRI Using LSTM Variational Auto-Encoder on Subcortical Surface to Detect Epilepsy}}, url = {https://ieeexplore.ieee.org/document/9761430/}, volume = {2022-March}, year = {2022} }
@inproceedings{dravid2022medxgan, abstract = {Despite the surge of deep learning in the past decade, some users are skeptical to deploy these models in practice due to their black-box nature. Specifically, in the medical space where there are severe potential repercussions, we need to develop methods to gain confidence in the models' decisions. To this end, we propose a novel medical imaging generative adversarial framework, medXGAN (medical eXplanation GAN), to visually explain what a medical classifier focuses on in its binary predictions. By encoding domain knowledge of medical images, we are able to disentangle anatomical structure and pathology, leading to fine-grained visualization through latent interpolation. Furthermore, we optimize the latent space such that interpolation explains how the features contribute to the classifier's output. Our method outperforms baselines such as Gradient-Weighted Class Activation Mapping (Grad-CAM) and Integrated Gradients in localization and explanatory ability. Additionally, a combination of the medXGAN with Integrated Gradients can yield explanations more robust to noise. The project page with code is available at: https://avdravid.github.io/medXGANpage/.}, archivePrefix = {arXiv}, arxivId = {2204.05376}, author = {Dravid, Amil and Schiffers, Florian and Gong, Boqing and Katsaggelos, Aggelos K.}, booktitle = {2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)}, doi = {10.1109/CVPRW56347.2022.00331}, eprint = {2204.05376}, isbn = {978-1-6654-8739-9}, issn = {21607516}, month = {jun}, pages = {2935--2944}, publisher = {IEEE}, title = {{medXGAN: Visual Explanations for Medical Classifiers through a Generative Latent Space}}, url = {https://ieeexplore.ieee.org/document/9857306/}, volume = {2022-June}, year = {2022} }
@inproceedings{banerjee2021lossy, abstract = {Event cameras have provided new opportunities for tackling visual tasks under challenging scenarios over conventional RGB cameras. However, not much focus has been given on event compression algorithms. The main challenge for compressing events is its unique asynchronous form. To address this problem, we propose a novel event compression algorithm based on a quad tree (QT) segmentation map derived from the adjacent intensity images. The QT informs 2D spatial priority within the 3D space-time volume. In the event encoding step, events are first aggregated over time to form polarity-based event histograms. The histograms are then variably sampled via Poisson Disk Sampling prioritized by the QT based segmentation map. Next, differential encoding and run length encoding are employed for encoding the spatial and polarity information of the sampled events, respectively, followed by Huffman encoding to produce the final encoded events. Our algorithm achieves greater than 6× higher compression compared to the state of the art.}, archivePrefix = {arXiv}, arxivId = {2005.00974}, author = {Banerjee, Srutarshi and Wang, Zihao W. and Chopp, Henry H. and Cossairt, Oliver and Katsaggelos, Aggelos K.}, booktitle = {2021 IEEE International Conference on Image Processing (ICIP)}, doi = {10.1109/ICIP42928.2021.9506546}, eprint = {2005.00974}, isbn = {978-1-6654-4115-5}, issn = {15224880}, keywords = {Lossy event compression,Poisson disk sampling,Quad tree segmentation}, month = {sep}, organization = {IEEE}, pages = {2154--2158}, publisher = {IEEE}, title = {{Lossy Event Compression Based On Image-Derived Quad Trees And Poisson Disk Sampling}}, url = {https://ieeexplore.ieee.org/document/9506546/}, volume = {2021-Septe}, year = {2021} }
@inproceedings{Yunhao2021, abstract = {In this paper, we present a low-cost 3D reconstruction method for large-scale specular objects based on deflectometry. Experiments show that our system reaches high accuracy and meets requirements of the target applications in the cultural heritage preservation.}, address = {Washington, D.C.}, author = {Li, Yunhao and Yeh, Chia-Kai and Xu, Bingjie and Schiffers, Florian and Walton, Marc and Tumblin, Jack and Katsaggelos, Aggelos and Willomitzer, Florian and Cossairt, Oliver}, booktitle = {OSA Imaging and Applied Optics Congress 2021 (3D, COSI, DH, ISA, pcAOP)}, doi = {10.1364/COSI.2021.CW4H.3}, isbn = {978-1-943580-89-7}, pages = {CW4H.3}, publisher = {Optica Publishing Group}, title = {{A Low-Cost Solution for 3D Reconstruction of Large-Scale Specular Objects}}, url = {https://opg.optica.org/abstract.cfm?URI=COSI-2021-CW4H.3}, year = {2021} }
@inproceedings{Santiago2021b, abstract = {Despite the success of Recurrent Neural Networks in tasks involving temporal video processing, few works in Video Super-Resolution (VSR) have employed them. In this work we propose a new Gated Recurrent Convolutional Neural Network for VSR adapting some of the key components of a Gated Recurrent Unit. Our model employs a deformable attention module to align the features calculated at the previous time step with the ones in the current step and then uses a gated operation to combine them. This allows our model to effectively reuse previously calculated features and exploit longer temporal relationships between frames without the need of explicit motion compensation. The experimental validation shows that our approach outperforms current VSR learning based models in terms of perceptual quality and temporal consistency.}, author = {Lopez-Tapia, Santiago and Lucas, Alice and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {2020 28th European Signal Processing Conference (EUSIPCO)}, doi = {10.23919/Eusipco47968.2020.9287713}, isbn = {978-9-0827-9705-3}, issn = {22195491}, keywords = {Convolutional Neuronal Networks,Recurrent Neural Networks,Super-resolution,Video}, month = {jan}, pages = {700--704}, publisher = {IEEE}, title = {{Gated Recurrent Networks for Video Super Resolution}}, url = {https://ieeexplore.ieee.org/document/9287713/}, volume = {2021-Janua}, year = {2021} }
@inproceedings{ballester2021fast, abstract = {We present an efficient simulation of the recording and playback phases of a 2D image in a reflection volume hologram. The proposed algorithm uses the free-space Green's function propagation and assumes the Born approximation.}, address = {Washington, D.C.}, author = {Ballester, Manuel and Schiffers, Florian and Wang, Zihao and Hasani, Hamid and Fiske, Lionel and Shedligeri, Prasan and Tumblin, Jack and Willomitzer, Florian and Katsaggelos, Aggelos K. and Cossairt, Oliver}, booktitle = {OSA Imaging and Applied Optics Congress 2021 (3D, COSI, DH, ISA, pcAOP)}, doi = {10.1364/COSI.2021.CTh4A.7}, isbn = {978-1-943580-89-7}, organization = {Optica Publishing Group}, pages = {CTh4A.7}, publisher = {Optica Publishing Group}, title = {{Fast simulations in Computer-Generated Holograms for binary data storage}}, url = {https://opg.optica.org/abstract.cfm?URI=COSI-2021-CTh4A.7}, year = {2021} }
@inproceedings{KyungPyo, author = {Hong, KyungPyo and DiCarlo, Amanda L and Katsaggelos, Aggelos K and Schiffers, Florian A and Rigsby, Cynthia K and Haji-Valizadeh, Hassan and Kim, Daniel}, booktitle = {2021 ISMRM & SMRT Annual Meeting & Exhibition}, title = {{Optimized Density Compensation Function for Filtered Backprojection and Compressed Sensing Reconstruction in Radial k-space MRI}}, url = {https://archive.ismrm.org/2021/2880.html}, year = {2021} }
@inproceedings{Yunan2021, author = {Wu, Yunan and Wang, Xijun and Katsaggelos, Aggelos K.}, booktitle = {17th International Symposium on Medical Information Processing and Analysis}, doi = {10.1117/12.2605824}, editor = {Walker, Adam and Rittner, Let{\'{i}}cia and {Romero Castro}, Eduardo and Lepore, Natasha and Brieva, Jorge and Linguraru, Marius G.}, isbn = {9781510650527}, issn = {1996756X}, month = {dec}, pages = {13}, publisher = {SPIE}, title = {{Motion artifact reduction in abdominal MRIs using generative adversarial networks with perceptual similarity loss}}, url = {https://www.spiedigitallibrary.org/conference-proceedings-of-spie/12088/2605824/Motion-artifact-reduction-in-abdominal-MRIs-using-generative-adversarial-networks/10.1117/12.2605824.full}, volume = {12088}, year = {2021} }
@inproceedings{Yunan2021a, abstract = {Intracranial hemorrhage (ICH) is a life-threatening emergency with high rates of mortality and morbidity. Rapid and accurate detection of ICH is crucial for patients to get a timely treatment. In order to achieve the automatic diagnosis of ICH, most deep learning models rely on huge amounts of slice labels for training. Unfortunately, the manual annotation of CT slices by radiologists is time-consuming and costly. To diagnose ICH, in this work, we propose to use an attention-based multiple instance learning (Att-MIL) approach implemented through the combination of an attention-based convolutional neural network (Att-CNN) and a variational Gaussian process for multiple instance learning (VGPMIL). Only labels at scan-level are necessary for training. Our method (a) trains the model using scan labels and assigns each slice with an attention weight, which can be used to provide slice-level predictions, and (b) uses the VGPMIL model based on low-dimensional features extracted by the Att-CNN to obtain improved predictions both at slice and scan levels. To analyze the performance of the proposed approach, our model has been trained on 1150 scans from an RSNA dataset and evaluated on 490 scans from an external CQ500 dataset. Our method outperforms other methods using the same scan-level training and is able to achieve comparable or even better results than other methods relying on slice-level annotations.}, author = {Wu, Yunan and Schmidt, Arne and Hern{\'{a}}ndez-S{\'{a}}nchez, Enrique and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)}, doi = {10.1007/978-3-030-87196-3_54}, isbn = {9783030871956}, issn = {16113349}, keywords = {Attention-based multiple instance learning,CT hemorrhage detection,Variational Gaussian processes}, pages = {582--591}, title = {{Combining Attention-Based Multiple Instance Learning and Gaussian Processes for CT Hemorrhage Detection}}, url = {https://link.springer.com/10.1007/978-3-030-87196-3_54}, volume = {12902 LNCS}, year = {2021} }
@inproceedings{nau2021skinscan, abstract = {The utilization of computational photography becomes increasingly essential in the medical field. Today, imaging techniques for dermatology range from two-dimensional (2D) color imagery with a mobile device to professional clinical imaging systems measuring additional detailed three-dimensional (3D) data. The latter are commonly expensive and not accessible to a broad audience. In this work, we propose a novel system and software framework that relies only on low-cost (and even mobile) commodity devices present in every household to measure detailed 3D information of the human skin with a 3D-gradient-illumination-based method. We believe that our system has great potential for early-stage diagnosis and monitoring of skin diseases, especially in vastly populated or underdeveloped areas.}, archivePrefix = {arXiv}, arxivId = {2102.00508}, author = {Nau, Merlin A. and Schiffers, Florian and Li, Yunhao and Xu, Bingjie and Maier, Andreas and Tumblin, Jack and Walton, Marc and Katsaggelos, Aggelos K. and Willomitzer, Florian and Cossairt, Oliver}, booktitle = {2021 IEEE International Conference on Image Processing (ICIP)}, doi = {10.1109/ICIP42928.2021.9506335}, eprint = {2102.00508}, isbn = {978-1-6654-4115-5}, issn = {15224880}, keywords = {Dermatologic imaging,Photometric stereo,Three-dimensional imaging,Topographic imaging}, month = {sep}, pages = {2918--2922}, publisher = {IEEE}, title = {{Skinscan: Low-Cost 3D-Scanning for Dermatologic Diagnosis and Documentation}}, url = {https://ieeexplore.ieee.org/document/9506335/}, volume = {2021-Septe}, year = {2021} }
@inproceedings{Yunan, author = {Wu, Yunan and Azcona, Emanuel A and Bandt, S Kathleen and Parrish, Todd B and Besson, Pierre and Katsaggelos, Aggelos K}, booktitle = {Proceedings of 27th Annual Conference of the Organization for Human Brain Mapping (OHBM) 2021}, title = {{Representative Learning of rsfMRI Using LSTM-Variational Autoencoder (VAE) on Subcortical Surface}}, year = {2021} }
@inproceedings{Shedligeri2021, abstract = {X-ray ptychography is one of the versatile techniques for nanometer resolution imaging. The magnitude of the diffraction patterns is recorded on a detector, and the phase of the diffraction patterns is estimated using phase retrieval techniques. Most phase retrieval algorithms make the solution well-posed by relying on the constraints imposed by the overlapping region between neighboring diffraction pattern samples. As the overlap between neighboring diffraction patterns reduces, the problem becomes ill-posed, and the object cannot be recovered. To avoid the ill-posedness, we investigate the effect of regularizing the phase retrieval algorithm with image priors for various overlap ratios between the neighboring diffraction patterns. We show that the object can be faithfully reconstructed at low overlap ratios by regularizing the phase retrieval algorithm with image priors such as Total-Variation prior and Structure Tensor Prior. We also show the effectiveness of our proposed algorithm on real data acquired from an IC chip with a coherent X-ray beam.}, archivePrefix = {arXiv}, arxivId = {2105.09892}, author = {Shedligeri, Prasan and Schiffers, Florian and Barutcu, Semih and Ruiz, Pablo and Katsaggelos, Aggelos K. and Cossairt, Oliver}, booktitle = {2021 IEEE International Conference on Image Processing (ICIP)}, doi = {10.1109/ICIP42928.2021.9506086}, eprint = {2105.09892}, isbn = {978-1-6654-4115-5}, issn = {15224880}, keywords = {Automatic differentiation,Phase-retrieval,Ptychography,Regularization}, month = {sep}, pages = {2968--2972}, publisher = {IEEE}, title = {{Improving Acquisition Speed of X-Ray Ptychography Through Spatial Undersampling and Regularization}}, url = {https://ieeexplore.ieee.org/document/9506086/}, volume = {2021-Septe}, year = {2021} }
@inproceedings{Fernando2020, abstract = {Color deconvolution aims at separating multi-stained images into single stained ones. In digital histopathological images, true stain color vectors vary between images and need to be estimated to obtain stain concentrations and separate stain bands. These band images can be used for image analysis purposes and, once normalized, utilized with other multi-stained images (from different laboratories and obtained using different scanners) for classification purposes. In this paper we propose the use of Super Gaussian (SG) priors for each stain concentration together with the similarity to a given reference matrix for the color vectors. Variational inference and an evidence lower bound are utilized to automatically estimate all the latent variables. The proposed methodology is tested on real images and compared to classical and state-of-the-art methods for histopathological blind image color deconvolution.}, author = {Perez-Bueno, Fernando and Vega, Miguel and Naranjo, Valery and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {2020 28th European Signal Processing Conference (EUSIPCO)}, doi = {10.23919/Eusipco47968.2020.9287497}, isbn = {978-9-0827-9705-3}, issn = {15224880}, keywords = {Blind Color Deconvolution,Histopathological Images,Super Gaussian,Variational Bayes}, month = {jan}, pages = {1254--1258}, publisher = {IEEE}, title = {{Fully Automatic Blind Color Deconvolution of Histological Images Using Super Gaussians}}, url = {https://ieeexplore.ieee.org/document/9191200/ https://ieeexplore.ieee.org/document/9287497/}, volume = {2020-Octob}, year = {2021} }
@inproceedings{Merlin2021, abstract = {Computational photography has become a valuable field of interest for dermatologists. Current telemedical approaches mainly use two-dimensional (2D) color imagery, which cannot always capture sufficient information for the physician. In clinical practice dedicated imaging systems can acquire valuable three-dimensional (3D) data to improve the patients outcome [1], [2]. The major drawback of clinical imaging systems is the price and the availability to the broad audience. We tackle this problem by providing an open-source software framework. The framework uses a photometric stereo-inspired gradient illumination technique, enabling detailed 3D measurements of fine skin structures, like fingerprints. Especially in vastly populated or underdeveloped areas, our system could show benefits for initial diagnosis and documenting the evolution of skin diseases.}, author = {Nau, Merlin A. and Schiffers, Florian and Li, Yunhao and Xu, Bingjie and Maier, Andreas and Tumblin, Jack and Walton, Marc and Katsaggelos, Aggelos K. and Willomitzer, Florian and Cossairt, Oliver}, booktitle = {2021 55th Asilomar Conference on Signals, Systems, and Computers}, doi = {10.1109/IEEECONF53345.2021.9723389}, isbn = {978-1-6654-5828-3}, issn = {10586393}, keywords = {Computational Photography,Dermatologic Imaging,Photometric Stereo,Three-Dimensional Imaging}, month = {oct}, pages = {873--875}, publisher = {IEEE}, title = {{Skinscan: 3D Dermatologic Diagnosis and Documentation with Commodity Devices}}, url = {https://ieeexplore.ieee.org/document/9723389/}, volume = {2021-Octob}, year = {2021} }
@inproceedings{Prasan2021a, abstract = {Ptychography becomes increasingly ill-posed when the overlap between neighboring scan points is reduced, inhibiting the object reconstruction. Here, we discuss and show reconstructions with low-overlap ratios by regularizing with priors such as Total-Variation and Structure-Tensor-Prior.}, address = {Washington, D.C.}, author = {Shedligeri, Prasan and Schiffers, Florian and Barutcu, Semih and Ruiz, Pablo and Katsaggelos, Aggelos K. and Cossairt, Oliver}, booktitle = {OSA Imaging and Applied Optics Congress 2021 (3D, COSI, DH, ISA, pcAOP)}, doi = {10.1364/COSI.2021.CW6B.5}, isbn = {978-1-943580-89-7}, pages = {CW6B.5}, publisher = {Optica Publishing Group}, title = {{Regularization for Undersampled Ptychography}}, url = {https://opg.optica.org/abstract.cfm?URI=COSI-2021-CW6B.5}, year = {2021} }
@inproceedings{Suvai, abstract = {Left atrial (LA) late gadolinium enhancement (LGE) imaging is essential for detecting fibrosis in patients with atrial fibrillation. Unfortunately, slow manual segmentation of LA LGE limits its use in the clinic. The purpose of this study was to develop a fully automated segmentation method for LA LGE images with deep learning. We tested two different U-net architectures that used either 2D or 3D image inputs for training. Our results demonstrate that 3D inputs are superior to 2D, and the 3D U-Net is a promising method to explore further for clinical translation of LA LGE fibrosis quantification.}, author = {Gunasekaran, Suvai and Hwang, Julia and Shen, Daming and Katsaggelos, Aggelos and Elbaz, Mohammed S M and Passman, Rod and Kim, Daniel}, booktitle = {2021 ISMRM & SMRT}, title = {{Automated Segmentation of the Left Atrium from 3D Late Gadolinium Enhancement Imaging using Deep Learning}}, url = {https://archive.ismrm.org/2021/2669.html}, year = {2021} }
@inproceedings{Nantheera, author = {Nantheera, Anantrasirichai and Paul, Hill and Anil, Kokaram and David, Taubman and Anne, Aaron and {Netflix Kiyoharu}, Aizawa and John, Apostolopoulos and {Cisco Axel}, Becker-Lakus and FiveOpenBooks, L L C David R Bull and Tsuhan, Chen and Al., Et and Et al. and Al., Et}, booktitle = {2021 Picture Coding Symposium (PCS)}, doi = {10.1109/PCS50896.2021.9477468}, isbn = {978-1-6654-2545-2}, month = {jun}, pages = {1}, publisher = {IEEE}, title = {{Committees}}, url = {https://ieeexplore.ieee.org/document/9477468/}, year = {2021} }
@inproceedings{banerjee2021event, abstract = {Room Temperature Semiconductor Detectors (RTSD) (e.g., CdZnTe and CdZnTeSe) have been recently proposed in novel space, homeland security and medical applications, which provide sub-millimeter position information of interacting $\gamma$-rays and excellent spectroscopic performance. These detectors have been constructed using a large variety of anode configurations. The virtual Frisch-grid concept with reduced readout channels has been proposed recently. To fully utilize the potential of RTSD, advanced single-polarity charge sensing reconstruction algorithms are needed. Energy and position of interaction reconstruction algorithms rely on physics-based models, with Principal Component Analysis being introduced recently. Proposed deep learning (DL) techniques have the potential to perform event reconstruction with improved position information and better energy resolution than conventional non-DL methods. In this paper, we present a novel DL approach based on Convolutional Neural Networks (CNN) for identifying the energy deposition and position of interaction of the $\gamma$-rays within the RTSD. The network is trained with input-output data pairs. The input data consists of signals at the electrodes corresponding to each incident event and the output data the position and energy spectrum of those events. Our network consists of 5 stages of convolutional layers, each followed by a batch normalization layer and a max-pooling layer. These layers extract features from the input signals fed to the model. This is followed by 2 stages of fully connected layers. Our model outputs the interaction positions and energies within the RTSD. The model is trained using gradient descent steps using the backpropagation method in Tensorflow library of Python. The network has been tested with unseen signals. The Root Mean Squared Error (RMSE) for test cases were around 1% or less for both position and energy interactions.}, author = {Banerjee, Srutarshi and Rodrigues, Miesher and Vija, Alexander Hans and Katsaggelos, Aggelos K.}, booktitle = {2021 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC)}, doi = {10.1109/NSS/MIC44867.2021.9875945}, isbn = {978-1-6654-2113-3}, month = {oct}, organization = {IEEE}, pages = {1--3}, publisher = {IEEE}, title = {{Event Reconstruction in Radiation Detectors using Convolutional Neural Networks}}, url = {https://ieeexplore.ieee.org/document/9875945/}, year = {2021} }
@inproceedings{Peng2021, abstract = {Previous research always solely utilizes Artificial Neural Networks (ANNs) or Spiking Neural Networks (SNNs) for object recognition. However, evidence in neuroscience suggests that the visual processing in human vision is performed hierarchically in the combination of analog and digital processing. To construct a more human vision-like object recognition system, we propose a general hierarchical ANN-SNN model. We evaluate our model and its variants on two popular datasets to show its effectiveness, robustness, efficiency, and generality. Extensive experiments clearly demonstrate the superiority of our proposed models for robust object recognition.}, author = {Kang, Peng and Hu, Hao and Banerjee, Srutarshi and Chopp, Henry and Katsaggelos, Aggelos and Cossairt, Oliver}, booktitle = {2021 IEEE International Conference on Image Processing (ICIP)}, doi = {10.1109/ICIP42928.2021.9506331}, isbn = {978-1-6654-4115-5}, issn = {15224880}, keywords = {Artificial Neural Networks,Human vision,Robust object recogniton,Spiking Neural Networks}, month = {sep}, pages = {709--713}, publisher = {IEEE}, title = {{Human Vision-Like Robust Object Recognition}}, url = {https://ieeexplore.ieee.org/document/9506331/}, volume = {2021-Septe}, year = {2021} }
@inproceedings{fiske2021data, abstract = {In this manuscript, we address the problem of studying layer structure in X-ray Fluorescence (XRF) elemental maps of paintings through the incorporation of reflectance imaging spectral data in the visible or near IR range. We propose a conceptually flexible approach, which involves an initial clustering step for the visible hyperspectral reflectance data (RIS) and the formation of a synthetic surface XRF image. Considering the difference of the full and synthetic surface XRF images, surface and subsurface correlated features are then identified. Results are demonstrated on real and simulated data.}, author = {Fiske, L. D. and Katsaggelos, A. K. and Aalders, M. C. G. and Alfeld, M. and Walton, M. and Cossairt, O.}, booktitle = {2021 IEEE International Conference on Image Processing (ICIP)}, doi = {10.1109/ICIP42928.2021.9506300}, isbn = {978-1-6654-4115-5}, issn = {15224880}, keywords = {Cultural heritage science,Data fusion,Hyperspectral imaging,RIS,XRF}, month = {sep}, organization = {IEEE}, pages = {3458--3462}, publisher = {IEEE}, title = {{A Data Fusion Method For The Delayering Of X-Ray Fluorescence Images Of Painted Works Of Art}}, url = {https://ieeexplore.ieee.org/document/9506300/}, volume = {2021-Septe}, year = {2021} }
@inproceedings{Neil, author = {Neil, Ridler and Rafik, Belarbi and Paul, Xirouchakis and Paolo, Mercorelli and Octavian, Agratini and {Maria Isabel}, Garcia-Planas and Ryzard, S Choras and Leon, Chua and Aggelos, Katsaggelos and Panos, Pardalos and Et al.}, booktitle = {2020 International Conference on Mathematics and Computers in Science and Engineering (MACISE)}, doi = {10.1109/MACISE49704.2020.00006}, isbn = {978-1-7281-6695-7}, month = {jan}, pages = {i--i}, publisher = {IEEE}, title = {{MACISE 2020 Committees}}, url = {https://ieeexplore.ieee.org/document/9195609/}, year = {2020} }
@inproceedings{Fernando2020a, abstract = {Color deconvolution aims at separating multi-stained images into single stained ones. In digital histopathological images, true stain color vectors vary between images and need to be estimated to obtain stain concentrations and separate stain bands. These band images can be used for image analysis purposes and, once normalized, utilized with other multi-stained images (from different laboratories and obtained using different scanners) for classification purposes. In this paper we propose the use of Super Gaussian (SG) priors for each stain concentration together with the similarity to a given reference matrix for the color vectors. Variational inference and an evidence lower bound are utilized to automatically estimate all the latent variables. The proposed methodology is tested on real images and compared to classical and state-of-the-art methods for histopathological blind image color deconvolution.}, author = {Perez-Bueno, Fernando and Vega, Miguel and Naranjo, Valery and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {2020 IEEE International Conference on Image Processing (ICIP)}, doi = {10.1109/ICIP40778.2020.9191200}, isbn = {978-1-7281-6395-6}, issn = {15224880}, keywords = {Blind Color Deconvolution,Histopathological Images,Super Gaussian,Variational Bayes}, month = {oct}, pages = {3010--3014}, publisher = {IEEE}, title = {{Super Gaussian Priors for Blind Color Deconvolution of Histological Images}}, url = {https://ieeexplore.ieee.org/document/9191200/}, volume = {2020-Octob}, year = {2020} }
@inproceedings{GrigoriosAris2020, abstract = {Intravascular Optical Coherence Tomography (IVOCT) is a modality which gives in vivo insight of coronaries' artery morphology. Thus, it helps diagnosis and prevention of atherosclerosis. About 100–300 cross-sectional OCT images are obtained for each artery. Therefore, it is important to facilitate and objectify the process of detecting regions of interest, which otherwise demand a lot of time and effort from medical experts. We propose a processing pipeline to automatically detect parts of the arterial wall which are not normal and possibly consist of plaque. The first step of the processing is transforming OCT images to polar coordinates and to detect the arterial wall. After binarization of the image and removal of the catheter, the arterial wall is detected in each axial line from the first white pixel to a depth of 80 pixels which is equal to 1.5 mm. Then, the arterial wall is split to orthogonal patches which undergo OCT-specific transformations and are labelled as plaque (4 distinct kinds: fibrous, calcified, lipid and mixed) or normal tissue. OCT-specific transformations include enhancing the more reflective parts of the image and rendering patches independent of the arterial wall curvature. The patches are input to AlexNet which is fine-tuned to learn to classify them. Fine-tuning is performed by retraining an already trained AlexNet with a learning rate which is 20 times larger for the last 3 fully-connected layers than for the initial 5 convolutional layers. 114 cross-sectional images were randomly selected to fine-tune AlexNet while 6 were selected to validate the results. Training accuracy was 100% while validation accuracy was 86%. Drop in validation accuracy rate is attributed mainly to false negatives which concern only calcified plaque. Thus, there is potential in this method especially in detecting the 3 other classes of plaque.}, author = {Cheimariotis, Grigorios-Aris and Riga, Maria and Toutouzas, Konstantinos and Tousoulis, Dimitris and Katsaggelos, Aggelos and Maglaveras, Nikolaos}, booktitle = {IFMBE Proceedings}, doi = {10.1007/978-3-030-30636-6_53}, keywords = {Convolutional Neural Networks,Deep learning,Intrav}, pages = {389--395}, title = {{Deep Learning Method to Detect Plaques in IVOCT Images}}, url = {http://link.springer.com/10.1007/978-3-030-30636-6_53}, volume = {74}, year = {2020} }
@inproceedings{azcona2020interpretation, abstract = {We propose a mesh-based technique to aid in the classification of Alzheimer's disease dementia (ADD) using mesh representations of the cortex and subcortical structures. Deep learning methods for classification tasks that utilize structural neuroimaging often require extensive learning parameters to optimize. Frequently, these approaches for automated medical diagnosis also lack visual interpretability for areas in the brain involved in making a diagnosis. This work: (a) analyzes brain shape using surface information of the cortex and subcortical structures, (b) proposes a residual learning framework for state-of-the-art graph convolutional networks which offer a significant reduction in learnable parameters, and (c) offers visual interpretability of the network via class-specific gradient information that localizes important regions of interest in our inputs. With our proposed method leveraging the use of cortical and subcortical surface information, we outperform other machine learning methods with a 96.35% testing accuracy for the ADD vs. healthy control problem. We confirm the validity of our model by observing its performance in a 25-trial Monte Carlo cross-validation. The generated visualization maps in our study show correspondences with current knowledge regarding the structural localization of pathological changes in the brain associated to dementia of the Alzheimer's type.}, archivePrefix = {arXiv}, arxivId = {2008.06151}, author = {Azcona, Emanuel A. and Besson, Pierre and Wu, Yunan and Punjabi, Arjun and Martersteck, Adam and Dravid, Amil and Parrish, Todd B. and Bandt, S. Kathleen and Katsaggelos, Aggelos K.}, booktitle = {Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)}, doi = {10.1007/978-3-030-61056-2_8}, eprint = {2008.06151}, isbn = {9783030610555}, issn = {16113349}, keywords = {Alzheimer's disease classification,Graph convolutional networks,Neural network interpretability,Triangulated meshes}, organization = {Springer International Publishing Cham}, pages = {95--107}, title = {{Interpretation of Brain Morphology in Association to Alzheimer's Disease Dementia Classification Using Graph Convolutional Networks on Triangulated Meshes}}, url = {https://link.springer.com/10.1007/978-3-030-61056-2_8}, volume = {12474 LNCS}, year = {2020} }
@inproceedings{barutcu2020simultaneous, abstract = {The acquisition model of a 3Dx-ray imaging system can be understood as the combination of two known techniques: tomography and ptychography. First, x-rays go through a 3D object producing a set of 2D tomographic projections at different angles. Then, a detector captures the magnitude of a diffraction pattern produced by the interaction of these projections with a finite-sized coherent beam spot (also called probe). In 2D ptychography, in order to solve this phase retrieval problem, the observations have to be captured with a large overlap between them. However, this constraint can be relaxed in 3Dx-ray imaging, due to the fact that most of the required redundant information is acquired thanks to the combination of tomography and ptychography. In this work, we address the so-called ptycho-tomography problem and introduce a 3D reconstruction method that uses the gradient descent algorithm. In the experimental section, the proposed method is evaluated and compared against state-of-art-methods.}, author = {Barutcu, Semih and Ruiz, Pablo and Schiffers, Florian and Aslan, Selin and Gursoy, Doga and Cossairt, Oliver and Katsaggelos, Aggelos K.}, booktitle = {2020 IEEE International Conference on Image Processing (ICIP)}, doi = {10.1109/ICIP40778.2020.9190775}, isbn = {978-1-7281-6395-6}, issn = {15224880}, keywords = {Phase retrieval,Ptychography,Reconstruction Algorithms,Three-Dimensional Image Processing,Tomography}, month = {oct}, organization = {IEEE}, pages = {96--100}, publisher = {IEEE}, title = {{SIMULTANEOUS 3D X-RAY PTYCHO-TOMOGRAPHY WITH GRADIENT DESCENT}}, url = {https://ieeexplore.ieee.org/document/9190775/}, volume = {2020-Octob}, year = {2020} }
@inproceedings{Zihaoa, abstract = {We present a novel computational imaging system with high resolution and low noise. Our system consists of a traditional video camera which captures high-resolution intensity images, and an event camera which encodes high-speed motion as a stream of asynchronous binary events. To process the hybrid input, we propose a unifying framework that first bridges the two sensing modalities via a noise-robust motion compensation model, and then performs joint image filtering. The filtered output represents the temporal gradient of the captured space-time volume, which can be viewed as motion-compensated event frames with high resolution and low noise. Therefore, the output can be widely applied to many existing event-based algorithms that are highly dependent on spatial resolution and noise robustness. In experimental results performed on both publicly available datasets as well as our new RGB-DAVIS dataset, we show systematic performance improvement in applications such as high frame-rate video synthesis, feature/corner detection and tracking, as well as high dynamic range image reconstruction.}, author = {Wang, Zihao W. and Duan, Peiqi and Cossairt, Oliver and Katsaggelos, Aggelos and Huang, Tiejun and Shi, Boxin}, booktitle = {2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, doi = {10.1109/CVPR42600.2020.00168}, isbn = {978-1-7281-7168-5}, issn = {10636919}, month = {jun}, pages = {1606--1616}, publisher = {IEEE}, title = {{Joint Filtering of Intensity Images and Neuromorphic Events for High-Resolution Noise-Robust Imaging}}, url = {https://ieeexplore.ieee.org/document/9156457/}, year = {2020} }
@inproceedings{Xijun2019a, abstract = {Deep Learning techniques and more specifically Generative Adversarial Networks (GANs) have recently been used for solving the video super-resolution (VSR) problem. In some of the published works, feature-based perceptual losses have also been used, resulting in promising results. While there has been work in the literature incorporating temporal information into the loss function, studies which make use of the spatial activity to improve GAN models are still lacking. Towards this end, this paper aims to train a GAN guided by a spatially adaptive loss function. Experimental results demonstrate that the learned model achieves improved results with sharper images, fewer artifacts and less noise.}, author = {Wang, Xijun and Lucas, Alice and Lopez-Tapia, Santiago and Wu, Xinyi and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, doi = {10.1109/ICASSP.2019.8682742}, isbn = {978-1-4799-8131-1}, issn = {15206149}, keywords = {Generative Adversarial Networks,Perceptual Loss,Spatial Adaptivity,Video Super-Resolution}, month = {may}, pages = {1697--1701}, publisher = {IEEE}, title = {{Spatially Adaptive Losses for Video Super-resolution with GANs}}, url = {https://ieeexplore.ieee.org/document/8682742/}, volume = {2019-May}, year = {2019} }
@inproceedings{Xinyi2019, abstract = {Semantic information is widely used in the deep learning literature to improve the performance of visual media processing. In this work, we propose a semantic prior based Generative Adversarial Network (GAN) model for video super-resolution. The model fully utilizes various texture styles from different semantic categories of video-frame patches, contributing to more accurate and efficient learning for the generator. Based on the GAN framework, we introduce the semantic prior by making use of the spatial feature transform during the learning process of the generator. The patch-wise semantic prior is extracted on the whole video frame by a semantic segmentation network. A hybrid loss function is designed to guide the learning performance. Experimental results show that our proposed model is advantageous in sharpening video frames, reducing noise and artifacts, and recovering realistic textures.}, author = {Wu, Xinyi and Lucas, Alice and Lopez-Tapia, Santiago and Wang, Xijun and Kim, Yul Hee and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {2019 27th European Signal Processing Conference (EUSIPCO)}, doi = {10.23919/EUSIPCO.2019.8902987}, isbn = {978-9-0827-9703-9}, issn = {22195491}, keywords = {Generative Adversarial Networks,Hybrid loss function,Semantic Segmentation,Spatial Feature Transform,Video Super-Resolution}, month = {sep}, pages = {1--5}, publisher = {IEEE}, title = {{Semantic Prior Based Generative Adversarial Network for Video Super-Resolution}}, url = {https://ieeexplore.ieee.org/document/8902987/}, volume = {2019-Septe}, year = {2019} }
@inproceedings{Alice2019d, abstract = {While Deep Neural Networks trained for solving inverse imaging problems (such as super-resolution, denoising, or inpainting tasks) regularly achieve new state-of-the-art restoration performance, this increase in performance is often accompanied with undesired artifacts generated in their solution. These artifacts are usually specific to the type of neural network architecture, training, or test input image used for the inverse imaging problem at hand. In this paper, we propose a fast, efficient post-processing method for reducing these artifacts. Given a test input image and its known image formation model, we fine-tune the parameters of the trained network and iteratively update them using a data consistency loss. We show that in addition to being efficient and applicable to large variety of problems, our post-processing through fine-tuning approach enhances the solution originally provided by the neural network by maintaining its restoration quality while reducing the observed artifacts, as measured qualitatively and quantitatively.}, author = {Lucas, Alice and Lopez-Tapia, Santiago and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {2019 IEEE International Conference on Image Processing (ICIP)}, doi = {10.1109/ICIP.2019.8803715}, isbn = {978-1-5386-6249-6}, issn = {15224880}, keywords = {Artifacts,Data Consistency,Deep Neural Networks,Fine-tuning,Image and Video Processing,Inversion}, month = {sep}, pages = {3591--3595}, publisher = {IEEE}, title = {{Efficient Fine-Tuning of Neural Networks for Artifact Removal in Deep Learning for Inverse Imaging Problems}}, url = {https://ieeexplore.ieee.org/document/8803715/}, volume = {2019-Septe}, year = {2019} }
@inproceedings{Neda2019, abstract = {In this paper, the problem of automatic nonlinear unmixing of hyperspectral reflectance data using works of art as test cases is described. We use a deep neural network to decompose a given spectrum quantitatively to the abundance values of pure pigments. We show that adding another step to identify the constituent pigments of a given spectrum leads to more accurate unmixing results. Towards this, we use another deep neural network to identify pigments first and integrate this information to different layers of the network used for pigment unmixing. As a test set, the hyperspectral images of a set of mock-up paintings consisting of a broad palette of pigment mixtures, and pure pigment exemplars, were measured. The results of the algorithm on the mock-up test set are reported and analyzed.}, author = {Rohani, Neda and Pouyet, Emeline and Walton, Marc and Cossairt, Oliver and Katsaggelos, Aggelos K.}, booktitle = {ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, doi = {10.1109/ICASSP.2019.8682838}, isbn = {978-1-4799-8131-1}, issn = {15206149}, keywords = {Hyperspectral imaging,deep neural network,fusion,nonlinear unmixing,pigment identification}, month = {may}, pages = {3217--3221}, publisher = {IEEE}, title = {{Pigment Unmixing of Hyperspectral Images of Paintings Using Deep Neural Networks}}, url = {https://ieeexplore.ieee.org/document/8682838/}, volume = {2019-May}, year = {2019} }
@inproceedings{Nima2019, abstract = {We argue that learning a hierarchy of features in a hierarchical dataset requires lower layers to approach convergence faster than layers above them. We show that, if this assumption holds, we can analytically approximate the outcome of stochastic gradient descent (SGD) for each layer. We find that the weights should converge to a class-based PCA, with some weights in every layer dedicated to principal components of each label class. The class-based PCA allows us to train layers directly, without SGD, often leading to a dramatic decrease in training complexity. We demonstrate the effectiveness of this by using our results to replace one and two convolutional layers in networks trained on MNIST, CIFAR10 and CIFAR100 datasets, showing that our method achieves performance superior or comparable to similar architectures trained using SGD.}, author = {Dehmamy, Nima and Rohani, Neda and Katsaggelos, Aggelos K.}, booktitle = {ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, doi = {10.1109/ICASSP.2019.8682781}, isbn = {978-1-4799-8131-1}, issn = {15206149}, month = {may}, pages = {3232--3236}, publisher = {IEEE}, title = {{Direct Estimation of Weights and Efficient Training of Deep Neural Networks without SGD}}, url = {https://ieeexplore.ieee.org/document/8682781/}, volume = {2019-May}, year = {2019} }
@inproceedings{Florian2019, abstract = {Optical imagers experience a fundamental trade-off between spatial resolution and depth-of-field (DoF). This work discusses the possibility of speckle projection to achieve super-resolution within a large DoF. Preliminary results for planar objects are presented.}, address = {Washington, D.C.}, author = {Schiffers, Florian and Willomitzer, Florian and Ruiz, Pablo and Katsaggelos, Aggelos K. and Cossairt, Oliver}, booktitle = {Imaging and Applied Optics 2019 (COSI, IS, MATH, pcAOP)}, doi = {10.1364/COSI.2019.CTh4A.6}, isbn = {978-1-943580-63-7}, pages = {CTh4A.6}, publisher = {OSA}, title = {{Speckle based Extended Depth-of-Field for Macroscopic Imaging: First results}}, url = {https://opg.optica.org/abstract.cfm?URI=COSI-2019-CTh4A.6}, volume = {Part F170-}, year = {2019} }
@inproceedings{Xijun2019, abstract = {Generative Adversarial Networks (GANs) have been used for solving the video super-resolution problem. So far, video super-resolution GAN-based methods use the traditional GAN framework which consists of a single generator and a single discriminator that are trained against each other. In this work we propose a new framework which incorporates two collaborative discriminators whose aim is to jointly improve the quality of the reconstructed video sequence. While one discriminator concentrates on general properties of the images, the second one specializes on obtaining realistically reconstructed features, such as, edges. Experiments results demonstrate that the learned model outperforms current state of the art models and obtains super-resolved frames, with fine details, sharp edges, and fewer artifacts.}, author = {Wang, Xijun and Lucas, Alice and Lopez-Tapia, Santiago and Wu, Xinyi and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {2019 27th European Signal Processing Conference (EUSIPCO)}, doi = {10.23919/EUSIPCO.2019.8903072}, isbn = {978-9-0827-9703-9}, issn = {22195491}, keywords = {Generative Adversarial Networks,Spatially Adaptive,The Composite Discriminator,Video Super-Resolution}, month = {sep}, pages = {1--5}, publisher = {IEEE}, title = {{A Composite Discriminator for Generative Adversarial Network based Video Super-Resolution}}, url = {https://ieeexplore.ieee.org/document/8903072/}, volume = {2019-Septe}, year = {2019} }
@inproceedings{Santiago2019a, abstract = {While high and ultra high definition displays are becoming popular, most of the available content has been acquired at much lower resolutions. In this work we propose to pseudo-invert with regularization the image formation model using GANs and perceptual losses. Our model, which does not require the use of motion compensation, utilizes explicitly the low resolution image formation model and additionally introduces two feature losses which are used to obtain perceptually improved high resolution images. The experimental validation shows that our approach outperforms current video super resolution learning based models.}, author = {Lopez-Tapia, Santiago and Lucas, Alice and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {2019 IEEE International Conference on Image Processing (ICIP)}, doi = {10.1109/ICIP.2019.8803709}, isbn = {978-1-5386-6249-6}, issn = {15224880}, keywords = {Convolutional Neuronal Networks,Generative Adversarial Networks,Perceptual Loss Functions,Super-resolution,Video}, month = {sep}, pages = {2886--2890}, publisher = {IEEE}, title = {{Gan-Based Video Super-Resolution With Direct Regularized Inversion of the Low-Resolution Formation Model}}, url = {https://ieeexplore.ieee.org/document/8803709/}, volume = {2019-Septe}, year = {2019} }
@inproceedings{Zihao, abstract = {Temporal Video Frame Synthesis (TVFS) aims at synthesizing novel frames at timestamps different from existing frames, which has wide applications in video codec, editing and analysis. In this paper, we propose a high frame-rate TVFS framework which takes hybrid input data from a low-speed frame-based sensor and a high-speed event-based sensor. Compared to frame-based sensors, event-based sensors report brightness changes at very high speed, which may well provide useful spatio-temoral information for high frame-rate TVFS. Therefore, we first introduce a differentiable fusion model to approximate the dual-modal physical sensing process, unifying a variety of TVFS scenarios, e.g., interpolation, prediction and motion deblur. Our differentiable model enables iterative optimization of the latent video tensor via autodifferentiation, which propagates the gradients of a loss function defined on the measured data. Our differentiable model-based reconstruction does not involve training, yet is parallelizable and can be implemented on machine learning platforms (such as TensorFlow). Second, we develop a deep learning strategy to enhance the results from the first step, which we refer as a residual 'denoising' process. Our trained 'denoiser' is beyond Gaussian denoising and shows properties such as contrast enhancement and motion awareness. We show that our framework is capable of handling challenging scenes including both fast motion and strong occlusions.}, archivePrefix = {arXiv}, arxivId = {1902.09680}, author = {Wang, Zihao W. and Jiang, Weixin and He, Kuan and Shi, Boxin and Katsaggelos, Aggelos and Cossairt, Oliver}, booktitle = {2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)}, doi = {10.1109/ICCVW.2019.00532}, eprint = {1902.09680}, isbn = {978-1-7281-5023-9}, keywords = {Event based vision,Motion deblur,Multi modal sensor fusion,Video frame interpolation,Video frame prediction}, month = {oct}, pages = {4320--4329}, publisher = {IEEE}, title = {{Event-Driven Video Frame Synthesis}}, url = {https://ieeexplore.ieee.org/document/9022389/}, year = {2019} }
@inproceedings{Miguel2019, abstract = {In digital brightfield microscopy, tissues are usually stained with two or more dyes. Color deconvolution aims at separating multi-stained images into single stained images. We formulate the blind color deconvolution problem within the Bayesian framework. Our model takes into account the similarity to a given reference color-vector matrix and spatial relations among the concentration pixels by a total variation prior. It utilizes variational inference and an evidence lower bound to estimate all the latent variables. The proposed algorithm is tested on real images and compared with classical and state-of-the-art color deconvolution algorithms.}, author = {Vega, Miguel and Mateos, Javier and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {2019 27th European Signal Processing Conference (EUSIPCO)}, doi = {10.23919/EUSIPCO.2019.8902589}, isbn = {978-9-0827-9703-9}, issn = {22195491}, keywords = {Blind color deconvolution,Histopathological images,Total variation,Variational Bayes}, month = {sep}, pages = {1--5}, publisher = {IEEE}, title = {{Variational Bayes Color Deconvolution with a Total Variation Prior}}, url = {https://ieeexplore.ieee.org/document/8902589/}, volume = {2019-Septe}, year = {2019} }
@inproceedings{Seunghwan2019, abstract = {In this paper, we present a novel approach based on deep neural network for solving the limited angle tomography problem. The limited angle views in tomography cause severe artifacts in the tomographic reconstruction. We use deep convolutional generative adversarial networks (DCGAN) to fill in the missing information in the sino-gram domain. By using the continuity loss and the two-ends method, the image completion in the sinogram domain is done effectively, resulting in high quality reconstructions with fewer artifacts. The sinogram completion method can be applied to different problems such as ring artifact removal and truncated tomography problems.}, author = {Yoo, Seunghwan and Yang, Xiaogang and Wolfman, Mark and Gursoy, Doga and Katsaggelos, Aggelos K.}, booktitle = {2019 IEEE International Conference on Image Processing (ICIP)}, doi = {10.1109/ICIP.2019.8804416}, isbn = {978-1-5386-6249-6}, issn = {15224880}, keywords = {Limited angle tomography,deep convolutional generative adversarial networks,sinogram image completion}, month = {sep}, pages = {1252--1256}, publisher = {IEEE}, title = {{Sinogram Image Completion for Limited Angle Tomography With Generative Adversarial Networks}}, url = {https://ieeexplore.ieee.org/document/8804416/}, volume = {2019-Septe}, year = {2019} }
@inproceedings{Bingjie2019, abstract = {Las mediciones precisas de la forma geom{\'{e}}trica y la estructura interna de los artefactos culturales son de gran importancia para el an{\'{a}}lisis y la comprensi{\'{o}}n de obras de arte como las pinturas. A menudo, sus capas complejas, sus materiales delicados, su alto valor y su exclusividad excluyen todas las mediciones basadas en muestras, excepto las m{\'{a}}s escasas (microtom{\'{i}}a o incrustaci{\'{o}}n de peque{\~{n}}as astillas de pintura). En la {\'{u}}ltima d{\'{e}}cada, la tomograf{\'{i}}a de coherencia {\'{o}}ptica (OCT) ha permitido mediciones densas puntuales de superficies en capas para crear im{\'{a}}genes en 3D con resoluciones axiales a escalas de micras. Los sistemas OCT comerciales a longitudes de onda biol{\'{o}}gicamente {\'{u}}tiles (900 nm a 1.3 µm) pueden revelar algunas capas de pintura, una fuerte dispersi{\'{o}}n y absorci{\'{o}}n en estas longitudes de onda limita severamente la profundidad de penetraci{\'{o}}n. Si bien los m{\'{e}}todos de dominio de Fourier aumentan la velocidad de medici{\'{o}}n y eliminan las partes m{\'{o}}viles, tambi{\'{e}}n reducen las relaciones se{\~{n}}al / ruido y aumentan los costos del equipo. En este art{\'{i}}culo, presentamos un sistema OCT (TD-OCT) de dominio de tiempo mejorado y de menor costo para obtener im{\'{a}}genes en 3D m{\'{a}}s profundas y de alta resoluci{\'{o}}n de capas de pintura. Montado enteramente a partir de piezas comercializadas recientemente disponibles, su acoplador de fibra {\'{o}}ptica fusionado 2x2 forma un interfer{\'{o}}metro sin un divisor de haz delicado y alineado manualmente, su fuente de l{\'{a}}ser s{\'{u}}per continuo Q de banda ancha de bajo costo suministra 20 KHz 0.4- Pulsos coherentes de 2.4 µm que penetran profundamente en la matriz de la muestra, y su {\'{u}}nico fotodetector amplificado InGaAs de bajo costo reemplaza la c{\'{a}}mara espectrosc{\'{o}}pica sensible requerida por los sistemas OCT de dominio de Fourier (FD-OCT). Nuestras opciones de fibra y filtro operan a longitudes de onda de 2.0 ± 0.2 µm, ya que luego pueden ayudarnos a caracterizar las caracter{\'{i}}sticas de dispersi{\'{o}}n y absorci{\'{o}}n, y producir una resoluci{\'{o}}n axial de aproximadamente 4.85 µm, sorprendentemente cerca del m{\'{a}}ximo te{\'{o}}rico de 4.41 µm. Demostramos que, a pesar de las partes m{\'{o}}viles que hacen que las mediciones TD-OCT sean m{\'{a}}s lentas, reemplazar la c{\'{a}}mara espectrosc{\'{o}}pica requerida por FD-OCT con un detector de un solo p{\'{i}}xel ofrece grandes ventajas. Este detector mide la potencia de interferencia en todas las longitudes de onda simult{\'{a}}neamente, pero a una sola profundidad, lo que permite que el sistema alcance sus l{\'{i}}mites de resoluci{\'{o}}n axial simplemente usando m{\'{a}}s tiempo para adquirir m{\'{a}}s muestras por A-scan. Caracterizamos el rendimiento del sistema utilizando muestras de materiales que coinciden con obras de arte reales. Nuestro sistema proporciona una forma econ{\'{o}}mica y pr{\'{a}}ctica de mejorar el rendimiento de las im{\'{a}}genes en 3D para aplicaciones de patrimonio cultural en t{\'{e}}rminos de penetraci{\'{o}}n, resoluci{\'{o}}n y rango din{\'{a}}mico.}, author = {Xu, Bingjie and He, Kuan and Hao, Pengxiao and Gao, Jian and Willomitzer, Florian and Katsaggelos, Aggelos K. and Tumblin, John E. and Cossairt, Oliver and Walton, Marc S.}, booktitle = {Optics for Arts, Architecture, and Archaeology VII}, doi = {10.1117/12.2525649}, editor = {Targowski, Piotr and Groves, Roger and Liang, Haida}, isbn = {9781510627956}, issn = {1996756X}, month = {jul}, pages = {21}, publisher = {SPIE}, title = {{Time-domain optical coherence tomography can measure artworks with high penetration and high resolution}}, url = {https://www.spiedigitallibrary.org/conference-proceedings-of-spie/11058/2525649/Time-domain-optical-coherence-tomography-can-measure-artworks-with-high/10.1117/12.2525649.full}, volume = {11058}, year = {2019} }
@inproceedings{Fengqiang2019, author = {Li, Fengqiang and Ruiz, Pablo and Cossairt, Oliver and Katsaggelos, Aggelos K}, booktitle = {ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, doi = {10.1109/ICASSP.2019.8683042}, isbn = {978-1-4799-8131-1}, month = {may}, pages = {2327--2331}, publisher = {IEEE}, title = {{Multi-frame Super-resolution for Time-of-flight Imaging}}, url = {https://ieeexplore.ieee.org/document/8683042/}, year = {2019} }
@inproceedings{Lionel2019, author = {Fiske, Lionel and Cossairt, Oliver and Katsaggelos, Aggelos K. and Walton, Marc S.}, booktitle = {Optics for Arts, Architecture, and Archaeology VII}, doi = {10.1117/12.2525382}, editor = {Targowski, Piotr and Groves, Roger and Liang, Haida}, isbn = {9781510627956}, month = {jul}, pages = {13}, publisher = {SPIE}, title = {{Investigation of reflectance-based pigment classification in layered media (Conference Presentation)}}, url = {https://www.spiedigitallibrary.org/conference-proceedings-of-spie/11058/2525382/Investigation-of-reflectance-based-pigment-classification-in-layered-media-Conference/10.1117/12.2525382.full}, volume = {11058}, year = {2019} }
@inproceedings{cheimariotis2019automatic, abstract = {Intravascular optical coherence tomography (IVOCT) is a light-based imaging modality of great interest because it can contribute in diagnosing and preventing atherosclerosis due to its ability to provide in vivo insight of coronary arteries' morphology. The substantial number of slices which are obtained per artery, makes it laborious for medical experts to classify image regions of interest. We propose a framework based on Convolutional Neural Networks (CNN) for classification of regions of intravascular OCT images into 4 categories: fibrous tissue, mixed plaque, lipid plaque and calcified plaque. The framework consists of 2 main parts. In the first part, square patches (8 × 8 pixels) of OCT images are classified as fibrous tissue or plaque using a CNN which was designed for texture classification. In the second part, larger regions consisting of adjacent patches which are classified as plaque in the first part, are classified in 3 categories: lipid, calcium, mixed. Region classification is implemented by an AlexNet version re-trained on images artificially constructed to depict only the core of the plaque region which is considered as its blueprint. Various simple steps like thresholding and morphological operations are used through the framework, mainly to exclude background from analysis and to merge patches into regions. The first results are promising since the classification accuracy of the two networks is high (95% and 89% respectively).}, author = {Cheimariotis, G. A. and Riga, M. and Toutouzas, K. and Tousoulis, D. and Katsaggelos, A. and Maglaveras, N.}, booktitle = {IFMBE Proceedings}, doi = {10.1007/978-981-10-9035-6_47}, issn = {16800737}, keywords = {Convolutional neural networks,Deep learning,Intravascular OCT,Segmentation}, number = {1}, organization = {Springer Singapore}, pages = {261--265}, title = {{Automatic Characterization of Plaques and Tissue in IVOCT Images Using a Multi-step Convolutional Neural Network Framework}}, url = {https://link.springer.com/10.1007/978-981-10-9035-6_47}, volume = {68}, year = {2019} }
@inproceedings{Yan-Ran2019, abstract = {Chronic stroke lesion segmentation on magnetic resonance imaging scans plays a critical role in helping physicians to determine stroke patient prognosis. We propose a convolutional neural network (CNN) segmentation network - a 3D Cross-hemisphere Neighborhood Difference ConvNet -which utilizes brain symmetry. The main novelty of this network lies on a 3D cross-hemisphere neighborhood difference layer which introduces robustness to position and scale in brain symmetry. Such robustness is important in helping the CNN distinguish between minute hemispheric differences and the asymmetry caused by a lesion. We compared our model with the state-of-the-art method using a chronic stroke lesion segmentation database. Our results demonstrate the effectiveness of the proposed model and the benefit of a CNN that combines the physiologically based information, that is, the brain symmetry property.}, author = {Wang, Yan-Ran and Wang, Hengkang and Chen, Sophia and Katsaggelos, Aggelos K. and Martersteck, Adam and Higgins, James and Hill, Virginia B. and Parrish, Todd B.}, booktitle = {2019 IEEE International Conference on Image Processing (ICIP)}, doi = {10.1109/ICIP.2019.8803092}, isbn = {978-1-5386-6249-6}, issn = {15224880}, keywords = {brain symmetry,convolutional neural networks,stroke lesion segmentation}, month = {sep}, pages = {1545--1549}, publisher = {IEEE}, title = {{A 3D Cross-Hemisphere Neighborhood Difference Convnet for Chronic Stroke Lesion Segmentation}}, url = {https://ieeexplore.ieee.org/document/8803092/}, volume = {2019-Septe}, year = {2019} }
@inproceedings{Petros2018, abstract = {In this paper we address the Phase Retrieval problem, which aims to recover the phase of the Fourier transform of a signal when only magnitude measurements are available. Following recent developments in Phase Retrieval, the problem can be transformed into a convex semidefinite programming optimization problem, which can be solved using Matrix Completion techniques. In this paper the acquisition process is modeled using a likelihood function, which splits the original problem into two convex optimization problems, and alternates between the solution of each of them. To relate both convex problems we introduce a heuristic, which results in fast convergence of the proposed method.}, author = {Nyfantis, Petros and Ruiz, Pablo and Katsaggelos, Aggelos K.}, booktitle = {2018 25th IEEE International Conference on Image Processing (ICIP)}, doi = {10.1109/ICIP.2018.8451272}, isbn = {978-1-4799-7061-2}, issn = {15224880}, keywords = {Alternating minimization,Lifting,Nonconvex quadratic programming,Phase,Retrieval}, month = {oct}, pages = {3983--3987}, publisher = {IEEE}, title = {{Probabilistic Matrix Completion for Image Phase Retrieval}}, url = {https://ieeexplore.ieee.org/document/8451272/}, year = {2018} }
@inproceedings{Adrian2018, abstract = {Exudates are the most noticeable sign in the first stage of diabetic retinopathy. This disease causes about five percent of world blindness. Making use of retinal fundus images, exudates can be detected, which helps the early diagnosis of the pathology. In this work, a novel method for automatic hard exudate detection is presented. After an exhaustive pre-processing step, Local Binary Patterns Variance (LBPV) histograms are used to locally extract texture information. We then use Gaussian Processes to distinguish between healthy and pathological retinal patches. The proposed methodology is validated using the E-OPHTA exudates database. The experimental results demonstrate that Gaussian Process classifiers outperform the current state of the art classifiers for this problem.}, author = {Colomer, Adri{\'{a}}n and Ruiz, Pablo and Naranjo, Valery and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)}, doi = {10.1007/978-3-319-93000-8_73}, isbn = {9783319929996}, issn = {16113349}, keywords = {Bayesian modeling,Gaussian Processes,Hard exudate,Local Binary Patterns,Variational inference}, pages = {639--649}, title = {{Hard Exudate Detection Using Local Texture Analysis and Gaussian Processes}}, url = {http://link.springer.com/10.1007/978-3-319-93000-8_73}, volume = {10882 LNCS}, year = {2018} }
@inproceedings{Arun2018, abstract = {This paper presents an adaptable decoder-like model for video error concealment through optical flow prediction using deep neural networks. The horizontal and vertical motion fields from previous optical flows are separated and passed through two parallel pipelines with convolutional and long short-term memory layers. The combined output from these two networks, the predicted flow, is then used to reconstruct the degraded portion of the future video frame. Unlike current methods that use pixel or voxel information, we propose an architecture that uses three previous optical flows obtained through a flow generation step. The generator portion of the network can be easily interchanged with other methods, increasing the adaptability of the model. The network is trained in supervised mode and the performance is evaluated using standard video quality metrics by comparing the reconstructed frames from our prediction and the generated ground truth.}, author = {Sankisa, Arun and Punjabi, Arjun and Katsaggelos, Aggelos K.}, booktitle = {2018 25th IEEE International Conference on Image Processing (ICIP)}, doi = {10.1109/ICIP.2018.8451090}, isbn = {978-1-4799-7061-2}, issn = {15224880}, keywords = {CNN,ConvLSTM,Deep Neural Networks,Optical flow,Video Error Concealment}, month = {oct}, pages = {380--384}, publisher = {IEEE}, title = {{Video Error Concealment Using Deep Neural Networks}}, url = {https://ieeexplore.ieee.org/document/8451090/}, year = {2018} }
@inproceedings{Seunghwan2018, abstract = {We present a Bayesian approach for 3D image reconstruction of an extended object imaged with multi-focus microscopy (MFM). MFM simultaneously captures multiple sub-images of different focal planes to provide 3D information of the sample. The naive method to reconstruct the object is to stack the sub-images along the z-axis, but the result suffers from poor resolution in the z-axis. The maximum a posteriori framework provides a way to reconstruct a 3D image according to its observation model and prior knowledge. It jointly estimates the 3D image and the model parameters. Experimental results with synthetic and real experimental data show that it enables the high-quality 3D reconstruction of an extended object from MFM.}, author = {Yoo, Seunghwan and Ruiz, Pablo and Huang, Xiang and He, Kuan and Wang, Xiaolei and Gdor, Itay and Selewa, Alan and Daddysman, Matthew and Ferrier, Nicola J. and Hereld, Mark and Scherer, Norbert and Cossairt, Oliver and Katsaggelos, Aggelos K.}, booktitle = {2018 25th IEEE International Conference on Image Processing (ICIP)}, doi = {10.1109/ICIP.2018.8451309}, isbn = {978-1-4799-7061-2}, issn = {15224880}, keywords = {3D image reconstruction,Bayesian,Maximum a posteriori,Multi-focus microscopy,Total variation}, month = {oct}, pages = {3583--3587}, publisher = {IEEE}, title = {{Bayesian Approach for Automatic Joint Parameter Estimation in 3D Image Reconstruction from Multi-Focus Microscope}}, url = {https://ieeexplore.ieee.org/document/8451309/}, year = {2018} }
@inproceedings{Morteza2018, abstract = {Defective sleep arousal can contribute to significant sleep-related injuries and affect the quality of life. Investigating the arousal process is a challenging task as most of such events may be associated with subtle electrophysiological indications. Thus, developing an accurate model is an essential step toward the diagnosis and assessment of arousals. Here we introduce a novel approach for automatic arousal detection inspired by the states' recurrences in nonlinear dynamics. We first show how the states distance matrices of a complex system can be reconstructed to decrease the effect of false neighbors. Then, we use a convolutional neural network for probing the correlated structures inside the distance matrices with the arousal occurrences. Contrary to earlier studies in the literature, the proposed approach focuses on the dynamic behavior of polysomnography recordings rather than frequency analysis. The proposed approach is evaluated on the training dataset in a 3-fold cross-validation scheme and achieved an average of 19.20% and 78.57% for the area under the precision-recall (AUPRC) and area under the ROC curves, respectively. The overall AUPRC on the unseen test dataset is 19%.}, author = {Zabihi, Morteza and {Bahrami Rad}, Ali and S{\"{a}}rkk{\"{a}}, Simo and Kiranyaz, Serkan and {K. Katsaggelos}, Aggelos and Gabbouj, Moncef}, booktitle = {Computing in Cardiology}, doi = {10.22489/CinC.2018.257}, isbn = {9781728109589}, issn = {2325887X}, month = {dec}, pages = {1--4}, title = {{Automatic Sleep Arousal Detection Using Multimodal Biosignal Analysis}}, url = {http://www.cinc.org/archives/2018/pdf/CinC2018-257.pdf}, volume = {2018-Septe}, year = {2018} }
@inproceedings{bahaadini2018direct, abstract = {In this paper, benefiting from the strong ability of deep neural network in estimating non-linear functions, we propose a discriminative embedding function to be used as a feature extractor for clustering tasks. The trained embedding function transfers knowledge from the domain of a labeled set of morphologically-distinct images, known as classes, to a new domain within which new classes can potentially be isolated and identified. Our target application in this paper is the Gravity Spy Project, which is an effort to characterize transient, non-Gaussian noise present in data from the Advanced Laser Interferometer Gravitational-wave Observatory, or LIGO. Accumulating large, labeled sets of noise features and identifying of new classes of noise lead to a better understanding of their origin, which makes their removal from the data and/or detectors possible.}, archivePrefix = {arXiv}, arxivId = {1805.02296}, author = {Bahaadini, S. and Rohani, N. and Katsaggelos, A.K. and Noroozi, V. and Coughlin, S. and Zevin, M.}, booktitle = {2018 25th IEEE International Conference on Image Processing (ICIP)}, doi = {10.1109/ICIP.2018.8451708}, eprint = {1805.02296}, isbn = {978-1-4799-7061-2}, issn = {15224880}, keywords = {Deep Learning,Domain adaptation,Image Clustering,LIGO}, month = {oct}, organization = {IEEE}, pages = {748--752}, publisher = {IEEE}, title = {{Direct: Deep Discriminative Embedding for Clustering of Ligo Data}}, url = {https://ieeexplore.ieee.org/document/8451708/}, year = {2018} }
@inproceedings{Ewa, author = {Ewa, Deelman and Alan, Edelman and Lieven, Eeckhout and Jiaya, Jia and Steven, Feiner and Kevin, Fu and Thomas, Furness and Haibo, He and Pan, Hui and Sozon, Papavlasopoulos and Et al.}, booktitle = {2018 5th International Conference on Mathematics and Computers in Sciences and Industry (MCSI)}, doi = {10.1109/MCSI.2018.00007}, isbn = {978-1-5386-7500-7}, month = {aug}, pages = {11--12}, publisher = {IEEE}, title = {{Program Committee}}, url = {https://ieeexplore.ieee.org/document/8769805/}, year = {2018} }
@inproceedings{Aggelos2018, author = {Katsaggelos, Aggelos}, booktitle = {2018 AAAS Annual Meeting}, title = {{Hidden Intentions: Hyperspectral Data Fusion of Picasso's Blue Period Paintings}}, url = {https://aaas.confex.com/aaas/2018/meetingapp.cgi/Paper/20953}, year = {2018} }
@inproceedings{Hidalgo-Gavira2018, author = {Hidalgo-Gavira, Natalia and Mateos, Javier and Vega, Miguel and Molina, Rafael and Katsaggelos, Aggelos K.}, doi = {10.1007/978-3-030-00934-2_21}, pages = {183--191}, title = {{Fully Automated Blind Color Deconvolution of Histopathological Images}}, url = {http://link.springer.com/10.1007/978-3-030-00934-2_21}, year = {2018} }
@inproceedings{Seunghwan2018a, author = {Yoo, Seunghwan and Ruiz, Pablo and Huang, Xiang and He, Kuan and Ferrier, Nicola J and Hereld, Mark and Selewa, Alan and Daddysman, Matthew and Scherer, Norbert and Cossairt, Oliver and Katsaggelos, Aggelos K.}, booktitle = {2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, doi = {10.1109/ICASSP.2018.8462234}, isbn = {978-1-5386-4658-8}, month = {apr}, pages = {1453--1457}, publisher = {IEEE}, title = {{3D Image Reconstruction from Multi-Focus Microscope: Axial Super-Resolution and Multiple-Frame Processing}}, url = {https://ieeexplore.ieee.org/document/8462234/}, year = {2018} }
@inproceedings{Xiang2018, abstract = {We present a primal-dual interior point method (IPM) with a novel preconditioner to solve the ℓ 1 -norm regularized least square problem for nonnegative sparse signal reconstruction. IPM is a second-order method that uses both gradient and Hessian information to compute effective search directions and achieve super-linear convergence rates. It therefore requires many fewer iterations than first-order methods such as iterative shrinkage/thresholding algorithms (ISTA) that only achieve sub-linear convergence rates. However, each iteration of IPM is more expensive than in ISTA because it needs to evaluate an inverse of a Hessian matrix to compute the Newton direction. We propose to approximate each Hessian matrix by a diagonal matrix plus a rank-one matrix. This approximation matrix is easily invertible using the Sherman-Morrison formula, and is used as a novel preconditioner in a preconditioned conjugate gradient method to compute a truncated Newton direction. We demonstrate the efficiency of our algorithm in compressive 3D volumetric image reconstruction. Numerical experiments show favorable results of our method in comparison with previous interior point based and iterative shrinkage/thresholding based algorithms.}, author = {Huang, Xiang and He, Kuan and Yoo, Seunghwan and Cossairt, Oliver and Katsaggelos, Aggelos and Ferrier, Nicola and Hereld, Mark}, booktitle = {2018 25th IEEE International Conference on Image Processing (ICIP)}, doi = {10.1109/ICIP.2018.8451710}, isbn = {978-1-4799-7061-2}, issn = {15224880}, keywords = {3d volumetric image reconstruction,Compressive sensing,Nonnegative sparse,Norm regularized optimization,Primal-dual preconditioned interior point method}, month = {oct}, pages = {1193--1197}, publisher = {IEEE}, title = {{An Interior Point Method for Nonnegative Sparse Signal Reconstruction}}, url = {https://ieeexplore.ieee.org/document/8451710/}, year = {2018} }
@inproceedings{Natalia2018, abstract = {Most whole-slide histological images are stained with two or more chemical dyes. Slide stain separation or color deconvolution is a crucial step within the digital pathology workflow. In this paper, the blind color deconvolution problem is formulated within the Bayesian framework. Starting from a multi-stained histological image, our model takes into account both spatial relations among the concentration image pixels and similarity between a given reference color-vector matrix and the estimated one. Using Variational Bayes inference, three efficient new blind color deconvolution methods are proposed which provide automated procedures to estimate all the model parameters in the problem. A comparison with classical and current state-of-the-art color deconvolution algorithms using real images has been carried out demonstrating the superiority of the proposed approach.}, author = {Hidalgo-Gavira, Natalia and Mateos, Javier and Vega, Miguel and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {2018 25th IEEE International Conference on Image Processing (ICIP)}, doi = {10.1109/ICIP.2018.8451314}, isbn = {978-1-4799-7061-2}, issn = {1057-7149}, keywords = {Bayesian modeling and inference,Blind color deconvolution,histopathological images,variational Bayes}, month = {oct}, number = {1}, pages = {983--987}, pmid = {31634128}, publisher = {IEEE}, title = {{Blind Color Deconvolution of Histopathological Images Using a Variational Bayesian Approach}}, url = {https://ieeexplore.ieee.org/document/8870230/ https://ieeexplore.ieee.org/document/8451314/}, volume = {29}, year = {2018} }
@inproceedings{Sushobhan2018, abstract = {Ptychography is an imaging technique which aims to recover the complex-valued exit wavefront of an object from a set of its diffraction pattern magnitudes. Ptychography is one of the most popular techniques for sub-30 nanometer imaging as it does not suffer from the limitations of typical lens based imaging techniques. The object can be reconstructed from the captured diffraction patterns using iterative phase retrieval algorithms. Over time many algorithms have been proposed for iterative reconstruction of the object based on manually derived update rules. In this paper, we adapt automatic differentiation framework to solve practical and complex ptychographic phase retrieval problems and demonstrate its advantages in terms of speed, accuracy, adaptability and generalizability across different scanning techniques.}, author = {Ghosh, Sushobhan and Nashed, Youssef S. G. and Cossairt, Oliver and Katsaggelos, Aggelos}, booktitle = {2018 IEEE International Conference on Computational Photography (ICCP)}, doi = {10.1109/ICCPHOT.2018.8368470}, isbn = {978-1-5386-2526-2}, month = {may}, pages = {1--10}, publisher = {IEEE}, title = {{ADP: Automatic differentiation ptychography}}, url = {https://ieeexplore.ieee.org/document/8368470/}, year = {2018} }
@inproceedings{Linjie2018, abstract = {Video object segmentation targets segmenting a specific object throughout a video sequence when given only an annotated first frame. Recent deep learning based approaches find it effective to fine-tune a general-purpose segmentation model on the annotated frame using hundreds of iterations of gradient descent. Despite the high accuracy that these methods achieve, the fine-tuning process is inefficient and fails to meet the requirements of real world applications. We propose a novel approach that uses a single forward pass to adapt the segmentation model to the appearance of a specific object. Specifically, a second meta neural network named modulator is trained to manipulate the intermediate layers of the segmentation network given limited visual and spatial information of the target object. The experiments show that our approach is 70{\~{A}} - faster than fine-tuning approaches and achieves similar accuracy. Our model and code have been released at https://github.com/linjieyangsc/video-seg.}, archivePrefix = {arXiv}, arxivId = {1802.01218}, author = {Yang, Linjie and Wang, Yanran and Xiong, Xuehan and Yang, Jianchao and Katsaggelos, Aggelos K.}, booktitle = {2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition}, doi = {10.1109/CVPR.2018.00680}, eprint = {1802.01218}, isbn = {978-1-5386-6420-9}, issn = {10636919}, month = {jun}, pages = {6499--6507}, publisher = {IEEE}, title = {{Efficient Video Object Segmentation via Network Modulation}}, url = {https://ieeexplore.ieee.org/document/8578778/}, year = {2018} }
@inproceedings{Morteza, abstract = {The various award winners and the titles of their award winning papers are listed.}, author = {Morteza, Zabihi and {Ali Bahrami}, Rad and Aggelos, K Katsaggelos and Serkan, Kiranyaz and Susanna, Narkilahti and Tom{\'{a}}s, Teijeiro and ia Constantino, A Garc ' and Paulo, F{\'{e}}lix and Daniel, Castro and Et al.}, booktitle = {2017 Computing in Cardiology (CinC)}, doi = {10.23919/CIC.2017.8331431}, title = {{Computing in Cardiology 2017 awards summary ,}}, url = {https://ieeexplore.ieee.org/abstract/document/8331431}, year = {2017} }
@inproceedings{bahaadini2017deep, abstract = {Non-cosmic, non-Gaussian disturbances known as 'glitches', show up in gravitational-wave data of the Advanced Laser Interferometer Gravitational-wave Observatory, or aLIGO. In this paper, we propose a deep multi-view convolutional neural network to classify glitches automatically. The primary purpose of classifying glitches is to understand their characteristics and origin, which facilitates their removal from the data or from the detector entirely. We visualize glitches as spectrograms and leverage the state-of-the-art image classification techniques in our model. The suggested classifier is a multi-view deep neural network that exploits four different views for classification. The experimental results demonstrate that the proposed model improves the overall accuracy of the classification compared to traditional single view algorithms.}, archivePrefix = {arXiv}, arxivId = {1705.00034}, author = {Bahaadini, Sara and Rohani, Neda and Coughlin, Scott and Zevin, Michael and Kalogera, Vicky and Katsaggelos, Aggelos K.}, booktitle = {2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, doi = {10.1109/ICASSP.2017.7952693}, eprint = {1705.00034}, isbn = {978-1-5090-4117-6}, issn = {15206149}, keywords = {Multi-view learning,deep learning,image classification,neural network}, month = {mar}, organization = {IEEE}, pages = {2931--2935}, publisher = {IEEE}, title = {{Deep multi-view models for glitch classification}}, url = {http://ieeexplore.ieee.org/document/7952693/}, year = {2017} }
@inproceedings{Zihao2017b, abstract = {Digital in-line holography serves as a useful encoder for spatial information. This allows three-dimensional reconstruction from a two-dimensional image. This is applicable to the tasks of fast motion capture, particle tracking etc. Sampling high resolution holograms yields a spatiotemporal tradeoff. We spatially subsample holograms to increase temporal resolution. We demonstrate this idea with two subsampling techniques, periodic and uniformly random sampling. The implementation includes an on-chip setup for periodic subsampling and a DMD (Digital Micromirror Device)-based setup for pixel-wise random subsampling. The on-chip setup enables direct increase of up to 20 in camera frame rate. Alternatively, the DMD-based setup encodes temporal information as high-speed mask patterns, and projects these masks within a single exposure (coded exposure). This way, the frame rate is improved to the level of the DMD with a temporal gain of 10. The reconstruction of sub sampled data using the aforementioned setups is achieved in two ways. We examine and compare two iterative reconstruction methods. One is an error reduction phase retrieval and the other is sparsity-based compressed sensing algorithm. Both methods show strong capability of reconstructing complex object fields. We present both simulations and real experiments. In the lab, we image and reconstruct structure and movement of static polystyrene microspheres, microscopic moving peranema, macroscopic fast moving fur and glitters.}, author = {Wang, Zihao and Ryu, Donghun and He, Kuan and Horstmeyer, Roarke and Katsaggelos, Aggelos and Cossairt, Oliver}, booktitle = {Computational Imaging II}, doi = {10.1117/12.2262737}, editor = {Mahalanobis, Abhijit and Ashok, Amit and Tian, Lei and Petruccelli, Jonathan C. and Kubala, Kenneth S.}, isbn = {9781510609457}, issn = {1996756X}, month = {may}, pages = {102220G}, title = {{High-speed holographic imaging using compressed sensing and phase retrieval}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?doi=10.1117/12.2262737}, volume = {10222}, year = {2017} }
@inproceedings{Morteza2017, abstract = {Atrial Fibrillation (AF) is characterized by chaotic electrical impulses in the atria, which leads to irregular heartbeats and can develop blood clots and stroke. Therefore, early detection of AF is crucial for increasing the success rate of the treatment. This study is focused on detection of AF rhythm using hand-held ECG monitoring devices, in addition to three other classes: normal or sinus rhythm, other rhythms, and too noisy to analyze. The pipeline of the proposed method consists of three major components: preprocessing and feature extraction, feature selection, and classification. In total, 491 hand-crafted features are extracted. Then, 150 features are selected in a feature ranking procedure. The selected features are from time, frequency, time-frequency domains, and phase space reconstruction of the ECG signals. In the final stage, a random forest classifier is used to classify the selected features into one of the four aforementioned ECG classes. Using the scoring mechanism provided by PhysioNet/Computing in Cardiology (CinC) Challenge 2017, the overall score (mean±std) of 81.9±2.6% is achieved over the training dataset in 10-fold cross-validation. The proposed algorithm tied for the first place in the PhysioNet/CinC Challenge 2017 with an overall score of 82.6% (rounded to 83%) on the unseen test dataset.}, author = {Zabihi, Morteza and {Bahrami Rad}, Ali and Katsaggelos, Aggelos K. and Kiranyaz, Serkan and Narkilahti, Susanna and Gabbouj, Moncef}, booktitle = {Computing in Cardiology}, doi = {10.22489/CinC.2017.069-336}, issn = {2325887X}, month = {sep}, pages = {1--4}, title = {{Detection of Atrial Fibrillation in ECG Hand-held Devices Using a Random Forest Classifier}}, url = {http://www.cinc.org/archives/2017/pdf/069-336.pdf}, volume = {44}, year = {2017} }
@inproceedings{Manerikar2017, abstract = {Identifying food types consumed and their calorie composition is one of the central tasks of dietary assessment. Traditional automated image processing methods learn to map images to an existing food database with known caloric composition. However, even when the correct food type is identified, caloric makeup can vary depending on its ingredients, and using true-color images proves insufficient to distinguish within food type variability. In this paper, we show that hyperspectral imaging provides useful information and promise in distinguishing caloric composition within the same food type. We collect data using a hyperspectral camera from Nigerian foods cooked with varying degrees of fat content, and capture images under different intensities of light. We apply Principle Component Analysis (PCA) to reduce the dimensionality, and train a Support Vector Machine (SVM) classifier using a Radial Basis Function kernel and show that applying this technique on hyperspectral images can more readily distinguish calorie composition. Furthermore, compared with methods that only use true-color based features, our method shows that a classifier trained using features from hyperspectral images is significantly more predictive of within-food caloric content, and by fusing results from two classifiers trained separately using hyperspectral and RGB imagery we obtain the greatest predictive power.}, author = {Wang, Xinzuo and Rohani, Neda and Manerikar, Adwaiy and Katsagellos, Aggelos and Cossairt, Oliver and Alshurafa, Nabil}, booktitle = {Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)}, doi = {10.1007/978-3-319-70742-6_45}, isbn = {9783319707419}, issn = {16113349}, keywords = {Calorie detection,Food identification,Hyperspectral imaging}, pages = {462--470}, title = {{Distinguishing Nigerian Food Items and Calorie Content with Hyperspectral Imaging}}, url = {https://link.springer.com/10.1007/978-3-319-70742-6_45}, volume = {10590 LNCS}, year = {2017} }
@inproceedings{Juan2017b, abstract = {In this work, we propose a new variational blind deconvolution method for spike and slab prior models. Soft-sparse or shrinkage priors such as the Laplace and other related Gaussian Scale Mixture priors may not be ideal sparsity promoting priors. They assign zero probability mass to events we may be interested in assigning a probability greater than zero. The truly sparse nature of the spike and slab priors allows us to discard irrelevant information in the blur estimation process, resulting in improved performance. We present an efficient inference algorithm to estimate the unknown blur kernel in the filter space, from which we estimate the final deblurred image. The VB approach we propose in this paper handles the inference in a much more efficient way than MCMC, and is more accurate than the standard mean field variational approximation. We prove the efficacy of our method by means of a series of experiments on both synthetically generated and real images.}, author = {Serra, Juan G. and Mateos, Javier and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {2017 IEEE International Conference on Image Processing (ICIP)}, doi = {10.1109/ICIP.2017.8296986}, isbn = {978-1-5090-2175-8}, issn = {15224880}, keywords = {Blind deconvolution,Spike-and-slab,Variational Bayesian approach}, month = {sep}, pages = {3765--3769}, publisher = {IEEE}, title = {{Spike and slab variational inference for blind image deconvolution}}, url = {http://ieeexplore.ieee.org/document/8296986/}, volume = {2017-Septe}, year = {2017} }
@inproceedings{David2017, author = {Stork, David G. and Rohani, Neda and Katsaggelos, Aggelos K.}, booktitle = {Computational Imaging II}, doi = {10.1117/12.2257670}, editor = {Mahalanobis, Abhijit and Ashok, Amit and Tian, Lei and Petruccelli, Jonathan C. and Kubala, Kenneth S.}, isbn = {9781510609457}, issn = {1996756X}, month = {may}, pages = {102220P}, title = {{Matrix sparsification and non-negative factorization for task partitioning in computational sensing and imaging}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?doi=10.1117/12.2257670}, volume = {10222}, year = {2017} }
@inproceedings{Domingo2017, abstract = {In the last years, many computer vision algorithms have been developed for X-ray testing tasks. Some of them deal with baggage inspection, in which the aim is to detect automatically target objects. The progress in automated baggage inspection, however, is modest and very limited compared to what is needed because X-ray screening systems are still being manipulated by human inspectors. In this work, we present an X-ray imaging model that can separate foreground from background in baggage screening. The model can be used in two main tasks: i) Simulation of new X-ray images, where simulated images can be used in training programs for human inspectors, or can be used to enhance datasets for computer vision algorithms. ii) Detection of (threat) objects, where new algorithms can be employed to perform automated baggage inspection or to aid an user in the inspection task showing potential threats. In our model, rather than a multiplication of foreground and background, that is typically used in X-ray imaging, we propose the addition of logarithmic images. This allows the use of linear strategies to superimpose images of threat objects onto X-ray images and the use of sparse representations in order to segment target objects. In our experiments, we simulate new X-ray images of handguns, shuriken and razor blades, in which it is impossible to distinguish simulated and real X-ray images. In addition, we show in our experiments the effective detection of shuriken, razor blades and handguns using the proposed algorithm outperforming some alternative state-of- the-art techniques.}, author = {Mery, Domingo and Katsaggelos, Aggelos K.}, booktitle = {2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)}, doi = {10.1109/CVPRW.2017.37}, isbn = {978-1-5386-0733-6}, issn = {21607516}, month = {jul}, pages = {251--259}, publisher = {IEEE}, title = {{A Logarithmic X-Ray Imaging Model for Baggage Inspection: Simulation and Object Detection}}, url = {http://ieeexplore.ieee.org/document/8014771/}, volume = {2017-July}, year = {2017} }
@inproceedings{Armin2017, abstract = {Fourier ptychography is an imaging technique that overcomes the diffraction limit of conventional cameras with applications in microscopy and long range imaging. Diffraction blur causes resolution loss in both cases. In Fourier ptychography, a coherent light source illuminates an object, which is then imaged from multiple viewpoints. The reconstruction of the object from these set of recordings can be obtained by an iterative phase retrieval algorithm. However, the retrieval process is slow and does not work well under certain conditions. In this paper, we propose a new reconstruction algorithm that is based on convolutional neural networks and demonstrate its advantages in terms of speed and performance.}, author = {Kappeler, Armin and Ghosh, Sushobhan and Holloway, Jason and Cossairt, Oliver and Katsaggelos, Aggelos}, booktitle = {2017 IEEE International Conference on Image Processing (ICIP)}, doi = {10.1109/ICIP.2017.8296574}, isbn = {978-1-5090-2175-8}, issn = {15224880}, keywords = {CNN,Convolutional Neural Network,Fourier ptychography}, month = {sep}, pages = {1712--1716}, publisher = {IEEE}, title = {{Ptychnet: CNN based fourier ptychography}}, url = {http://ieeexplore.ieee.org/document/8296574/}, volume = {2017-Septe}, year = {2017} }
@inproceedings{Nima2017a, abstract = {We develop a theoretical framework for how hierarchical representation of features in input data emerges from progressive renormalization and sparse-coding done using convolutional layers. At each level new degrees of freedom appear, which are low-lying energy states, separated by a gap from a pool of high energy states. This separation defines a natural way for sparse encoding of training data. Repeating this renormalization procedure results in a hierarchical representation of the data. We show that trained filter in popular image processing deep neural nets are consistent with such a hierarchical representation.}, author = {Dehmamy, Nima and Rohani, Neda and Katsaggelos, Aggelos}, booktitle = {APS March Meeting Abstracts}, pages = {T1----371}, title = {{Hierarchical abstraction of information in Deep Neural Networks}}, url = {https://meetings.aps.org/Meeting/MAR17/Event/299460}, volume = {2017}, year = {2017} }
@inproceedings{Juan2017, abstract = {This work presents a greedy Bayesian dictionary learning (DL) algorithm where not only the signals but also the dictionary representation matrix accept a sparse representation. This double-sparsity (DS) model has been shown to be superior to the standard sparse approach in some image processing tasks, where sparsity is only imposed on the signal coefficients. We present a new Bayesian approach which addresses typical shortcomings of regularization-based DS algorithms: the prior knowledge of the true noise level and the need of parameter tuning. Our model estimates the noise and sparsity levels as well as the model parameters from the observations and frequently outperforms state-of-the-art dictionary based techniques by taking into account the uncertainty of the estimates. Additionally, we introduce a versatile notation which generalizes denoising, inpainting and compressive sensing problem formulations. Finally, theoretical results are validated with denoising experiments on a set of images.}, author = {Serra, Juan G. and Villena, Salvador and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {2017 IEEE International Conference on Image Processing (ICIP)}, doi = {10.1109/ICIP.2017.8296619}, isbn = {978-1-5090-2175-8}, issn = {15224880}, keywords = {Bayesian Inference,Dictionary Learning,Sparse Representation}, month = {sep}, pages = {1935--1939}, publisher = {IEEE}, title = {{Greedy Bayesian double sparsity dictionary learning}}, url = {http://ieeexplore.ieee.org/document/8296619/}, volume = {2017-Septe}, year = {2017} }
@inproceedings{Zihao2017, abstract = {We propose a dictionary-based phase retrieval approach for monitoring in vivo biological samples based on lens-free on-chip holographic video. Our results present a temporal increase of 9× with 4×4 sub-sampling.}, address = {Washington, D.C.}, author = {Wang, Zihao and Dai, Qiqin and Ryu, Donghun and He, Kuan and Horstmeyer, Roarke and Katsaggelos, Aggelos K. and Cossairt, Oliver}, booktitle = {Imaging and Applied Optics 2017 (3D, AIO, COSI, IS, MATH, pcAOP)}, doi = {10.1364/COSI.2017.CTu2B.3}, isbn = {978-1-943580-29-3}, pages = {CTu2B.3}, publisher = {OSA}, title = {{Dictionary-based phase retrieval for space-time super resolution using lens-free on-chip holographic video}}, url = {https://opg.optica.org/abstract.cfm?URI=COSI-2017-CTu2B.3}, volume = {Part F46-C}, year = {2017} }
@inproceedings{Arjun2017, abstract = {Convolutional neural networks (CNNs) are a staple in the fields of computer vision and image processing. These networks perform visual tasks with state-of-the-art accuracy; yet, the understanding behind the success of these algorithms is still lacking. In particular, the process by which CNNs learn effective task-specific features is still unclear. This work elucidates such phenomena by applying recent deep visualization techniques during different stages of the training process. Additionally, this investigation provides visual justification to the benefits of transfer learning. The results are in line with previously discussed notions of feature specificity, and show a new facet of a particularly vexing machine learning pitfall: overfitting.}, author = {Punjabi, Arjun and Katsaggelos, Aggelos K.}, booktitle = {2017 25th European Signal Processing Conference (EUSIPCO)}, doi = {10.23919/EUSIPCO.2017.8081219}, isbn = {978-0-9928626-7-1}, keywords = {Convolutional neural network,Deep learning,Feature visualization,Transfer learning}, month = {aug}, pages = {311--315}, publisher = {IEEE}, title = {{Visualization of feature evolution during convolutional neural network training}}, url = {http://ieeexplore.ieee.org/document/8081219/}, volume = {2017-Janua}, year = {2017} }
@inproceedings{Serra2017, author = {Serra, Juan G. and Mateos, Javier and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {2017 25th European Signal Processing Conference (EUSIPCO)}, doi = {10.23919/EUSIPCO.2017.8081458}, isbn = {978-0-9928626-7-1}, month = {aug}, pages = {1495--1499}, publisher = {IEEE}, title = {{Parameter estimation in spike and slab variational inference for blind image deconvolution}}, url = {http://ieeexplore.ieee.org/document/8081458/}, year = {2017} }
@inproceedings{Pablo2017, abstract = {Passive Millimeter Wave Images (PMMWIs) are being increasingly used to identify and localize objects concealed under clothing. Taking into account the quality of these images and the unknown position, shape, and size of the hidden objects, large data sets are required to build successful classification/detection systems. Kernel methods, in particular Gaussian Processes (GPs), are sound, flexible, and popular techniques to address supervised learning problems. Unfortunately, their computational cost is known to be prohibitive for large scale applications. In this work, we present a novel approach to PMMWI classification based on the use of Gaussian Processes for large data sets. The proposed methodology relies on linear approximations to kernel functions through random Fourier features. Model hyperparameters are learned within a variational Bayes inference scheme. Our proposal is well suited for real-time applications, since its computational cost at training and test times is much lower than the original GP formulation. The proposed approach is tested on a unique, large, and real PMMWI database containing a broad variety of sizes, types, and locations of hidden objects.}, author = {Morales, Pablo and Perez-Suay, Adrian and Molina, Rafael and Camps-Valls, Gustau and Katsaggelos, Aggelos K.}, booktitle = {2017 IEEE International Conference on Image Processing (ICIP)}, doi = {10.1109/ICIP.2017.8296305}, isbn = {978-1-5090-2175-8}, issn = {15224880}, keywords = {Gaussian processes,Large scale classification,PMMWI,Random Fourier features,Variational inference}, month = {sep}, pages = {370--374}, publisher = {IEEE}, title = {{Passive millimeter wave image classification with large scale Gaussian processes}}, url = {http://ieeexplore.ieee.org/document/8296305/}, volume = {2017-Septe}, year = {2017} }
@inproceedings{Chia-Kai2017, abstract = {Surface shape scanning techniques, such as laser scanning and photometric stereo, are widespread analytical tools used in the field of cultural heritage. Compared to regular 2D RGB photos, 3D surface scans provide higher fidelity of an object's surface shape which assist conservators, art historians, and archaeologists in understanding how these artworks and artifacts are made and to digitally document them for purposes of conservation. However, current state-of-the-art 3D surface scanning tools used in art conservation are often expensive and bulky-such as light dome structures that are often over 1 m in diameter. In this paper, we introduce mobile shape-from-shifting (SfS): A simple, low-cost and streamlined photometric stereo framework for scanning planar surfaces with a consumer mobile device coupled to a low-cost add-on component. Our free-form mobile SfS framework relaxes the rigorous hardware and other complex requirements inherent to conventional 3D scanning tools. This is achieved by taking a sequence of photos with the on-board camera and flash of a mobile device. The sequence of captures are used to reconstruct high quality normal maps using nearlight photometric stereo algorithms, which are of comparable quality to conventional photometric stereo. We demonstrate 3D surface reconstructions with SfS on different materials and scales. Moreover, the mobile SfS technique can be used 'in the wild' so that 3D scans may be performed in their natural environment, eliminating the need for transport to a laboratory setting. With the elegant design and low cost, we believe our Mobile SfS can greatly benefit the conservation community by providing a userfriendly and cost-effective solution for 3D surface scanning.}, author = {Yeh, Chia-Kai and Li, Fengqiang and Pastorelli, Gianluca and Walton, Marc and Katsaggelos, Aggelos K. and Cossairt, Oliver}, booktitle = {2017 IEEE 13th International Conference on e-Science (e-Science)}, doi = {10.1109/eScience.2017.89}, isbn = {978-1-5386-2686-3}, keywords = {3D Surface Shape Reconstruction,Image-Based Modeling,Near-Light Position Calibration,Photometric Stereo,Reflectance Transformation Imaging,Scale-invariant Feature Transform}, month = {oct}, pages = {551--558}, publisher = {IEEE}, title = {{Shape-from-Shifting: Uncalibrated Photometric Stereo with a Mobile Device}}, url = {http://ieeexplore.ieee.org/document/8109194/}, year = {2017} }
@inproceedings{Stefanos, author = {Stefanos, Kollias and George, Vachtsevanos and Ryzard, S Choras and Tadeusz, Kaczorek and Leon, Chua and Aggelos, Katsaggelos and Panos, Pardalos and Narsingh, Deo and Wasfy, B Mikhael and Georgios, B Giannakis and Et al.}, booktitle = {2017 International Conference on Control, Artificial Intelligence, Robotics & Optimization (ICCAIRO)}, doi = {10.1109/ICCAIRO.2017.7}, isbn = {978-1-5090-6536-3}, month = {may}, pages = {xiii--xiii}, publisher = {IEEE}, title = {{Program Committee}}, url = {http://ieeexplore.ieee.org/document/8252949/}, year = {2017} }
@inproceedings{Matthew2017, abstract = {Multi-frame image super-resolution (SR) is an image processing technology applicable to any digital, pixilated camera that is limited, by construction, to a certain number of pixels. The objective of SR is to utilize signal processing to overcome the physical limitation and emulate the 'capabilities' of a camera with a higher-density pixel array. SR is well known to be an ill-posed problem and, consequently, state-of-the-art solutions approach it statistically, typically making use of Bayesian inference. Unfortunately, direct marginalization of the posterior distribution resulting from the Bayesian modeling is not analytically tractable. An approximation method, such as Variational Bayesian Inference (VBI), is a powerful tool that retains the advantages of statistical modeling. However, its derivation is tedious and model specific. In this paper, we propose an alternative approximate inference methodology, based upon the well-established, Gaussian Information Filter, which offers a much simpler mathematical derivation while retaining the statistical advantages of VBI.}, author = {Woods, Matthew and Katsaggelos, Aggelos}, booktitle = {2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, doi = {10.1109/ICASSP.2017.7952380}, isbn = {978-1-5090-4117-6}, issn = {15206149}, keywords = {Image-Processing,Inverse Problems,Photogrammetry,Remote Sensing,Super-Resolution}, month = {mar}, pages = {1368--1372}, publisher = {IEEE}, title = {{A bayesian multi-frame image super-resolution algorithm using the Gaussian Information Filter}}, url = {http://ieeexplore.ieee.org/document/7952380/}, year = {2017} }
@inproceedings{Zihao2017c, abstract = {We propose an auto-refocused phase retrieval approach that combines refocusing and phase retrieving properties based on lens-free on-chip in-line holography. We demonstrate a 4D tracking application of imaging/monitoring in vivo biomedical scenes, e.g. Blepharisma.}, address = {Washington, D.C.}, author = {Wang, Zihao and Ryu, Donghun and He, Kuan and Cossairt, Oliver and Katsaggelos, Aggelos K.}, booktitle = {Digital Holography and Three-Dimensional Imaging}, doi = {10.1364/DH.2017.Tu2A.4}, isbn = {978-1-943580-28-6}, pages = {Tu2A.4}, publisher = {OSA}, title = {{4D Tracking of Biological Samples using Lens-free On-chip In-line Holography}}, url = {https://opg.optica.org/abstract.cfm?URI=DH-2017-Tu2A.4}, volume = {Part F47-D}, year = {2016} }
@inproceedings{Michael2016, abstract = {In this work we present a general framework for robust error estimation in face recognition. The proposed formulation allows the simultaneous use of various loss functions for modeling the residual in face images, which usually follows non-standard distributions, depending on the image capturing conditions. Our method extends the current vast literature offering flexibility in the selection of the residual modeling characteristics but, at the same time, considering many existing algorithms as special cases. As such, it proves robust for a range of error inducing factors, such as, varying illumination, occlusion, pixel corruption, disguise or their combinations. Extensive simulations document the superiority of selecting multiple models for representing the noise term in face recognition problems, allowing the algorithm to achieve near-optimal performance in most of the tested face databases. Finally, the multi-model residual representation offers useful insights into understanding how different noise types affect face recognition rates.}, author = {Iliadis, Michael and Spinoulas, Leonidas and Berahas, Albert S. and Wang, Haohong and Katsaggelos, Aggelos K.}, booktitle = {2016 IEEE International Conference on Image Processing (ICIP)}, doi = {10.1109/ICIP.2016.7532956}, isbn = {978-1-4673-9961-6}, issn = {15224880}, keywords = {Error correction,Face recognition,Robust representation,Sparse representation}, month = {sep}, pages = {3229--3233}, publisher = {IEEE}, title = {{Multi-model robust error correction for face recognition}}, url = {http://ieeexplore.ieee.org/document/7532956/}, volume = {2016-Augus}, year = {2016} }
@inproceedings{Ruiz2016, author = {Ruiz, Pablo and Besler, Emre and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {2016 IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP)}, doi = {10.1109/MLSP.2016.7738909}, isbn = {978-1-5090-0746-2}, month = {sep}, pages = {1--6}, publisher = {IEEE}, title = {{Variational Gaussian process for missing label crowdsourcing classification problems}}, url = {http://ieeexplore.ieee.org/document/7738909/}, year = {2016} }
@inproceedings{Armin2016a, abstract = {Convolutional neural networks (CNN) have been successfully applied to image super-resolution (SR) as well as other image restoration tasks. In this paper, we consider the problem of compressed video super-resolution. Traditional SR algorithms for compressed videos rely on information from the encoder such as frame type or quantizer step, whereas our algorithm only requires the compressed low resolution frames to reconstruct the high resolution video. We propose a CNN that is trained on both the spatial and the temporal dimensions of compressed videos to enhance their spatial resolution. Consecutive frames are motion compensated and used as input to a CNN that provides super-resolved video frames as output. Our network is pretrained with images, which significantly improves the performance over random initialization. In extensive experimental evaluations, we trained the state-of-the-art image and video superresolution algorithms on compressed videos and compared their performance to our proposed method.}, author = {Kappeler, Armin and Yoo, Seunghwan and Dai, Qiqin and Katsaggelos, Aggelos K.}, booktitle = {2016 IEEE International Conference on Image Processing (ICIP)}, doi = {10.1109/ICIP.2016.7532538}, isbn = {978-1-4673-9961-6}, issn = {15224880}, keywords = {Convolutional Neural Networks,Deep Learning,Super-Resolution,Video Compression}, month = {sep}, pages = {1150--1154}, publisher = {IEEE}, title = {{Super-resolution of compressed videos using convolutional neural networks}}, url = {http://ieeexplore.ieee.org/document/7532538/}, volume = {2016-Augus}, year = {2016} }
@inproceedings{Juan2016, abstract = {In this work we address the multispectral image classification problem from a Bayesian perspective. We develop an algorithm which utilizes the logistic regression function as the observation model in a probabilistic framework, Super-Gaussian (SG) priors which promote sparsity on the adaptive coefficients, and Variational inference to obtain estimates of all the model unknowns. The proposed algorithm is validated on both synthetic and real experiments and compared with other state-of-the-art methods, such as Support Vector Machine and Gaussian Processes, demonstrating its improved performance.}, author = {Serra, Juan G. and Ruiz, Pablo and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {2016 IEEE International Conference on Image Processing (ICIP)}, doi = {10.1109/ICIP.2016.7532687}, isbn = {978-1-4673-9961-6}, issn = {15224880}, keywords = {Bayes Methods,Image Classification,Inference Algorithms}, month = {sep}, pages = {1893--1897}, publisher = {IEEE}, title = {{Bayesian logistic regression with sparse general representation prior for multispectral image classification}}, url = {http://ieeexplore.ieee.org/document/7532687/}, volume = {2016-Augus}, year = {2016} }
@inproceedings{Javier2016, abstract = {Passive Millimeter Wave Images currently used to detect hidden threats suffer from low resolution, blur, and a very low signal-to-noise-ratio. These shortcomings render threat detection, both visual and automatic, very challenging. Furthermore, due to the presence of very severe noise, most of the blind image restoration methods fail to recover the system blurring kernel from a single image. In this paper we propose a robust Bayesian multiframe blind image deconvolution method that approximates the posterior distribution of the blur by a Dirichlet distribution. We show that this approach naturally incorporates the non-negativity and normalization constraints for the blur and cope well with the image noise. The performance of the proposed method is tested on both synthetic and real images.}, author = {Mateos, Javier and Lopez, Antonio and Vega, Miguel and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {2016 IEEE International Conference on Image Processing (ICIP)}, doi = {10.1109/ICIP.2016.7532845}, isbn = {978-1-4673-9961-6}, issn = {15224880}, keywords = {Blind image deconvolution,Passive millimeter wave imaging,Variational Dirichlet}, month = {sep}, pages = {2678--2682}, publisher = {IEEE}, title = {{Multiframe blind deconvolution of passive millimeter wave images using variational dirichlet blur kernel estimation}}, url = {http://ieeexplore.ieee.org/document/7532845/}, volume = {2016-Augus}, year = {2016} }
@inproceedings{Yanran2016, abstract = {Stroke is one of the leading causes of death and disability. Clinically, to establish stroke patient prognosis, an accurate delineation of brain lesion is essential, which is time consuming and prone to subjective errors. In this paper, we propose a novel method call Deep Lesion Symmetry ConvNet to automatically segment chronic stroke lesions using MRI. An 8-layer 3D convolutional neural network is constructed to handle the MRI voxels. An additional CNN stream using the corresponding symmetric MRI voxels is combined, leading to a significant improvement in system performance. The high average dice coefficient achieved on our dataset based on data collected from three research labs demonstrates the effectiveness of our method.}, author = {Wang, Yanran and Katsaggelos, Aggelos K. and Wang, Xue and Parrish, Todd B.}, booktitle = {2016 IEEE International Conference on Image Processing (ICIP)}, doi = {10.1109/ICIP.2016.7532329}, isbn = {978-1-4673-9961-6}, issn = {15224880}, keywords = {Brain Quasi-symmetry,Deep Learning,Image Segmentation,MRI,Stroke}, month = {sep}, pages = {111--115}, publisher = {IEEE}, title = {{A deep symmetry convnet for stroke lesion segmentation}}, url = {http://ieeexplore.ieee.org/document/7532329/}, volume = {2016-Augus}, year = {2016} }
@inproceedings{Qiqin2016a, abstract = {X-Ray fluorescence (XRF) scanning of works of art is becoming an increasingly popular non-destructive analytical method. The high quality XRF spectra is necessary to obtain significant information on both major and minor elements used for characterization and provenance analysis. However, there is a trade-off between the spatial resolution of an XRF scan and the Signal-to-Noise Ratio (SNR) of each pixel's spectrum, due to the limited scanning time. In this paper, we propose an XRF image super-resolution method to address this trade-off, thus obtaining a high spatial resolution XRF scan with high SNR. We use a sparse representation of each pixel using a dictionary trained from the spectrum samples of the image, while imposing a spatial smoothness constraint on the sparse coefficients. We then increase the spatial resolution of the sparse coefficient map using a conventional super-resolution method. Finally the high spatial resolution XRF image is reconstructed by the high spatial resolution sparse coefficient map and the trained spectrum dictionary.}, author = {Dai, Qiqin and Pouyet, Emeline and Cossairt, Oliver and Walton, Marc and Casadio, Francesca and Katsaggelos, Aggelos}, booktitle = {2016 IEEE 12th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP)}, doi = {10.1109/IVMSPW.2016.7528182}, isbn = {978-1-5090-1929-8}, keywords = {X-ray fluorescence,dictionary learning,sparse coding,super-resolution}, month = {jul}, pages = {1--5}, publisher = {IEEE}, title = {{X-Ray fluorescence image super-resolution using dictionary learning}}, url = {http://ieeexplore.ieee.org/document/7528182/}, year = {2016} }
@inproceedings{Armin2016b, abstract = {Video retrieval and video copy detection are well studied problems. The goal is to find the matching video in a database from a given query video. Typically, these query videos are short and aligning the query video is of secondary importance. Short sequences can be aligned using dynamic time warping. But, since time and memory usage increases quadratically with the length of the sequences, such process is not suitable for the alignment of two full length movies. A typical feature film is between 70 and 210 minutes long. Our goal is to find an accurate frame-by-frame alignment of a full length original film and a copy that has inserted and deleted sequences (e.g., commercial breaks or censorship), as well as differences in quality, format and framerate. We propose a fast, robust and memory efficient video sequence alignment algorithm which has linear space and time complexity.}, author = {Kappeler, Armin and Iliadis, Michael and Wang, Haohong and Katsaggelos, Aggelos K.}, booktitle = {2016 IEEE International Conference on Image Processing (ICIP)}, doi = {10.1109/ICIP.2016.7532975}, isbn = {978-1-4673-9961-6}, issn = {15224880}, keywords = {A∗,Dynamic Time Warping,Keyframe Extraction,Sequence Alignment,Video Alignment}, month = {sep}, pages = {3324--3328}, publisher = {IEEE}, title = {{Block based video alignment with linear time and space complexity}}, url = {http://ieeexplore.ieee.org/document/7532975/}, volume = {2016-Augus}, year = {2016} }
@inproceedings{Arun2016a, abstract = {In this paper we propose a new quality metric to estimate the impact of packet loss on the perceptual quality of encoded video sequences transmitted over error-prone networks. The proposed metric, henceforth referred to as Cumulative Distortion using Structural Similarity (CDSSIM), quantifies the overall structural distortion resulting from bidirectional error propagation in predictively coded, motion compensated videos. Furthermore, we present a No-Reference (NR) sparse regression model to predict the proposed CDSSIM metric using pre-defined features associated with slice loss. The Least Absolute Shrinkage and Selection Operator (LASSO) method is applied for two resolution formats with features extracted solely from the encoded bit-stream. Standardized statistical performance measures show that the model can predict the cumulative distortion to a high degree of accuracy. We further evaluate the results using a Quartile-Based Prioritization (QBP) scheme and demonstrate that the predicted data provides an effective way to prioritize packets for video streaming applications.}, author = {Sankisa, Arun and Pandremmenou, Katerina and Kondi, Lisimachos P. and Katsaggelos, Aggelos K.}, booktitle = {2016 IEEE International Conference on Image Processing (ICIP)}, doi = {10.1109/ICIP.2016.7532728}, isbn = {978-1-4673-9961-6}, issn = {15224880}, keywords = {Cumulative distortion,LASSO,Packet prioritization,Structural Similarity,Video quality}, month = {sep}, pages = {2097--2101}, publisher = {IEEE}, title = {{A novel cumulative distortion metric and a no-reference sparse prediction model for packet prioritization in encoded video transmission}}, url = {http://ieeexplore.ieee.org/document/7532728/}, volume = {2016-Augus}, year = {2016} }
@inproceedings{Neda2016, abstract = {In this paper, we study the problem of automatic identification of pigments applied to paintings using hyperspectral reflectance data. Here, we cast the problem of pigment identification in a novel way by decomposing the spectrum into pure pigments. The pure pigment exemplars, chosen and prepared in our laboratory based on historic sources and archaeological examples, closely resemble the materials used to make ancient paintings. To validate our algorithm, we created a set of mock-up paintings in our laboratory consisting of a broad palette of mixtures of pure pigments. Our results clearly demonstrate more accurate estimation of pigment composition than purely distance-based methods such as spectral angle mapping (SAM) and spectral correlation mapping (SCM). In addition, we studied hyperspectral imagery acquired of a Roman-Egyptian portrait, excavated from the site of Tebtunis in the Fayum region of Egypt, and dated to about the 2nd century CE. Using ground truth information obtained using Raman spectroscopy, we show qualitatively that our method accurately detects pigment composition for the specific pigments hematite and indigo.}, author = {Rohani, Neda and Salvant, Johanna and Bahaadini, Sara and Cossairt, Oliver and Walton, Marc and Katsaggelos, Aggelos}, booktitle = {2016 24th European Signal Processing Conference (EUSIPCO)}, doi = {10.1109/EUSIPCO.2016.7760621}, isbn = {978-0-9928-6265-7}, issn = {22195491}, month = {aug}, pages = {2111--2115}, publisher = {IEEE}, title = {{Automatic pigment identification on roman Egyptian paintings by using sparse modeling of hyperspectral images}}, url = {http://ieeexplore.ieee.org/document/7760621/}, volume = {2016-Novem}, year = {2016} }
@inproceedings{besler2016classification, abstract = {In this paper we address supervised learning problems where, instead of having a single annotator who provides the ground truth, multiple annotators, usually with varying degrees of expertise, provide conflicting labels for the same sample. Once Gaussian Process classification has been adapted to this problem we propose and describe how Variational Bayes inference can be used to, given the observed labels, approximate the posterior distribution of the latent classifier and also estimate each annotator's reliability. In the experimental section, we evaluate the proposed method on both generated synthetic and real data, and compare it with state of the art crowdsourcing methods.}, author = {Besler, Emre and Ruiz, Pablo and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {2016 24th European Signal Processing Conference (EUSIPCO)}, doi = {10.1109/EUSIPCO.2016.7760604}, isbn = {978-0-9928-6265-7}, issn = {22195491}, keywords = {Bayesian modeling,Classification,Crowdsourcing,Gaussian process,Multiple labels,Variational inference}, month = {aug}, organization = {IEEE}, pages = {2025--2029}, publisher = {IEEE}, title = {{Classification of multiple annotator data using variational Gaussian process inference}}, url = {http://ieeexplore.ieee.org/document/7760604/}, volume = {2016-Novem}, year = {2016} }
@inproceedings{Oliver2016, abstract = {Incoherent holography has recently attracted significant research interest due to its flexibility for a wide variety of light sources. In this paper, we use compressive sensing to reconstruct a three-dimensional volumetric object from its two-dimensional Fresnel incoherent correlation hologram. We show how compressed sensing enables reconstruction without out-of-focus artifacts, when compared to conventional back-propagation recovery. Finally, we analyze the reconstruction guarantees of the proposed approach both numerically and theoretically and compare that with coherent holography.}, author = {Cossairt, Oliver and He, Kuan and Shang, Ruibo and Matsuda, Nathan and Sharma, Manoj and Huang, Xiang and Katsaggelos, Aggelos and Spinoulas, Leonidas and Yoo, Seunghwan}, booktitle = {2016 IEEE International Conference on Image Processing (ICIP)}, doi = {10.1109/ICIP.2016.7532499}, isbn = {978-1-4673-9961-6}, issn = {15224880}, keywords = {Compressive sensing,Incoherent holography,Inverse problems,Microscopy}, month = {sep}, pages = {958--962}, publisher = {IEEE}, title = {{Compressive reconstruction for 3D incoherent holographic microscopy}}, url = {http://ieeexplore.ieee.org/document/7532499/}, volume = {2016-Augus}, year = {2016} }
@inproceedings{Wael2016, abstract = {In this work we estimate Super Resolution (SR) images from a sequence of true color Compressed Sensing (CS) observations. The red, green, blue (RGB) channels are sensed separately using a measurement matrix that can be synthesized practically. The joint optimization problem to estimate the registration parameters, and the High Resolution (HR) image is transformed into a sequence of unconstrained optimization sub-problems using the Alternate Direction Method of Multipliers (ADMM). A new, simple, and accurate, image registration procedure is proposed. The performed experiments show that the proposed method compares favorably to existing color CS reconstruction methods at unity zooming factor (P), obtaining very good performance varying P and the compression factor simultaneously. The algorithm is tested on real and synthetic images.}, author = {Saafin, Wael and Vega, Miguel and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {2016 24th European Signal Processing Conference (EUSIPCO)}, doi = {10.1109/EUSIPCO.2016.7760511}, isbn = {978-0-9928-6265-7}, issn = {22195491}, keywords = {Color images,Compressed Sensing,Image enhancement,Image reconstruction,Super Resolution}, month = {aug}, pages = {1563--1567}, publisher = {IEEE}, title = {{Compressed sensing super resolution of color images}}, url = {http://ieeexplore.ieee.org/document/7760511/}, volume = {2016-Novem}, year = {2016} }
@inproceedings{Morteza2016, abstract = {Phonocardiogram (PCG) signal is used as a diagnostic test in ambulatory monitoring in order to evaluate the heart hemodynamic status and to detect a cardiovascular disease. The objective of this study is to develop an automatic classification method for anomaly (normal vs. abnormal) and quality (good vs. bad) detection of PCG recordings without segmentation. For this purpose, a subset of 18 features is selected among 40 features based on a wrapper feature selection scheme. These features are extracted from time, frequency, and time-frequency domains without any segmentation. The selected features are fed into an ensemble of 20 feedforward neural networks for classification task. The proposed algorithm achieved the overall score of 91.50% (94.23% sensitivity and 88.76% specificity) and 85.90% (86.91% sensitivity and 84.90% specificity) on the train and unseen test datasets, respectively. The proposed method got the second best score in the PhysioNet/CinC Challenge 2016.}, author = {Zabihi, Morteza and {Bahrami Rad}, Ali and Kiranyaz, Serkan and Gabbouj, Moncef and {K. Katsaggelos}, Aggelos}, booktitle = {Computing in Cardiology}, doi = {10.22489/CinC.2016.180-213}, isbn = {9781509008964}, issn = {2325887X}, month = {sep}, pages = {613--616}, title = {{Heart Sound Anomaly and Quality Detection using Ensemble of Neural Networks without Segmentation}}, url = {http://www.cinc.org/archives/2016/pdf/180-213.pdf}, volume = {43}, year = {2016} }
@inproceedings{Lina, author = {Lina, Karam and Aggelos, Katsaggelos and Fernando, Pereira}, booktitle = {2016 IEEE International Conference on Image Processing (ICIP)}, doi = {10.1109/ICIP.2016.7532302}, isbn = {978-1-4673-9961-6}, month = {sep}, pages = {iv--iv}, publisher = {IEEE}, title = {{Organizing committee}}, url = {http://ieeexplore.ieee.org/document/7532302/}, year = {2016} }
@inproceedings{Baena-Galle2015, author = {{Roberto Baena-Gall{\'{e}}} and Gladysz, Szymon and Gladysz, Szymon and Baena-Gall{\'{e}}, Roberto and Gladysz, Szymon and Gladysz, Szymon}, booktitle = {Proceedings of the Advanced Maui Optical and Space Surveillance Technologies Conference}, title = {{Anisoplanatic imaging through turbulence using principal component analysis}}, url = {http://adsabs.harvard.edu/abs/2015amos.confE...1B}, year = {2015} }
@inproceedings{Panos, author = {Panos, M Pardalos and Dimitri, Bertsekas and Ferhan, M Atici and Anastassios, Venetsanopoulos and Ravi, P Agarwal and Feliz, Minhos and Mihai, Mihailescu and Aggelos, Katsaggelos and Alberto, Parmeggiani and Abraham, Bers and Et al.}, booktitle = {2015 Second International Conference on Mathematics and Computers in Sciences and in Industry (MCSI)}, doi = {10.1109/MCSI.2015.7}, isbn = {978-1-4799-8673-6}, month = {aug}, pages = {xiii--xiv}, publisher = {IEEE}, title = {{Program Committee}}, url = {http://ieeexplore.ieee.org/document/7423931/}, year = {2015} }
@inproceedings{Leonidas2015, abstract = {In this work, we compare the performance of previously proposed ultra-miniature diffraction gratings with ideal lenses and zone plates of similar structural characteristics. The analysis aims at understanding the differences of designs utilizing non-focusing gratings and the potential benefits of their use in computational imaging systems.}, address = {Washington, D.C.}, author = {Spinoulas, Leonidas and Cossairt, Oliver and Katsaggelos, Aggelos K. and Gill, Patrick R. and Stork, David G.}, booktitle = {Imaging and Applied Optics 2015}, doi = {10.1364/COSI.2015.CM3E.1}, isbn = {978-1-943580-00-2}, pages = {CM3E.1}, publisher = {OSA}, title = {{Performance Comparison of Ultra-Miniature Diffraction Gratings with Lenses and Zone Plates}}, url = {https://opg.optica.org/abstract.cfm?URI=COSI-2015-CM3E.1}, year = {2015} }
@inproceedings{Qiqin2015, author = {Dai, Qiqin and Yoo, Seunghwan and Kappeler, Armin and Katsaggelos, Aggelos K.}, booktitle = {2015 IEEE International Conference on Image Processing (ICIP)}, doi = {10.1109/ICIP.2015.7350764}, isbn = {978-1-4799-8339-1}, month = {sep}, pages = {83--87}, publisher = {IEEE}, title = {{Dictionary-based multiple frame video super-resolution}}, url = {http://ieeexplore.ieee.org/document/7350764/}, year = {2015} }
@inproceedings{Leonidas2015a, abstract = {In this paper, we consider the problem of on-chip temporal compressive sensing for video reconstruction at high frame-rates without the need of any additional optical components. We devise an optimization scheme in order to achieve adequate spatio-temporal sampling of subsequent frames under maximal capturing speed, based on the bandwidth constraints of a sensor. We test this optimization strategy on a commercially available camera and propose a set of reconstruction steps that can achieve reasonable performance but, at the same time, accommodate high-resolution video reconstruction under realistic time requirements. Our analysis constitutes a set of first steps bringing high-speed compressive video capture within the realm of commercial availability.}, author = {Spinoulas, Leonidas and Cossairt, Oliver and Katsaggelos, Aggelos K.}, booktitle = {2015 IEEE International Conference on Image Processing (ICIP)}, doi = {10.1109/ICIP.2015.7351420}, isbn = {978-1-4799-8339-1}, issn = {15224880}, keywords = {CMOS sensor,Sampling optimization,compressive sensing,high-speed video}, month = {sep}, pages = {3329--3333}, publisher = {IEEE}, title = {{Sampling optimization for on-chip compressive video}}, url = {http://ieeexplore.ieee.org/document/7351420/}, volume = {2015-Decem}, year = {2015} }
@inproceedings{Arun2015, abstract = {Efficient streaming of video over wireless networks requires real-time assessment of distortion due to packet loss, especially because predictive coding at the encoder can cause inter-frame propagation of errors and impact the overall quality of the transmitted video. This paper presents an algorithm to evaluate the expected receiver distortion on the source side by utilizing encoder information, transmission channel characteristics and error concealment. Specifically, distinct video transmission units, Group of Blocks (GOBs), are iteratively built at the source by taking into account macroblock coding modes and motion-compensated error concealment for three different combinations of packet loss. Distortion of these units is then calculated using the structural similarity (SSIM) metric and they are stochastically combined to derive the overall expected distortion. The proposed model provides a more accurate estimate of the distortion that closely models quality as perceived through the human visual system. When incorporated into a content-aware utility function, preliminary experimental results show improved packet ordering & scheduling efficiency and overall video signal at the receiver.}, author = {Sankisa, Arun and Katsaggelos, A.K. and Pahalawatta, Peshala V.}, booktitle = {2015 IEEE International Symposium on Multimedia (ISM)}, doi = {10.1109/ISM.2015.88}, isbn = {978-1-5090-0379-2}, keywords = {Video quality assessment,cross-layer optimization,motion-compensation,packet scheduling,structural similarity}, month = {dec}, pages = {513--518}, publisher = {IEEE}, title = {{Distortion Estimation Using Structural Similarity for Video Transmission over Wireless Networks}}, url = {http://ieeexplore.ieee.org/document/7442388/}, year = {2015} }
@inproceedings{Wael2015a, author = {Saafin, Wael and Vega, Miguel and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {2015 IEEE International Conference on Image Processing (ICIP)}, doi = {10.1109/ICIP.2015.7351611}, isbn = {978-1-4799-8339-1}, month = {sep}, pages = {4268--4272}, publisher = {IEEE}, title = {{Image super-resolution from compressed sensing observations}}, url = {http://ieeexplore.ieee.org/document/7351611/}, year = {2015} }
@inproceedings{Oliver2015, abstract = {Starting in the 1890s the artist Paul Gauguin (1848-1903) created a series of prints and transfer drawings using techniques that are not entirely understood. To better understand the artist's production methods, photometric stereo was used to assess the surface shape of a number of these graphic works that are now in the collection of the Art Institute of Chicago. Photometric stereo uses multiple images of Gauguin's graphic works captured from a fixed camera position, lit from multiple specific angles to create an interactive composite image that reveals textural characteristics. These active images reveal details of sequential media application upon experimental printing matrices that help resolve longstanding art historical questions about the evolution of Gauguin's printing techniques. Our study promotes the use of photometric stereo to capitalize on the increasing popularity of Reflectance Transformation Imaging (RTI) among conservators in the world's leading museums.}, author = {Cossairt, Oliver and {Xiang Huang} and Matsuda, Nathan and Stratis, Harriet and Broadway, Mary and Tumblin, Jack and Bearman, Greg and Doehne, Eric and Katsaggelos, Aggelos and Walton, Marc}, booktitle = {2015 Digital Heritage}, doi = {10.1109/DigitalHeritage.2015.7419447}, isbn = {978-1-5090-0254-2}, keywords = {Gauguin,photometric stereo,printmaking techniques,quantitative surface shape measurement,reflectance transformation imaging,transfer drawings}, month = {sep}, pages = {13--20}, publisher = {IEEE}, title = {{Surface shape studies of the art of Paul Gauguin}}, url = {http://ieeexplore.ieee.org/document/7419447/}, volume = {2}, year = {2015} }
@inproceedings{Guido1996d, abstract = {In this paper we present a theory for the optimal bit allocation among quad-tree (QT) segmentation, displacement vector field (DVF) and displaced frame difference (DFD). The theory is applicable to variable block size motion compensated video coders (VBSMCVC), where the variable block sizes are encoded using the QT structure, the DVF is encoded by first order differential pulse code modulation (DPCM), the DFD is encoded by a block based scheme and an additive distortion measure is employed. We consider the case of a lossless VBSMCVC first, for which we develop the optimal bit allocation algorithm using Dynamic Programming (DP). We then consider a lossy VBSMCVC, for which we use La-grangian relaxation and show how an iterative scheme, which employees the DP-based solution, can be used to find the optimal solution. We finally present a VBSMCVC, which is based on the proposed theory, which employees a DCT-based DFD encoding scheme. We compare the proposed coder with H.263. The results show that it outperforms H.263 by about 25% in terms of bit rate for the same quality reconstructed image.}, author = {Schuster, Guido M. and Katsaggelos, Aggelos K.}, booktitle = {European Signal Processing Conference}, issn = {22195491}, pages = {1--4}, title = {{A very low bit-rate video codec with optimal trade-off among DVF, DFD and segmentation}}, year = {2015} }
@inproceedings{Leonidas2015b, abstract = {The maximum achievable frame-rate for a video camera is limited by the sensor's pixel readout rate. The same sensor may achieve either a slow frame-rate at full resolution (e.g., 60 fps at 4 Mpixel resolution) or a fast frame-rate at low resolution (e.g., 240 fps at 1 Mpixel resolution). Higher frame-rates are achieved using pixel readout modes (e.g., subsampling or binning) that sacrifice spatial for temporal resolution within a fixed bandwidth. A number of compressive video cameras have been introduced to overcome this fixed bandwidth constraint and achieve high frame-rates without sacrificing spatial resolution. These methods use electro-optic components (e.g., LCoS, DLPs, piezo actuators) to introduce high speed spatio-temporal multiplexing in captured images. Full resolution, high speed video is then restored by solving an undetermined system of equations using a sparse regularization framework. In this work, we introduce the first all-digital temporal compressive video camera that uses custom subsampling modes to achieve spatio-temporal multiplexing. Unlike previous compressive video cameras, ours requires no additional optical components, enabling it to be implemented in a compact package such as a mobile camera module. We demonstrate results using a TrueSense development kit with a 12 Mpixel sensor and programmable FPGA read out circuitry.}, author = {Spinoulas, Leonidas and He, Kuan and Cossairt, Oliver and Katsaggelos, Aggelos}, booktitle = {2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)}, doi = {10.1109/CVPRW.2015.7301375}, isbn = {978-1-4673-6759-2}, issn = {21607516}, keywords = {Cameras,Compressed sensing,Image reconstruction,Registers,Spatial resolution,Video sequences}, month = {jun}, pages = {49--57}, publisher = {IEEE}, title = {{Video compressive sensing with on-chip programmable subsampling}}, url = {http://ieeexplore.ieee.org/document/7301375/}, volume = {2015-Octob}, year = {2015} }
@inproceedings{Wael2015, abstract = {In this paper we propose a novel optimization framework to obtain High Resolution (HR) Passive Millimeter Wave (P-MMW) images from multiple Low Resolution (LR) observations captured using a simulated Compressed Sensing (CS) imaging system. The proposed CS Super Resolution (CSS-R) approach combines existing CS reconstruction algorithms with the use of Super Gaussian (SG) regularization terms on the image to be reconstructed, smoothness constraints on the registration parameters to be estimated and the use of the Alternate Direction Methods of Multipliers (ADMM) to link the CS and SR problems. The image estimation subproblem is solved using Majorization-Minimization (MM), registration is tackled minimizing a quadratic function and CS reconstruction is approached as an l1-minimization problem subject to a quadratic constraint. The performed experiments, on simulated and real PMMW observations, validate the used approach.}, author = {Saafin, Wael and Villena, Salvador and Vega, Miguel and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {2015 23rd European Signal Processing Conference (EUSIPCO)}, doi = {10.1109/EUSIPCO.2015.7362697}, isbn = {978-0-9928-6263-3}, keywords = {Passive millimeter-wave,compressive sensing,image restoration,super resolution}, month = {aug}, pages = {1815--1819}, publisher = {IEEE}, title = {{PMMW image super resolution from compressed sensing observations}}, url = {http://ieeexplore.ieee.org/document/7362697/}, year = {2015} }
@inproceedings{maqueda2015fast, abstract = {Millimeter Wave (MMW) imaging systems are currently being used to detect hidden threats. Unfortunately the current performance of detection algorithms is very poor due to the presence of severe noise, the low resolution of MMW images and, in general, the poor quality of the acquired images. In this paper we present a new real time MMW threat detection algorithm based on a tailored de-noising, body and threat segmentation, and threat detection process that outperforms currently existing detection procedures. A complete comparison with a state of art threat detection algorithm is presented in the experimental section.}, author = {Maqueda, I. Gomez and de la Blanca, N. Perez and Molina, R. and Katsaggelos, A. K.}, booktitle = {2015 23rd European Signal Processing Conference (EUSIPCO)}, doi = {10.1109/EUSIPCO.2015.7362453}, isbn = {978-0-9928-6263-3}, keywords = {Millimeter wave imaging,Security,image processing}, month = {aug}, organization = {IEEE}, pages = {599--603}, publisher = {IEEE}, title = {{Fast millimeter wave threat detection algorithm}}, url = {http://ieeexplore.ieee.org/document/7362453/}, year = {2015} }
@inproceedings{Qiqin2014, abstract = {This paper presents a novel directionally adaptive cubic-spline interpolation method which is applicable to mobile camera digital zoom systems. The problems of conventional (linear and cubic-spline) and advanced interpolation exhibit blurring and jagging artifacts in the digitally zoomed image. To solve this problem, the proposed method performs directionally adaptive interpolation using the optimal interpolation kernel according to the edge orientation. Experimental results show that the proposed method successfully enlarges images with reduced interpolation artifacts compared with both conventional and advanced interpolation methods. Objective evaluation reveals that the proposed method gives higher peak signal to noise ratio (PSNR) and structural similarity (SSIM) figures. {\textcopyright} 2014 IEEE.}, author = {Dai, Qiqin and Katsaggelos, Aggelos K. and Yu, Soohwan and Kang, Wonseok and Jeon, Jaehwan and Paik, Joonki}, booktitle = {The 18th IEEE International Symposium on Consumer Electronics (ISCE 2014)}, doi = {10.1109/ISCE.2014.6884434}, isbn = {978-1-4799-4592-4}, keywords = {digital zooming,directionally adaptive interpolation,interpolation kernel estimation}, month = {jun}, pages = {1--2}, publisher = {IEEE}, title = {{Directionally adaptive cubic-spline interpolation using optimized interpolation kernel and edge orientation for mobile digital zoom system}}, url = {https://ieeexplore.ieee.org/document/6884434}, year = {2014} }
@inproceedings{Michael2014, abstract = {In this paper we present a novel approach to face recognition. We propose an adaptation and extension to the state-of-the-art methods in face recognition, such as sparse representation-based classification and its extensions. Effectively, our method combines the sparsity-based approaches with additional least-squares steps and exhitbits robustness to outliers achieving significant performance improvement with little additional cost. This approach also mitigates the need for a large number of training images since it proves robust to varying number of training samples.}, author = {Iliadis, Michael and Spinoulas, Leonidas and Berahas, Albert S. and Wang, Haohong and Katsaggelos, Aggelos K.}, booktitle = {European Signal Processing Conference}, isbn = {9780992862619}, issn = {22195491}, keywords = {Face recognition,classification,sparse representation}, pages = {526--530}, title = {{Sparse representation and least squares-based classification in face recognition}}, year = {2014} }
@inproceedings{Miguel2014, author = {Miguel, Vega and Rafael, Molina and Aggelos, K Katsaggelos}, booktitle = {2014 22nd European Signal Processing Conference (EUSIPCO)}, pages = {1632--1636}, title = {{Parameter estimation in Bayesian blind deconvolution with super Gaussian image priors}}, year = {2014} }
@inproceedings{AliBahrami2015, author = {Rad, Ali Bahrami and Zabihi, Morteza and Katsaggelos, Aggelos and Kiranyaz, Serkan and Gabbouj, Moncef Gabbouj}, booktitle = {International IEEE/EMBS Conference on Neural Engineering}, keywords = {Brain-computer/machine interface}, pages = {2014}, title = {{A Novel P300-Speller Error Detection Approach in Brain-Computer Interface}}, volume = {277}, year = {2014} }
@inproceedings{Xu2014, abstract = {Iteratively reweighted least squares (IRLS) is one of the most effective methods to minimize the lp regularized linear inverse problem. Unfortunately, the regularizer is nonsmooth and nonconvex when 0 < p < 1. In spite of its properties and mainly due to its high computation cost, IRLS is not widely used in image deconvolution and reconstruction. In this paper, we first derive the IRLS method from the perspective of majorization minimization and then propose an Alternating Direction Method of Multipliers (ADMM) to solve the reweighted linear equations. Interestingly, the resulting algorithm has a shrinkage operator that pushes each component to zero in a multiplicative fashion. Experimental results on both image deconvolution and reconstruction demonstrate that the proposed method outperforms state-of-the-art algorithms in terms of speed and recovery quality.}, author = {Zhou, Xu and Molina, Rafael and Zhou, Fugen and Katsaggelos, Aggelos K.}, booktitle = {2014 IEEE International Conference on Image Processing (ICIP)}, doi = {10.1109/ICIP.2014.7025357}, isbn = {978-1-4799-5751-4}, keywords = {Image restoration,compressive sensing,image reconstruction,iteratively reweighted least squares,nonconvex nonsmooth regularization}, month = {oct}, pages = {1783--1787}, publisher = {IEEE}, title = {{Fast iteratively reweighted least squares for lp regularized image deconvolution and reconstruction}}, url = {http://ieeexplore.ieee.org/document/7025357/}, year = {2014} }
@inproceedings{Seunghwan2014, abstract = {This paper presents a video completion algorithm using block matching for video stabilization. In order to fill in missing pixels, the proposed algorithm consists of three steps: i) mosaicking for covering the missing static, planar regions, ii) estimation of local motion vectors using the hierarchical Lucas-Kanade optical flow method, and iii) selection of the most similar patch in both spatial and temporal neighbors. The proposed video completion algorithm can be applied in the wide areas of consumer electronics including camcorders, smart phone cameras, tablet cameras, and smart glasses. {\textcopyright} 2014 IEEE.}, author = {Yoo, Seunghwan and Katsaggelos, Aggelos K. and Jo, Gwanghyun and Chae, Eunjung and Cheong, Hejin and Jeon, Semi and Kim, Minseo and Paik, Joonki and Park, Chanyong}, booktitle = {The 18th IEEE International Symposium on Consumer Electronics (ISCE 2014)}, doi = {10.1109/ISCE.2014.6884435}, isbn = {978-1-4799-4592-4}, keywords = {block matching,motion inpainting,video completion,video stabilization}, month = {jun}, pages = {1--2}, publisher = {IEEE}, title = {{Video completion using block matching for video stabilization}}, url = {https://ieeexplore.ieee.org/document/6884435}, year = {2014} }
@inproceedings{Leonidas2014, abstract = {This paper presents a defocus-invariant image registration method for measuring the shifting value between two differently located patterns in an imaging sensor. Existing registration methods fail with unfocused images since features or regions of interest are degraded by defocus. In order to solve this problem, the proposed method consists of three stages: i) pre-generation of the set of point spread functions (PSFs) estimated in different focusing positions, ii) the geometric transformation estimation using estimated PSF data, and iii) registration using estimated transformation matrix. The proposed method improves out-of-focus degradation through estimation of PSF. For this reason, the proposed method can accurately estimate the difference of phase between two out-of-focus images. Furthermore, it can be applied to phase-difference detection auto focusing, and provide accurate auto focusing performance. {\textcopyright} 2014 IEEE.}, author = {Spinoulas, Leonidas and Katsaggelos, Aggelos K. and Jang, Jinbeum and Yoo, Yoonjong and Im, Jaehyun and Paik, Joonki}, booktitle = {The 18th IEEE International Symposium on Consumer Electronics (ISCE 2014)}, doi = {10.1109/ISCE.2014.6884378}, isbn = {978-1-4799-4592-4}, keywords = {constrained least square filter,elastic registration,floating values,phase difference detection auto focus}, month = {jun}, pages = {1--2}, publisher = {IEEE}, title = {{Defocus-invariant image registration for phase-difference detection auto focusing}}, url = {https://ieeexplore.ieee.org/document/6884378}, year = {2014} }
@inproceedings{Pablo2014a, abstract = {Many real classification tasks are oriented to sequence (neighbor) labeling, that is, assigning a label to every sample of a signal while taking into account the sequentiality (or neighborhood) of the samples. This is normally approached by first filtering the data and then performing classification. In consequence, both processes are optimized separately, with no guarantee of global optimality. In this work we utilize Bayesian modeling and inference to jointly learn a classifier and estimate an optimal filterbank. Variational Bayesian inference is used to approximate the posterior distributions of all unknowns, resulting in an iterative procedure to estimate the classifier parameters and the filterbank coefficients. In the experimental section we show, using synthetic and real data, that the proposed method compares favorably with other classification/filtering approaches, without the need of parameter tuning.}, author = {Ruiz, Pablo and Mateos, Javier and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {2014 IEEE International Conference on Image Processing (ICIP)}, doi = {10.1109/ICIP.2014.7025589}, isbn = {978-1-4799-5751-4}, keywords = {Gaussian Process classification,analysis representation,filter estimation}, month = {oct}, pages = {2913--2917}, publisher = {IEEE}, title = {{Learning filters in Gaussian process classification problems}}, url = {http://ieeexplore.ieee.org/document/7025589/}, year = {2014} }
@inproceedings{Zhaofu2014, abstract = {In this paper we consider the problem of recovering temporally smooth or correlated sparse signals from a set of undersampled measurements. We propose two algorithmic solutions that exploit the signal temporal properties to improve the reconstruction accuracy. The effectiveness of the proposed algorithms is corroborated with experimental results.}, author = {Chen, Zhaofu and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {European Signal Processing Conference}, isbn = {9780992862619}, issn = {22195491}, keywords = {Sparse signal recovery,convex relaxation method,greedy algorithm,multiple measurement}, pages = {451--455}, title = {{Recovery of correlated sparse signals from under-sampled measurements}}, year = {2014} }
@inproceedings{Pablo2014, abstract = {In this paper we utilize Bayesian modeling and inference to learn a softmax classification model which performs Supervised Classification and Active Learning. For p < 1, lp-priors are used to impose sparsity on the adaptive parameters. Using variational inference, all model parameters are estimated and the posterior probabilities of the classes given the samples are calculated. A relationship between the prior model used and the independent Gaussian prior model is provided. The posterior probabilities are used to classify new samples and to define two Active Learning methods to improve classifier performance: Minimum Probability and Maximum Entropy. In the experimental section the proposed Bayesian framework is applied to Image Segmentation problems on both synthetic and real datasets, showing higher accuracy than state-of-the-art approaches.}, author = {Ruiz, Pablo and {De La Blanca}, Nicol{\'{a}}s P{\'{e}}rez and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {European Signal Processing Conference}, isbn = {9780992862619}, issn = {22195491}, pages = {1183--1187}, title = {{Bayesian classification and active learning using lp-priors. Application to image segmentation}}, year = {2014} }
@inproceedings{cho2013real, author = {Cho, W and Cheong, Hejin and Chae, Eunjung and Lee, Eunsung and Katsaggelos, Aggelos K and Paik, Joonki}, booktitle = {Proceedings of the International Technical Conference on Circuits/Systems, Computers and communications (ITC-CSCC)}, title = {{Real-time image restoration using adaptive truncated constrained least-squares (TCLS) filter based on blur estimation}}, year = {2013} }
@inproceedings{xin2013spectral, abstract = {In a variety of problems, objects are represented as a collection of feature points fk and their spatial positions pk. In some cases, feature points doesn't carry enough discriminating information to identify objects so as to raise the question of point set verification, i.e., matching two point sets to identify whether they are match or not. Point set verification problem involves two challenges. The first challenge is to identify a one-to-one mapping between two point sets and the second is to measure the similarity between the two aligned point sets. The first challenge is a well-known one-to-one mapping problem in computer vision with a combinatorial nature and computationally expensive. However, we are able to avoid the computation of one-to-one mapping by directly giving a matching similarity score. The second challenge is attacked with lots of solutions, which shares two disadvantages, i.e., sensitive to both outliners and affine transform. These two challenges are solved simultaneously by our eigenvalue approximation solution. In this work, the point sets are modeled as affinity matrix and the distances between affinity matrices of two point sets are lower bounded by eigenvalue distance. This affinity representation is invariant to scale, translation and rotation and insensitive to outliners and affine transforms. Experiments on both synthetic data and real data shows that this method outperforms both statistics based and geometry based methods. {\textcopyright} 2013 IEEE.}, author = {Xin, Xin and Li, Zhu and {Zhan Ma} and Katsaggelos, Aggelos K.}, booktitle = {2013 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)}, doi = {10.1109/ICMEW.2013.6618283}, isbn = {978-1-4799-1604-7}, keywords = {Affinity matrix,Spectral Analysis,Topology Verification,Visual Search}, month = {jul}, organization = {IEEE}, pages = {1--4}, publisher = {IEEE}, title = {{Spectral approximation to point set similarity metric}}, url = {http://ieeexplore.ieee.org/document/6618283/}, year = {2013} }
@inproceedings{Yun2013b, abstract = {This paper presents a multi-camera motion capture system aiming to provide caregivers with timely access to the patient's health status through mobile communication devices. The major components include video capture, object detection, video coding and transmission, error concealment, and video analysis. Our contribution is twofold. First, several novel ideas are developed, including fast object detection, and content-aware and adaptive video coding and transmission. Second, all components are seamlessly integrated in a unified optimization framework dedicated for online data transmission. In the scenario, the subject walked on a treadmill with four tripod cameras capturing the video from different viewpoints. After video compression and transmission over a wireless sensor network, the remote receiver recovered the videos and performed multi-view motion capture for gait analysis. Experimental results show that the presented system design achieves better video quality than traditional video coding and transmission scheme, while the requirement for a low-cost, noninvasive and real-time healthcare monitoring system is accommodated. {\textcopyright} 2013 IEEE.}, author = {Ye, Yun and Ci, Song and Katsaggelos, Aggelos K. and Liu, Yanwei}, booktitle = {2013 IEEE International Conference on Multimedia and Expo (ICME)}, doi = {10.1109/ICME.2013.6607566}, isbn = {978-1-4799-0015-2}, issn = {19457871}, keywords = {Healthcare monitoring,multi-view motion capture,object detection,video coding and transmission,wireless communications}, month = {jul}, pages = {1--6}, publisher = {IEEE}, title = {{A multi-camera motion capture system for remote healthcare monitoring}}, url = {http://ieeexplore.ieee.org/document/6607566/}, year = {2013} }
@inproceedings{Aggelos2013, abstract = {In this paper, we summarize our recent results on simultaneous compressive sensing reconstruction and blind deconvolution of images, captured by a compressive imaging system introducing degradation of the captured scene by an unknown point spread function. {\textcopyright} OSA 2013.}, address = {Washington, D.C.}, author = {Katsaggelos, Aggelos K. and Spinoulas, Leonidas and Amizic, Bruno and Molina, Rafael}, booktitle = {Imaging and Applied Optics}, doi = {10.1364/COSI.2013.CM2C.1}, isbn = {978-1-55752-975-6}, issn = {21622701}, pages = {CM2C.1}, publisher = {OSA}, title = {{Compressive Sensing and Blind Image Deconvolution}}, url = {https://opg.optica.org/abstract.cfm?URI=COSI-2013-CM2C.1}, year = {2013} }
@inproceedings{Michael2013, abstract = {This paper proposes a Content Based Image Retrieval (CBIR) application for searching landmarks and buildings in a city using a smartphone. A user can snap a picture of the building using his smartphone. The application is able to quickly and accurately find the name of the building along with many other interesting information, such as the history of the building and its Wi-Fi availability. We present a novel client-server CBIR application that combines Laplacian-SIFT for feature descriptor, multiple kd-trees for indexing and two levels of geometric verification. We present back-end and front-end Application Programming Interfaces (API) for client-server CBIR applications and we propose a distributed system architecture to support multiple client requests. The application consists of two user interfaces, a web interface and a mobile interface. Image retrieval results demonstrate the accuracy of the system in recognizing buildings. {\textcopyright} 2013 IEEE.}, author = {Iliadis, Michael and {Seunghwan Yoo} and Xin, Xin and Katsaggelos, Aggelos K.}, booktitle = {2013 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)}, doi = {10.1109/ICMEW.2013.6618285}, isbn = {978-1-4799-1604-7}, keywords = {image features,image retrieval system,image similarity,indexing,visual search}, month = {jul}, pages = {1--4}, publisher = {IEEE}, title = {{Virtual touring: A Content Based Image Retrieval application}}, url = {http://ieeexplore.ieee.org/document/6618285/}, year = {2013} }
@inproceedings{Pablo2013, abstract = {In this paper we deal with the problem of acquiring a scene light field using a programmable coded aperture camera when the angular observations are out-of-focus. We describe a portable programmable coded aperture prototype that can be attached to any DSLR camera lens and propose a blind deconvolution method to deblur light fields. The performance of the proposed method is evaluated on synthetic and real images. {\textcopyright} 2013 EURASIP.}, author = {Ruiz, P. and Mateos, J. and Cardenas, M. C. and Nakajima, S. and Molina, R. and Katsaggelos, A. K.}, booktitle = {European Signal Processing Conference}, isbn = {9780992862602}, issn = {22195491}, keywords = {Computational photography,blurred observations,light field,programmable coded aperture camera}, pages = {1--5}, title = {{Light field acquisition from blurred observations using a programmable coded aperture camera}}, year = {2013} }
@inproceedings{Michael2013a, abstract = {Compressive Sensing (CS) suggests that, under certain conditions, a signal can be reconstructed using a small number of incoherent measurements. We propose a novel video CS framework based on Multiple Measurement Vectors (MMV) which is suitable for signals with temporal correlation such as video sequences. In addition, a CS circulant matrix is employed for fast reconstruction. Furthermore, the proposed framework allows the number of CS measurements associated with each frame to be chosen in the decoder rather than the encoder offering robustness compared to the multi-scale approaches. Experimental results on two video sequences exhibiting fast motion and occlusions, show the advantages of the proposed method over the current state-of-the-art in video CS. {\textcopyright} 2013 IEEE.}, author = {Iliadis, Michael and Watt, Jeremy and Spinoulas, Leonidas and Katsaggelos, Aggelos K.}, booktitle = {2013 IEEE International Conference on Image Processing}, doi = {10.1109/ICIP.2013.6738029}, isbn = {978-1-4799-2341-0}, keywords = {Video compressive sensing,circulant matrix,fast motion,multiple measurement vectors}, month = {sep}, pages = {136--140}, publisher = {IEEE}, title = {{Video compressive sensing using multiple measurement vectors}}, url = {http://ieeexplore.ieee.org/document/6738029/}, year = {2013} }
@inproceedings{Wonseok2013a, abstract = {In this paper, we present a compressive sensing-based image denoising algorithm using spatially adaptive image representation and estimation of optimal error tolerance based on sparse signal analysis. The proposed method performs block-based multiple compressive sampling after decomposing the sparse signal into feature and non-feature regions using simple statistical analysis. For minimization of recovery error and number of iterations, the modified OMP method estimates the optimal error tolerance using the average variance in the recovery step. Experimental results demonstrate that the proposed denoising algorithm better removes noise without undesired artifacts than existing state-of-the-art methods in terms of both objective (PSNR/SSIM) and subjective measures. Processing time of the proposed method is 5 to 10 times faster than the standard OMP-based method. {\textcopyright} 2013 IEEE.}, author = {Kang, Wonseok and Lee, Eunsung and Chea, Eunjung and Katsaggelos, Aggelos K. and Paik, Joonki}, booktitle = {2013 IEEE International Conference on Acoustics, Speech and Signal Processing}, doi = {10.1109/ICASSP.2013.6638106}, isbn = {978-1-4799-0356-6}, issn = {15206149}, keywords = {Compressed sensing,image denoising,matching pursuit algorithms}, month = {may}, pages = {2503--2507}, publisher = {IEEE}, title = {{Compressive sensing-based image denoising using adaptive multiple sampling and optimal error tolerance}}, url = {http://ieeexplore.ieee.org/document/6638106/}, year = {2013} }
@inproceedings{Wonseok2013, abstract = {This paper presents a novel real-time super-resolution (SR) method using directionally adaptive image interpolation and image restoration. The proposed interpolation method estimates the edge orientation using steerable filters and performs edge refinement along the estimated edge orientation. Bi-linear and bi-cubic interpolation filters are then selectively used according to the estimated edge orientation for reducing jagging artifacts in slanting edge regions. The proposed restoration method can effectively remove image degradation caused by interpolation using the directionally adaptive truncated constrained least-squares (TCLS) filter. The proposed method provides high-quality magnified images which are similar to or better than the result of advanced interpolation or SR methods without high computational load. Experimental results indicate that the proposed system gives higher peak-to-peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) values than the state-of-the-art image interpolation methods. {\textcopyright} 2013 IEEE.}, author = {Kang, Wonseok and Jeon, Jaehwan and Lee, Eunsung and Cho, Changhun and Jung, Junghoon and Kim, Taechan and Katsaggelos, Aggelos K. and Paik, Joonki}, booktitle = {2013 IEEE International Conference on Image Processing}, doi = {10.1109/ICIP.2013.6738270}, isbn = {978-1-4799-2341-0}, keywords = {Super-resolution,digital zooming,image interpolation,image restoration}, month = {sep}, pages = {1311--1315}, publisher = {IEEE}, title = {{Real-time super-resolution for digital zooming using finite kernel-based edge orientation estimation and truncated image restoration}}, url = {http://ieeexplore.ieee.org/document/6738270/}, year = {2013} }
@inproceedings{kim2013image, author = {Kim, S and Cho, C and Jeon, Jaehwan and Katsaggelos, Aggelos and Paik, Joonki}, booktitle = {Proceedings of the International Technical Conference on Circuits/Systems, Computers and communications (ITC-CSCC)}, title = {{Image restoration using vaguelette-curvelet decomposition}}, year = {2013} }
@inproceedings{Hiram2013, abstract = {In this paper a new combination of image priors is introduced and applied to Bayesian image restoration. Total Variation (TV) image prior preserves edge structure while imposing smoothness on the solutions. However, it does not perform well in textured areas. To alleviate this problem we propose to combine TV with the Poisson Singular Integral (PSI) image prior, which is able to preserve image textures. The proposed method utilizes a bound for the TV image model based on the majorization-minimization principle, and performs maximum a posteriori Bayesian inference. In the experimental section the proposed approach is tested on synthetically degraded images with different levels of spatial activity and areas with different types of texture. Since the proposed method depends on a set of parameters, an analysis, about their impact on the final restorations, is carried out. {\textcopyright} 2013 EURASIP.}, author = {Madero-Orozco, Hiram and Ruiz, Pablo and Mateos, Javier and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {European Signal Processing Conference}, isbn = {9780992862602}, issn = {22195491}, keywords = {Bayesian image restoration,Deblurring,Poisson Singular Integral,Total Variation}, pages = {1--5}, title = {{Image deblurring combining poisson singular integral and total variation prior models}}, year = {2013} }
@inproceedings{Jorge2013, abstract = {In this paper a general combination of sparse image priors is applied to Bayesian Compressed Sensing (CS) reconstruction of digital images. A simultaneous deblurring and CS reconstruction variational algorithm is derived. The application of the new algorithm, to both blurred and non-blurred images at different compression ratios, is studied. The new method is applied to Passive Millimeter-Wave Imaging (PMWI) CS. and its performance compared to state of the art CS reconstruction methods. {\textcopyright} 2013 EURASIP.}, author = {Rubio, Jorge and Vega, Miguel and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {European Signal Processing Conference}, isbn = {9780992862602}, issn = {22195491}, keywords = {Bayesian inference,Bayesian modeling,compressed sensing,image processing,millimeter wave imaging}, pages = {1--5}, title = {{A general sparse image prior combination in Compressed Sensing}}, year = {2013} }
@inproceedings{cho2013wavelet, author = {Cho, W and Park, J and Kim, Donggyun and Jung, J and Kim, T and Katsaggelos, Agggelos and Paik, Joonki}, booktitle = {Proceedings of the International Technical Conference on Circuits/Systems, Computers and communications (ITC-CSCC)}, title = {{Wavelet based super-resolution using local self-examples}}, year = {2013} }
@inproceedings{xin2013robust, abstract = {With the increasing power of mobile headsets and mobile networks, mobile visual search applications have gained popularity and became tractable. One of the key technologies to enable visual search are the robust and compact features, which are extracted from an image and are invariant to recapturing variations. One of the key factors for compact visual descriptors is the selection of local features. The size of the compact visual descriptors and the computational complexities of a visual search system increase with the number of features selected. In this sense, ranking the descriptors extracted from a single image according to their importance in terms of recapturing is very necessary and important. In this paper, we attack this problem by proposing a novel self-matching selection. In this method, we randomly apply an out-of-plane rotation to the target image and match the original features to the features that are extracted from the out-of-plane rotated image. The importance of the features is ranked according to the self-matching score. This method is proven to be better than other peak strength and edge strength based methods by 30% from experiments on a large database. {\textcopyright} 2013 IEEE.}, author = {Xin, Xin and Li, Zhu and Ma, Zhan and Katsaggelos, Aggelos K.}, booktitle = {2013 IEEE International Conference on Image Processing}, doi = {10.1109/ICIP.2013.6738899}, isbn = {978-1-4799-2341-0}, keywords = {compact visual descriptor,mobile visual search,self-matching score}, month = {sep}, organization = {IEEE}, pages = {4363--4366}, publisher = {IEEE}, title = {{Robust feature selection with self-matching score}}, url = {http://ieeexplore.ieee.org/document/6738899/}, year = {2013} }
@inproceedings{amizic2013variational, abstract = {We propose a novel variational Bayesian framework to perform simultaneous compressive sensing (CS) image reconstruction and blind deconvolution (BID) as well as estimate all modeling parameters. Furthermore, we show that the proposed framework generalizes the alternating direction method of multipliers which is often utilized to transform a constrained optimization problem into an unconstrained one through the use of the augmented Lagrangian. The proposed framework can be easily adapted to other signal processing applications or particular image and blur priors within the proposed context. In this work, as an example, we employ the following priors to illustrate the significance of the proposed approach: (1) a non-convex lp quasi-norm based prior for the image, (2) a simultaneous auto-regressive prior for the blur, and (3) an l1 norm based prior for the transformed coefficients. Experimental results using synthetic images demonstrate the advantages of the proposed algorithm over existing approaches. {\textcopyright} 2013 EURASIP.}, author = {Amizic, Bruno and Spinoulas, Leonidas and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {European Signal Processing Conference}, isbn = {9780992862602}, issn = {22195491}, keywords = {Bayesian methods,Inverse methods,blind image deconvolution,compressive sensing,parameter estimation}, organization = {IEEE}, pages = {1--5}, title = {{Variational Bayesian compressive blind image deconvolution}}, year = {2013} }
@inproceedings{Salvador2013, author = {Villena, Salvador and Vega, Miguel and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {2013 18th International Conference on Digital Signal Processing (DSP)}, doi = {10.1109/ICDSP.2013.6622841}, isbn = {978-1-4673-5807-1}, month = {jul}, pages = {1--6}, publisher = {IEEE}, title = {{A general sparse image prior combination in super-resolution}}, url = {http://ieeexplore.ieee.org/document/6622841/}, year = {2013} }
@inproceedings{Jonathan2013, abstract = {This paper introduces a hybrid method for searching large image datasets for approximate nearest neighbor items, specifically SIFT descriptors. The basic idea behind our method is to create a serial system that first partitions approximate nearest neighbors using multiple kd-trees before calling upon locally designed spectral hashing tables for retrieval. This combination gives us the local approximate nearest neighbor accuracy of kd-trees with the computational efficiency of hashing techniques. Experimental results show that our approach efficiently and accurately outperforms previous methods designed to achieve similar goals. {\textcopyright} 2013 IEEE.}, author = {Springer, Jonathan and Xin, Xin and Li, Zhu and Watt, Jeremy and Katsaggelos, Aggelos}, booktitle = {2013 IEEE International Conference on Acoustics, Speech and Signal Processing}, doi = {10.1109/ICASSP.2013.6637938}, isbn = {978-1-4799-0356-6}, issn = {15206149}, keywords = {forest hashing,image retrieval,kd-tree,spectral hashing}, month = {may}, pages = {1681--1684}, publisher = {IEEE}, title = {{Forest hashing: Expediting large scale image retrieval}}, url = {http://ieeexplore.ieee.org/document/6637938/}, year = {2013} }
@inproceedings{Yun2013, abstract = {This paper presents a binocular PTU (pan-tilt unit) camera video object tracking scheme using the MeanShift algorithm and the runtime disparity estimation. The proposed method is to accommodate the requirement of 3D content generation and accurate tracking in more advanced video surveillance applications. The disparity estimation process for each stereoscopic pair is formulated as an energy minimization problem. The iterative solution procedure is implemented in a course-to-fine manner. The estimated disparity is used to scale the tracking window by the MeanShift algorithm, i.e. the size of the tracking area is adjustable according to its inner disparity, and thus the moving object can be better located by the camera. The program maintains the semi-real-time performance and acceptable accuracy as evaluated on a set of standard test data. In our experiment, two PointGrey cameras are controlled through a PTU device. The disparity estimation process on the recorded tracking video (640×480) achieves 6fps on an ordinary PC (2.66GHz CPU, 4GB RAM). {\textcopyright} 2013 IEEE.}, author = {Ye, Yun and Ci, Song and Liu, Yanwei and Wang, Haohong and Katsaggelos, Aggelos K.}, booktitle = {2013 10th IEEE International Conference on Advanced Video and Signal Based Surveillance}, doi = {10.1109/AVSS.2013.6636637}, isbn = {978-1-4799-0703-8}, month = {aug}, pages = {183--188}, publisher = {IEEE}, title = {{Binocular video object tracking with fast disparity estimation}}, url = {http://ieeexplore.ieee.org/document/6636637/}, year = {2013} }
@inproceedings{Fen2013, abstract = {In this paper, we propose a design framework for achieving efficient multimedia multicast services in cognitive radio (CR) networks. The framework incorporates the characteristics of both heterogeneous network environment and the scalable video content. By adopting cooperative transmissions for the delivery of enhancement layer data, we can not only improve the achieved video quality but also protect the rights of subscribed secondary users. We also utilize network coding and superposition coding to achieve efficient multicast transmissions of the layered video packets in multi-channel CR networks. Numerical examples show the proposed framework can improve the average received data rate by up to 15%. When achieving the same video quality, the proposed framework can save 30% transmission time comparing with the scenario using direct transmission alone. {\textcopyright} 2013 IEEE.}, author = {Hou, Fen and Chen, Zhaofu and Huang, Jianwei and Li, Zhu and Katsaggelos, Aggelos K.}, booktitle = {2013 9th International Wireless Communications and Mobile Computing Conference (IWCMC)}, doi = {10.1109/IWCMC.2013.6583723}, isbn = {978-1-4673-2480-9}, keywords = {Cognitive radio network,Cooperative transmission,Multimedia multicast}, month = {jul}, pages = {1175--1180}, publisher = {IEEE}, title = {{Multimedia multicast service provisioning in cognitive radio networks}}, url = {http://ieeexplore.ieee.org/document/6583723/}, year = {2013} }
@inproceedings{Jin2013, abstract = {The rapid advance in three-dimensional (3D) confocal imaging technologies is rapidly increasing the availability of 3D cellular images. However, the lack of robust automated methods for the extraction of cell or organelle shapes from the images is hindering researchers ability to take full advantage of the increase in experimental output. The lack of appropriate methods is particularly significant when the density of the features of interest in high, such as in the developing eye of the fruit fly. Here, we present a novel and efficient nuclei segmentation algorithm based on the combination of graph cut and convex shape prior. The main characteristic of the algorithm is that it segments nuclei foreground using a graph cut algorithm and splits overlapping or touching cell nuclei by simple convex and concavity analysis, using a convex shape assumption for nuclei contour. We evaluate the performance of our method by applying it to a library of publicly-available two-dimensional (2D) images that were hand-labeled by experts. Our algorithm yields a substantial quantitative improvement over other methods for this benchmark. For example, our method achieves a decrease of 3.2 in the Hausdorff distance and an decrease of 1.8 per slice in the merged nuclei error. {\textcopyright} 2013 IEEE.}, author = {Qi, Jin and Wang, B. and Pelaez, N. and Rebay, L. and Carthew, R. W. and Katsaggelos, A. K. and Amaral, L. A. Nunes}, booktitle = {2013 IEEE International Conference on Image Processing}, doi = {10.1109/ICIP.2013.6738138}, isbn = {978-1-4799-2341-0}, keywords = {convex and concavity analysis,drosophila eye,fluorescence microscopy image,graph cut,nuclei segmentation}, month = {sep}, pages = {670--674}, publisher = {IEEE}, title = {{Drosophila eye nuclei segmentation based on graph cut and convex shape prior}}, url = {http://ieeexplore.ieee.org/document/6738138/}, year = {2013} }
@inproceedings{Zhaofu2012, abstract = {In this paper we present a transportation video coding and transmission system specifically tailored to automated vehicle tracking applications. By taking into account the video characteristics and the lossy nature of the wireless channels, we propose error control approaches to enhance tracking accuracy. The proposed system is shown to give performance improvement over the current state-of-the-art system and yields bitrate savings of up to 60%. {\textcopyright} 2012 EURASIP.}, author = {Chen, Zhaofu and Soyak, Eren and Tsaftaris, Sotirios A. and Katsaggelos, Aggelos K.}, booktitle = {European Signal Processing Conference}, isbn = {9781467310680}, issn = {22195491}, keywords = {H.264/AVC,Transportation video,error concealment,forward error control (FEC),object tracking,surveillance centric coding}, pages = {1900--1904}, title = {{Tracking-optimal error control schemes for H.264 compressed video for vehicle surveillance}}, year = {2012} }
@inproceedings{Leonidas2012a, abstract = {The idea of compressive sensing in imaging refers to the reconstruction of an unknown image through a small number of incoherent measurements. Blind deconvolution is the recovery of a sharp version of a blurred image when the blur kernel is unknown. In this paper, we combine these two problems trying to estimate the unknown sharp image and blur kernel solely through the compressive sensing measurements of a blurred image. We present a novel algorithm for simultaneous image reconstruction, restoration and parameter estimation. Using a hierarchical Bayesian modeling followed by an Expectation-Minimization approach we estimate the unknown image, blur and hyperparameters of the global distribution. Experimental results on simulated blurred images support the effectiveness of our method. Moreover, real passive millimeter-wave images are used for evaluating the proposed method as well as strengthening its practical aspects. {\textcopyright} 2012 EURASIP.}, author = {Spinoulas, Leonidas and Amizic, Bruno and Vega, Miguel and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {European Signal Processing Conference}, isbn = {9781467310680}, issn = {22195491}, keywords = {Compressive sensing,bayesian method,blind deconvolution,blur kernel,passive millimeter wave images}, pages = {1414--1418}, title = {{Simultaneous Bayesian compressive sensing and blind deconvolution}}, year = {2012} }
@inproceedings{Evaggelia2012, abstract = {Compressed sensing (CS) theory relies on sparse representations in order to recover signals from an undersampled set of measurements. The sensing mechanism is described by the projection matrix, which should possess certain properties to guarantee high quality signal recovery, using efficient algorithms. Although the major breakthrough in compressed sensing results is obtained for random matrices, recent efforts have shown that CS performance could be improved with optimized non-random projections. Designing matrices that satisfy CS theoretical requirements is closely related to the construction of equiangular tight frames, a problem that has applications in various scientific fields like sparse approximations, coding, and communications. In this paper, we employ frame theory and propose an algorithm for the optimization of the projection matrix that improves sparse signal recovery. {\textcopyright} 2012 EURASIP.}, author = {Tsiligianni, Evaggelia and Kondi, Lisimachos P. and Katsaggelos, Aggelos K.}, booktitle = {European Signal Processing Conference}, isbn = {9781467310680}, issn = {22195491}, keywords = {Compressed sensing,Grassmannian frames,tight frames}, pages = {1439--1443}, title = {{Use of tight frames for optimized compressed sensing}}, year = {2012} }
@inproceedings{amizic2012compressive, abstract = {We propose a novel blind image deconvolution (BID) regularization framework for compressive passive millimeter-wave (PMMW) imaging systems. The proposed framework is based on the variable-splitting optimization technique, which allows us to utilize existing compressive sensing reconstruction algorithms in compressive BID problems. In addition, a non-convex lp quasi-norm with 0 <60; p <60; 1 is employed as a regularization term for the image, while a simultaneous auto-regressive (SAR) regularization term is utilized for the blur. Furthermore, the proposed framework is very general and it can be easily adapted to other state-of-the-art BID approaches that utilize different image/blur regularization terms. Experimental results, obtained with simulations using a synthetic image and real PMMW images, show the advantage of the proposed approach compared to existing ones. {\textcopyright} 2012 IEEE.}, author = {Amizic, Bruno and Spinoulas, Leonidas and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {2012 19th IEEE International Conference on Image Processing}, doi = {10.1109/ICIP.2012.6467012}, isbn = {978-1-4673-2533-2}, issn = {15224880}, keywords = {Variable-splitting,blind image deconvolution,compressive sensing,inverse methods}, month = {sep}, organization = {IEEE}, pages = {925--928}, publisher = {IEEE}, title = {{Compressive sampling with unknown blurring function: Application to passive millimeter-wave imaging}}, url = {http://ieeexplore.ieee.org/document/6467012/}, year = {2012} }
@inproceedings{Lasya2012, abstract = {In patients having suffered myocardial infarction, the myocardium does not function properly due to scarring. These patients are divided into high and low risk of getting arrhythmia using recognized risk markers like Left Ventricular Ejection Fraction (LVEF) and scar size. In Cardiac Magnetic Resonance (CMR) imaging, the scarred tissue in the myocardium is studied by increasing the intensity of scar area with the help of contrast agents. In this work, we have explored if a group of patients with high risk of getting arrhythmias (HAG) can be distinguished from a group of patients with low risk of getting arrhythmias (LAG) using the texture differences present in the scar tissue as inputs to a classifier. In this work, the textural differences of scarred myocardium tissue in HAG and LAG are captured using Local Binary Patterns (LBP). Automatic classification of HAG and LAG is important as patients with high risk of arrhythmia are identified and implanted with Implantable Cardioverter- Defibrillator (ICD). A non-parametric classification method is used to classify the LBP and contrast measure distributions of HAG and LAG. This is a preliminary work on the classification of HAG patients and LAG patients that has to be explored further. Even with a limited dataset, experiments show that HAG and LAG can be distinguished with a sensitivity of 75% and specificity of 83.33% using LBP. {\textcopyright} 2012 EURASIP.}, author = {Kotu, Lasya P. and Engan, Kjersti and Eftest{\o}l, Trygve and Woie, Leik and {\O}rn, Stein and Katsaggelos, Aggelos K.}, booktitle = {European Signal Processing Conference}, isbn = {9781467310680}, issn = {22195491}, keywords = {CMR image,Contrast measure,High and low risk arrhythmias,Local Binary Pattern,Scarred myocardium}, pages = {2586--2590}, title = {{Local Binary Patterns used on Cardiac MRI to classify high and low risk patient groups}}, year = {2012} }
@inproceedings{Seungwon2012, abstract = {A multiple color-filter aperture (MCA) camera can provide depth information as well as color and intensity in the single-camera framework, where the MCA generates misalignment between color channels depending on the distance of a region-of-interest. In this paper, we present a single camera-based estimation of the full depth map using the color shifting property of the MCA. For estimating the color shifting vectors (CSVs) among red, green, and blue color channels, edges are extracted at each color channel. At the edge, we estimate CSVs using normalized cross correlation combined with color shifting mask map. A full depth map is then generated by depth interpolation using the matting Laplacian method from sparsely estimated CSVs at an edge location. Experimental results show that the proposed method can not only estimate the full depth map but also correct the misaligned color image to generate photorealistic color images using a single camera equipped with MCA. {\textcopyright} 2012 IEEE.}, author = {Lee, Seungwon and Lee, Junghyun and Hayes, Monson H. and Katsaggelos, Aggelos K. and Paik, Joonki}, booktitle = {2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, doi = {10.1109/ICASSP.2012.6288005}, isbn = {978-1-4673-0046-9}, issn = {15206149}, keywords = {3D image acquisition,Depth estimation,computational camera,depth interpolation,normalized cross correlation}, month = {mar}, pages = {801--804}, publisher = {IEEE}, title = {{Single camera-based full depth map estimation using color shifting property of a multiple color-filter aperture}}, url = {http://ieeexplore.ieee.org/document/6288005/}, year = {2012} }
@inproceedings{babacan2012bayesian, abstract = {We present a general method for blind image deconvolution using Bayesian inference with super-Gaussian sparse image priors. We consider a large family of priors suitable for modeling natural images, and develop the general procedure for estimating the unknown image and the blur. Our formulation includes a number of existing modeling and inference methods as special cases while providing additional flexibility in image modeling and algorithm design. We also present an analysis of the proposed inference compared to other methods and discuss its advantages. Theoretical and experimental results demonstrate that the proposed formulation is very effective, efficient, and flexible. {\textcopyright} 2012 Springer-Verlag.}, author = {Babacan, S. Derin and Molina, Rafael and Do, Minh N. and Katsaggelos, Aggelos K.}, booktitle = {Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)}, doi = {10.1007/978-3-642-33783-3_25}, isbn = {9783642337826}, issn = {03029743}, number = {PART 6}, organization = {Springer Berlin Heidelberg}, pages = {341--355}, title = {{Bayesian Blind Deconvolution with General Sparse Image Priors}}, url = {http://link.springer.com/10.1007/978-3-642-33783-3_25}, volume = {7577 LNCS}, year = {2012} }
@inproceedings{Miguel2012a, abstract = {The recent development of low-cost and fast time-of-flight cameras enabled measuring depth information at video frame rates. Although these cameras provide invaluable information for many 3D applications, their imaging capabilities are very limited both in terms of resolution and noise level. In this paper, we present a novel method for obtaining a high resolution depth map from a pair of a low resolution depth map and a corresponding high resolution color image. The proposed method exploits the correlation between the objects present in the color and depth map images via joint segmentation, which is then used to increase the resolution and remove noise via estimating conditional modes. Regions with inconsistent color and depth information are detected and corrected with our algorithm for increased robustness. Experimental results in terms of image quality and running times demonstrate the high performance of the method. {\textcopyright} 2012 EURASIP.}, author = {Tall{\'{o}}n, Miguel and {Derin Babacan}, S. and Mateos, Javier and Do, Minh N. and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {European Signal Processing Conference}, isbn = {9781467310680}, issn = {22195491}, keywords = {Time-of-flight cameras,color segmentation,depth enhancement,multisensor image fusion}, pages = {245--249}, title = {{Upsampling and denoising of depth maps via joint-segmentation}}, year = {2012} }
@inproceedings{xin2012laplacian, author = {Xin, Xin and Li, Zhu and Katsaggelos, Aggelos K}, booktitle = {Proc. ICASSP}, isbn = {9781467300469}, pages = {957--960}, title = {{Laplacian Sift in Visual Search}}, url = {https://citeseerx.ist.psu.edu/document?repid=rep1&type=pdf&doi=654fb1ed94555c848ccc3d7cf9a43941e1a40a61}, year = {2012} }
@inproceedings{Tzu-Jui2012, abstract = {In this paper, a new content-based feature identification method for video sequences is presented. It is robust to a number of image transformations and relatively lightweight compare to most state of the art methods. A scale and rotation invariant descriptor for a set of interest points in detected key frames is proposed based on modified minimal spanning tree algorithm. In addition, a predicative coding scheme is used to achieve minimal size of the descriptor for transmission. Furthermore, the pairwise distance between the frequency responses of the curvature vector from the descriptors is calculated and compared to efficiently match query with a large database. Experimental results demonstrate the effectiveness of our approach. {\textcopyright} 2012 EURASIP.}, author = {Liu, Tzu Jui and Han, Hye Jung and Xin, Xin and Li, Zhu and Katsaggelos, Aggelos K.}, booktitle = {European Signal Processing Conference}, isbn = {9781467310680}, issn = {22195491}, keywords = {Robust video hashing,content-based fingerprinting,multimedia fingerprinting,video copy detection}, pages = {160--164}, title = {{A robust and lightweight feature system for video fingerprinting}}, year = {2012} }
@inproceedings{Yun2012, abstract = {This paper introduced a camera surveillance system in wireless communications. The system contains three major modules, PTU (pan-tilt unit) camera control for surveillance video capture, cross-layer control for data compression and transmission, and error concealment for video quality enhancement. Our contribution is twofold. First, a system design for data collection and transmission over wireless networks is presented and is evaluated with physical surveillance equipments. The camera is capable of following the moving target according to the control information. The end-to-end distortion estimation in the delay constrained video coding process takes into account the dynamic channel condition and physical layer modulation and coding scheme (MCS) to determine optimal coding and transmission parameters. Second, multiple error concealment strategies, including interleaving, boundary match and video up-sampling, are applied utilizing the special property of the PTU camera motion. {\textcopyright} 2012 IEEE.}, author = {Ye, Yun and Ci, Song and Liu, Yanwei and Wu, Dalei and Wang, Haohong and Katsaggelos, Aggelos K.}, booktitle = {2012 Visual Communications and Image Processing}, doi = {10.1109/VCIP.2012.6410812}, isbn = {978-1-4673-4407-4}, keywords = {Camera control,error concealment,video surveillance,wireless communications}, month = {nov}, pages = {1--6}, publisher = {IEEE}, title = {{A wireless video surveillance system with an active camera}}, url = {http://ieeexplore.ieee.org/document/6410812/}, year = {2012} }
@inproceedings{lopez2012hyperparameters, author = {L{\'{o}}pez, Antonio and Cort{\'{e}}s, Jes{\'{u}}s M and L{\'{o}}pez-Oiler, Domingo and Molina, Rafael and Katsaggelos, Aggelos K}, booktitle = {2012 Proceedings of the 20th European Signal Processing Conference (EUSIPCO)}, organization = {IEEE}, pages = {489--493}, title = {{Hyperparameters estimation for the Bayesian localization of the EEG sources with TV priors}}, year = {2012} }
@inproceedings{Lu2011b, abstract = {Nowadays, digital pictures are usually captured at very high resolution ranged up to 12 mega-pixels. Limited by low-resolution display, we have to shrink the image. Signal processing theory tells us that optimal decimation requires low-pass filtering with a suitable cut-off frequency followed by down-sampling. In doing so, we need to remove lots of details. Subpixel-based down-sampling, taking advantage of the fact that each pixel on a color LCD is actually composed of individual red, green, and blue subpixel stripes, can provide apparent higher resolution. In this paper, we use frequency domain analysis to explain what happens in subpixel-based downsampling and why it is possible to achieve a higher apparent resolution. According to our frequency domain analysis and observation, the cut-off frequency of the low-pass filter for subpixel-based decimation can be effectively extended beyond the Nyquist frequency using a novel anti-aliasing filter. Experimental results verify that the proposed subpixel down-sampling scheme based on frequency analysis (SDSFA) can give superior results compared with existing pixel-based down-sampling methods. {\textcopyright} 2011 IEEE.}, author = {Fang, Lu and Tang, Ketan and Au, Oscar C. and Katsaggelos, Aggelos K.}, booktitle = {2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, doi = {10.1109/ICASSP.2011.5946604}, isbn = {978-1-4577-0538-0}, issn = {15206149}, month = {may}, pages = {1117--1120}, publisher = {IEEE}, title = {{Anti-aliasing filter for subpixel down-sampling based on frequency analysis}}, url = {http://ieeexplore.ieee.org/document/5946604/}, year = {2011} }
@inproceedings{Stefanos2011, abstract = {In this paper we propose a class of SR algorithms for compressed video using the maximum a posteriori (MAP) approach. These algorithms utilize a novel multichannel image prior model which has already been presented mainly for uncompressed video, along with a new hierarchical Gaussian nonstationary version of the state-of-the-art quantization noise model. The relationship between model components and the decoded bitstream is also demonstrated. An additional novelty of this framework pertains to the transition flexibility from totally nonstationary algorithms used for compressed video to fully stationary algorithms used for raw video. Numerical simulations comparing the proposed models among themselves, verify the efficacy of the adopted multichannel nonstationary prior for different compression ratios, and the significant role of the nonstationary observation term. {\textcopyright} 2011 EURASIP.}, author = {Belekos, Stefanos P. and Galatsanos, Nikolaos P. and Katsaggelos, Aggelos K.}, booktitle = {European Signal Processing Conference}, issn = {22195491}, pages = {293--297}, title = {{Maximum a posteriori super-resolution of compressed video with a novel multichannel image prior and a new observation model}}, year = {2011} }
@inproceedings{Pablo2011b, author = {Ruiz, Pablo and Babacan, S Derin and Gao, Li and Li, Zhu and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {2011 IEEE International Conference on Multimedia and Expo}, doi = {10.1109/ICME.2011.6012002}, isbn = {978-1-61284-348-3}, month = {jul}, pages = {1--6}, publisher = {IEEE}, title = {{Video retrieval using sparse Bayesian reconstruction}}, url = {http://ieeexplore.ieee.org/document/6012002/}, year = {2011} }
@inproceedings{babacan2011low, abstract = {There has been a significant interest in the recovery of low-rank matrices from an incomplete of measurements, due to both theoretical and practical developments demonstrating the wide applicability of the problem. A number of methods have been developed for this recovery problem, however, a principled method for choosing the unknown target rank is generally missing. In this paper, we present a recovery algorithm based on sparse Bayesian learning (SBL) and automatic relevance determination principles. Starting from a matrix factorization formulation and enforcing the low-rank constraint in the estimates as a sparsity constraint, we develop an approach that is very effective in determining the correct rank while providing high recovery performance. We provide empirical results and comparisons with current state-of-the-art methods that illustrate the potential of this approach. {\textcopyright} 2011 IEEE.}, author = {Babacan, S. Derin and Luessi, Martin and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, doi = {10.1109/ICASSP.2011.5946762}, isbn = {978-1-4577-0538-0}, issn = {15206149}, keywords = {Bayesian methods,Low-rank matrix completion,automatic relevance determination}, month = {may}, organization = {IEEE}, pages = {2188--2191}, publisher = {IEEE}, title = {{Low-rank matrix completion by variational sparse Bayesian learning}}, url = {http://ieeexplore.ieee.org/document/5946762/}, year = {2011} }
@inproceedings{Lei2011, author = {Lei, Song and Fan, Jiang and Zhongke, Shi and Aggelos, K Katsaggelos}, booktitle = {2011 IEEE International Conference on Multimedia and Expo}, pages = {1--6}, title = {{Understanding dynamic scenes by hierarchical motion pattern mining}}, year = {2011} }
@inproceedings{Miguel2011a, abstract = {Synthetic aperture radar (SAR) imagery suffers from the speckle phenomenon. Speckle gives rise to the presence of multiplicative noise which severely degrades the observed images. It is known that logarithmically transformed speckle can be well approximated by a Gaussian distribution. In this paper we propose an algorithm for despeckling images, within the log-transformed spatial domain, using a TV prior whose model parameter is automatically determined using the Evidence Analysis within the Hierarchical Bayesian Paradigm. The effectiveness of the proposed algorithm, over both synthetically speckled and real SAR images, is studied. {\textcopyright} 2011 IEEE.}, author = {Vega, Miguel and Mateos, Javier and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {2011 18th IEEE International Conference on Image Processing}, doi = {10.1109/ICIP.2011.6115772}, isbn = {978-1-4577-1303-3}, issn = {15224880}, keywords = {Bayesian methods,SAR images denoising,despeckling,image restoration,parameter estimation}, month = {sep}, pages = {165--168}, publisher = {IEEE}, title = {{Bayesian TV denoising of SAR images}}, url = {http://ieeexplore.ieee.org/document/6115772/}, year = {2011} }
@inproceedings{Dacheng, author = {Dacheng, Tao and Zhu, Li and Jun, Li and Aggelos, Katsaggelos and Wei, Bian}, booktitle = {2011 IEEE 11th International Conference on Data Mining Workshops}, doi = {10.1109/ICDMW.2011.199}, isbn = {978-1-4673-0005-6}, month = {dec}, pages = {xliii--xliv}, publisher = {IEEE}, title = {{Preface to the Large Scale Visual Analytics Workshop}}, url = {http://ieeexplore.ieee.org/document/6137549/}, year = {2011} }
@inproceedings{babacan2011compressive, abstract = {In this paper, we present a novel passive millimeter-wave (PMMW) imaging system designed using compressive sensing principles. We employ randomly encoded masks at the focal plane of the PMMW imager to acquire incoherent measurements of the imaged scene. We develop a Bayesian reconstruction algorithm to estimate the original image from these measurements, where the sparsity inherent to typical PMMW images is efficiently exploited. Comparisons with other existing reconstruction methods show that the proposed reconstruction algorithm provides higher quality image estimates. Finally, we demonstrate with simulations using real PMMW images that the imaging duration can be dramatically reduced by acquiring only a few measurements compared to the size of the image. {\textcopyright} 2011 IEEE.}, author = {Babacan, S. D. and Luessi, M. and Spinoulas, L. and Katsaggelos, A. K. and Gopalsami, N. and Elmer, T. and Ahern, R. and Liao, S. and Raptis, A.}, booktitle = {2011 18th IEEE International Conference on Image Processing}, doi = {10.1109/ICIP.2011.6116227}, isbn = {978-1-4577-1303-3}, issn = {15224880}, keywords = {Bayesian methods,Passive millimeter wave imaging,compressive sensing,sparse reconstruction}, month = {sep}, organization = {IEEE}, pages = {2705--2708}, publisher = {IEEE}, title = {{Compressive passive millimeter-wave imaging}}, url = {http://ieeexplore.ieee.org/document/6116227/}, year = {2011} }
@inproceedings{Bruno2011, abstract = {In this paper we propose a novel partial out-of-focus blur removal method developed within the Bayesian framework. We concentrate on the removal of background out-of-focus blurs that are present in the images in which there is a strong interest to keep the foreground in sharp focus. However, often there is a desire to recover background details out of such partially blurred image. In this work, a non-convex l p-norm prior with 0 < p < 1 is used as the background and foreground image prior and a total variation (TV) based prior is utilized for both the background blur and the occlusion mask, that is, the mask determining the pixels belonging to the foreground. In order to model transparent foregrounds, the values in the occlusion mask are assumed to belong to the closed interval [0,1]. The proposed method is derived by utilizing bounds on the priors for the background and foreground image, the background blur and the occlusion mask using the majorization-minimization principle. Maximum a posteriori Bayesian inference is performed and as a result, the background and foreground image, the background blur, the occlusion mask and the model parameters are simultaneously estimated. Experimental results are presented to demonstrate the advantage of the proposed method over the existing ones. {\textcopyright} 2011 EURASIP.}, author = {Amizic, Bruno and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {European Signal Processing Conference}, issn = {22195491}, pages = {1673--1677}, title = {{Bayesian partial out-of-focus blur removal with parameter estimation}}, year = {2011} }
@inproceedings{Haomian2011, abstract = {Video action and event recognition is an important problem in video analysis research with many important applications, such as surveillance and video search. In this work, we deal with the appearance complexity in video action recognition by applying an indexing structure and partition in appearance space. The task requires spatio-temporal appearance modeling that can capture the discriminative information among different action classes. Traditional approaches are based on a global appearance model, which is not robust to local variations in background. In this work, we develop a query driven dynamic appearance modeling method and use a localized subspace to obtain a distance metric for appearance discrimination. Multiple localized models are constructed and utilized to measure the similarity between the trajectories and the sub-space metric is adaptive during the learning process. The processing is implemented based on an indexing scheme, which is very fast in computation. Simulation results demonstrate the effectiveness of the solution. {\textcopyright} 2011 IEEE.}, author = {Zheng, Haomian and Li, Zhu and Katsaggelos, Aggelos K. and {Jia You}}, booktitle = {2011 IEEE International Conference on Multimedia and Expo}, doi = {10.1109/ICME.2011.6012031}, isbn = {978-1-61284-348-3}, issn = {19457871}, keywords = {Localize Modeling,Query-Driven,Space Indexing,Spatio-temporal Modeling,Video Action Recognition}, month = {jul}, pages = {1--6}, publisher = {IEEE}, title = {{Indexed spatio-temporal appearance models for query-driven video action recognition}}, url = {http://ieeexplore.ieee.org/document/6012031/}, year = {2011} }
@inproceedings{Pablo2011a, abstract = {Fast and accurate algorithms are essential for the efficient search and retrieval of the huge amount of video data that is generated for different purposes and applications every day. The interesting properties of sparse representation and the new sampling theory named Compressive Sensing (CS) constitute the core of the new approach to video representation and retrieval we are presenting in this paper to deal with the search of noisy video clips with also possibly missing frames. Once the representation (where sparsity is expected) has been chosen and the observations have been taken, the proposed approach utilizes Bayesian modeling and inference to tackle the retrieval problem. In order to speed up the inference process the use of Principal Components Analysis (PCA) to provide an alternative representation of the frames is analyzed. Experimental results validate the proposed approach to the retrieval of video clips with missing frames as well as its robustness against noise. {\textcopyright} 2011 University of Zagreb.}, author = {Ruiz, Pablo and Babacan, S. Derin and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {ISPA 2011 - 7th International Symposium on Image and Signal Processing and Analysis}, isbn = {9789531841597}, pages = {443--448}, title = {{Retrieval of video clips with missing frames using sparse Bayesian reconstruction}}, year = {2011} }
@inproceedings{Miguel2011c, abstract = {In this paper we propose a space-variant kernel estimation method for effective deconvolution when combining different exposure image pairs. The proposed algorithm can be applied to images blurred by both camera and object motion in an efficient manner. The blur in the long exposure shot is mainly caused by camera shake or object motion, and the noise of the underexposed image is introduced by the gain factor applied to the sensor when the ISO is set to a high value. The main idea in this work is to incorporate a spatially-varying deblurring/denoising which is applied to image patches. The method exploits kernel estimation and error measures to choose between denoising and deblurring each patch. In addition, the proposed approach estimates all necessary parameters automatically without user supervision. {\textcopyright} 2011 EURASIP.}, author = {Tall{\'{o}}n, Miguel and Mateos, Javier and Babacan, S. Derin and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {European Signal Processing Conference}, issn = {22195491}, pages = {1678--1682}, title = {{Space-variant kernel deconvolution for dual exposure problem}}, year = {2011} }
@inproceedings{tallon2011image, author = {Tall{\'{o}}n, Miguel and Mateos, Javier and Molina, Rafael and Katsaggelos, Aggelos K}, booktitle = {2011 7th International Symposium on Image and Signal Processing and Analysis (ISPA)}, organization = {IEEE}, pages = {408--413}, title = {{Image prior combination in space-variant blur deconvolution for the dual exposure problem}}, year = {2011} }
@inproceedings{Randy2011, abstract = {The design of benchmark imagery for validation of image annotation algorithms is considered. Emphasis is placed on imagery that contains industrial facilities, such as chemical refineries. An application-level facility ontology is used as a means to define salient objects in the benchmark imagery. In-strinsic and extrinsic scene factors important for comprehensive validation are listed, and variability in the benchmarks discussed. Finally, the pros and cons of three forms of benchmark imagery: real, composite and synthetic, are delineated. {\textcopyright} 2011 IEEE.}, author = {Roberts, Randy S. and Pope, Paul A. and Vatsavai, Raju R. and Jiang, Ming and Arrowood, Lloyd F. and Trucano, Timothy G. and Gleason, Shaun and Cheriyadat, Anil and Sorokine, Alex and Katsaggelos, Aggelos K. and Pappas, Thrasyvoulos N. and Gaines, Lucinda R. and Chilton, Lawrence K.}, booktitle = {2011 IEEE International Geoscience and Remote Sensing Symposium}, doi = {10.1109/IGARSS.2011.6049340}, isbn = {978-1-4577-1003-2}, keywords = {Algorithm validation,Benchmark imagery,Benchmark variability,Ontology,Real annotated imagery,Validation using synthetic imagery}, month = {jul}, pages = {1453--1456}, publisher = {IEEE}, title = {{Design of benchmark imagery for validating facility annotation algorithms}}, url = {http://ieeexplore.ieee.org/document/6049340/}, year = {2011} }
@inproceedings{Sangjin2011, author = {Babacan, SD and Katsaggelos, AK and Kang, W and Lee, E and Kim, S and Paik, J}, booktitle = {Proceedings of the International Technical Conference on Circuits/Systems, Computers and communications (ITC-CSCC)}, keywords = {Real-time image restoration,directional wavelet ba}, title = {{Vaguelette-wavelet decomposition for frequency adaptive image restoration using directional wavelet bases}}, url = {https://www.scholars.northwestern.edu/en/publications/vaguelette-wavelet-decomposition-for-directionally-adaptive-image}, year = {2011} }
@inproceedings{Stefanos2011a, author = {Belekos, Stefanos P and Jeon, Jaehwan and Lee, Jinhee and Paik, Joonki and Katsaggelos, Aggelos K}, booktitle = {Proc. ITC-CSCC}, pages = {95--96}, title = {{Region-based super-resolution reconstruction using parallel programming}}, year = {2011} }
@inproceedings{Lu2011a, abstract = {A digital camera provided with a Bayer pattern single sensor needs color interpolation to reconstruct a full color image. To show high resolution image on a lower resolution display, it must then be down-sampled. These two steps influence each other, i.e., the color artifacts introduced in demosaicing may be magnified in subsequent down-sampling process and vice versa. Thanks to the fact that LCD displays are actually composed of separable subpixels, which can be individually addressed to achieve a higher effective apparent resolution. This paper presents an Adaptive Joint Demosaicing and Subpixel-based Down-sampling scheme (AJDSD) for single-sensor camera image, where the subpixel-based down-sampling is adaptively and directly applied in Bayer domain, without the process of demosaicing. Simulation results demonstrate that when compared with conventional demosaicing-first and down-sampling-later methods, AJDSD achieves superior performance improvement in terms of computational complexity. As for visual quality, AJDSD is more effective in preserving high frequency details, leading to much sharper and clearer results. {\textcopyright} 2011 IEEE.}, author = {Fang, Lu and Au, Oscar C. and Katsaggelos, Aggelos K.}, booktitle = {2011 IEEE International Conference on Multimedia and Expo}, doi = {10.1109/ICME.2011.6011888}, isbn = {978-1-61284-348-3}, issn = {19457871}, month = {jul}, pages = {1--6}, publisher = {IEEE}, title = {{Adaptive joint demosaicing and Subpixel-based Down-sampling for Bayer image}}, url = {http://ieeexplore.ieee.org/document/6011888/}, year = {2011} }
@inproceedings{Eren2011a, abstract = {We propose a tracking-aware system that removes video components of low tracking interest and optimizes the quantization during compression of frequency coefficients, particularly those that most influence trackers, significantly reducing bitrate while maintaining comparable tracking accuracy. We utilize tracking accuracy as our compression criterion in lieu of mean squared error metrics. The process of optimizing quantization tables suitable for automated tracking can be executed online or offline. The online implementation initializes the encoding procedure for a specific scene, but introduces delay. On the other hand, the offline procedure produces globally optimum quantization tables where the optimization occurs for a collection of video sequences. Our proposed system is designed with low processing power and memory requirements in mind, and as such can be deployed on remote nodes. Using H.264/AVC video coding and a commonly used state-of-the-art tracker we show that while maintaining comparable tracking accuracy our system allows for over 50% bitrate savings on top of existing savings from previous work. {\textcopyright} 2011 IEEE.}, author = {Soyak, E. and Tsaftaris, S. A. and Katsaggelos, A. K.}, booktitle = {2011 18th IEEE International Conference on Image Processing}, doi = {10.1109/ICIP.2011.6115739}, isbn = {978-1-4577-1303-3}, issn = {15224880}, keywords = {Urban traffic video tracking,postprocessing,preprocessing,quantization,transportation,video compression}, month = {sep}, pages = {153--156}, publisher = {IEEE}, title = {{Tracking-optimized quantization for H.264 compression in transportation video surveillance applications}}, url = {http://ieeexplore.ieee.org/document/6115739/}, year = {2011} }
@inproceedings{katsaggelos2011joie, author = {Katsaggelos, Aggelos K. and {S. A. Tsaftaris} and Casadio, F. and Gautier, G. and Andral, J.-L. and Katsaggelos, Aggelos K.}, booktitle = {Picasso Express}, title = {{La joie de vivre: The evolution of a masterpiece}}, year = {2011} }
@inproceedings{gopalsami2011compressive, author = {Gopalsami, N and Elmer, T W and Liao, Shaolin and Ahern, R and Heifetz, A and Raptis, A C and Luessi, M and Babacan, D and Katsaggelos, Aggelos K}, booktitle = {Passive Millimeter-Wave Imaging Technology XIV}, organization = {SPIE}, pages = {135--140}, title = {{Compressive sampling in passive millimeter-wave imaging}}, volume = {8022}, year = {2011} }
@inproceedings{Leonidas2011, author = {Spinoulas, Leonidas and Yoon, Inhye and Kim, Donggyun and Paik, Joonki and Katsaggelos, Aggelos K}, booktitle = {Proceedings of the International Technical Conference on Circuits/Systems, Computers and communications (ITC-CSCC)}, title = {{Spatially Adaptive Defogging Using Luminance Map}}, year = {2011} }
@inproceedings{Esteban2011, abstract = {In this paper, we propose an algorithm for image restoration based on fusing nonstationary edgepreserving priors. We develop a Bayesian modeling followed by an evidence approximation inference approach for deriving the analytic foundations of the proposed restoration method. Through a series of approximations, the final implementation of the proposed image restoration algorithm is iterative and takes advantage of the Fourier domain. Simulation results over a variety of blurred and noisy standard test images indicate that the presented method comfortably surpasses the current state-of-the-art image restoration for compactly supported degradations. We finally present experimental results by digitally refocusing images captured with controlled defocus, successfully confirming the ability of the proposed restoration algorithm in recovering extra features and rich details, while still preserving edges. {\textcopyright} 2013 Optical Society of America.}, author = {Vera, Esteban and Vega, Miguel and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {2011 18th IEEE International Conference on Image Processing}, doi = {10.1109/ICIP.2011.6116456}, isbn = {978-1-4577-1303-3}, issn = {1559-128X}, month = {sep}, number = {10}, pages = {3457--3460}, publisher = {IEEE}, title = {{A novel iterative image restoration algorithm using nonstationary image priors}}, url = {https://opg.optica.org/abstract.cfm?URI=ao-52-10-D102 http://ieeexplore.ieee.org/document/6116456/}, volume = {52}, year = {2011} }
@inproceedings{Sotirios2010, author = {Sotirios, A Tsaftaris and Xiangzhi, Zhou and Richard, Tang and Rachel, Klein and Aggelos, Katsaggelos and Rohan, Dharmakumar}, booktitle = {Proc. Intl. Soc. Mag. Reson. Med}, pages = {3722}, title = {{Automated synchronization of cardiac phases for Myocardial BOLD MRI}}, url = {https://cds.ismrm.org/protected/10MProceedings/PDFfiles/3722_2681.PDF}, volume = {18}, year = {2010} }
@inproceedings{Laszlo, author = {Laszlo, B{\"{o}}sz{\"{o}}rmenyi and Dumitru, Burdescu and Philip, Davis and Peter, L Stanchev and Farshad, Fotouhi and Antonio, Liotta and David, Newell and Klaus, Sch{\"{o}}ffmann and Christian, Spielvogel and Max, Agueh and Et al.}, booktitle = {MMEDIA 2010 Technical Program Committee}, title = {{MMEDIA 2010 Technical Program Committee}}, url = {https://www.iaria.org/conferences2010/ComMMEDIA10.html}, year = {2010} }
@inproceedings{babacan2010sparse, abstract = {In this paper we propose a novel Bayesian algorithm for image restoration and parameter estimation. We utilize an image prior where Gaussian distributions are placed per pixel in the high-pass filter outputs of the image. By following the hierarchical Bayesian framework, we simultaneously estimate the unknown image and hyperparameters for both the image prior and the image degradation noise. We show that the proposed formulation is a special case of the popular lp-norm based formulations with p = 0, and therefore enforces sparsity to an high extent in the filtered image coefficients. Moreover, the proposed formulation results in a convex optimization problem, and therefore does not suffer from the robustness issues common with non-convex image priors. Experimental results demonstrate that the proposed algorithm provides superior performance compared to state-of-the-art restoration algorithms although no user-supervision is required. {\textcopyright} 2010 IEEE.}, author = {Babacan, S. Derin and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {2010 IEEE International Conference on Image Processing}, doi = {10.1109/ICIP.2010.5650957}, isbn = {978-1-4244-7992-4}, issn = {15224880}, keywords = {Bayesian methods,Image restoration,Parameter estimation}, month = {sep}, organization = {IEEE}, pages = {3577--3580}, publisher = {IEEE}, title = {{Sparse Bayesian image restoration}}, url = {http://ieeexplore.ieee.org/document/5650957/}, year = {2010} }
@inproceedings{Eren2010a, abstract = {The compression of video can reduce the accuracy of automated tracking algorithms. This is problematic for centralized applications such as transportation surveillance systems, where remotely captured and compressed video is transmitted to a central location for tracking. In typical systems, the majority of communications bandwidth is spent on representing events such as capture noise or local changes to lighting. We propose a pre- and post-processing algorithm that identifies and removes such events of low tracking interest, significantly reducing the bitrate required to transmit remotely captured video while maintaining comparable tracking accuracy. Using the H.264/AVC video coding standard and a commonly used state-of-the-art tracker we show that our algorithm allows for up to 90% bitrate savings while maintaining comparable tracking accuracy. {\textcopyright}2010 IEEE.}, author = {Soyak, E. and Tsaftaris, S. A. and Katsaggelos, A. K.}, booktitle = {2010 17th IEEE International Conference on Electronics, Circuits and Systems}, doi = {10.1109/ICECS.2010.5724531}, isbn = {978-1-4244-8155-2}, keywords = {Postprocessing,Preprocessing,Transportation,Urban traffic video tracking,Video compression}, month = {dec}, pages = {375--378}, publisher = {IEEE}, title = {{Tracking-optimal pre- and post-processing for H.264 compression in traffic video surveillance applications}}, url = {http://ieeexplore.ieee.org/document/5724531/}, year = {2010} }
@inproceedings{babacan2009fast, abstract = {In this paper, we model the components of the compressive sensing (CS) problem, i.e., the signal acquisition process, the unknown signal coefficients and the model parameters for the signal and noise using the Bayesian framework. We utilize a hierarchical form of the Laplace prior to model the sparsity of the unknown signal. We describe the relationship among a number of sparsity priors proposed in the literature, and show the advantages of the proposed model including its high degree of sparsity. Moreover,we show that some of the existing models are special cases of the proposed model. Using our model, we develop a constructive (greedy) algorithm designed for fast reconstruction useful in practical settings. Unlike most existing CS reconstruction methods, the proposed algorithm is fully automated, i.e., the unknown signal coefficients and all necessary parameters are estimated solely from the observation, and, therefore, no user-intervention is needed. Additionally, the proposed algorithm provides estimates of the uncertainty of the reconstructions.We provide experimental results with synthetic 1-D signals and images, and compare with the state-of the-art CS reconstruction algorithms demonstrating the superior performance of the proposed approach. {\textcopyright} 2009 IEEE.}, author = {Babacan, S.D. and Molina, Rafael and Katsaggelos, A.K.}, booktitle = {IEEE Transactions on Image Processing}, doi = {10.1109/TIP.2009.2032894}, issn = {1057-7149}, keywords = {Bayesian methods,Compressive sensing,Inverse problems,Relevance vector machine (RVM),Sparse Bayesian learning}, month = {jan}, number = {1}, organization = {IEEE}, pages = {53--63}, pmid = {19775966}, title = {{Bayesian Compressive Sensing Using Laplace Priors}}, url = {http://ieeexplore.ieee.org/document/5256324/}, volume = {19}, year = {2010} }
@inproceedings{Bo2010, abstract = {A computational geometry approach is developed to detect video duplicate with mild transformations. We model the video sequence as a trajectory after scaling and projection. Through interpolation and equal curve length sampling, part of the frame points is selected. A simplified video representation is the line segment set connecting the left neighboring points. For a given query, match distortion is calculated by projecting the query frame points to the line segment set guided by the frame temporal relationship. Experiments demonstrate the effectiveness of the proposed approach. {\textcopyright} 2010 IEEE.}, author = {Liu, Bo and Li, Zhu and Wang, Meng and Katsaggelos, A. K.}, booktitle = {2010 IEEE International Conference on Image Processing}, doi = {10.1109/ICIP.2010.5652956}, isbn = {978-1-4244-7992-4}, issn = {15224880}, keywords = {Cubic interpolation,Curve matching,Duplicate detection}, month = {sep}, pages = {1037--1040}, publisher = {IEEE}, title = {{In-sequence video duplicate detection with fast point-to-line matching}}, url = {http://ieeexplore.ieee.org/document/5652956/}, year = {2010} }
@inproceedings{Fan2010, abstract = {Compared to other approaches that analyze object trajectories, we propose to detect anomalous video events at three levels considering spatiotemporal context of video objects, i.e., point anomaly, sequential anomaly, and co-occurrence anomaly. A hierarchical data mining approach is proposed to achieve this task. At each level, the frequency based analysis is performed to automatically discover regular rules of normal events. The events deviating from these rules are detected as anomalies. Experiments on real traffic video prove that the detected video anomalies are hazardous or illegal according to the traffic rule. {\textcopyright} 2010 IEEE.}, author = {Jiang, Fan and Yuan, Junsong and Tsaftaris, Sotirios A. and Katsaggelos, Aggelos K.}, booktitle = {2010 IEEE International Conference on Image Processing}, doi = {10.1109/ICIP.2010.5650993}, isbn = {978-1-4244-7992-4}, issn = {15224880}, month = {sep}, pages = {705--708}, publisher = {IEEE}, title = {{Video anomaly detection in spatiotemporal context}}, url = {http://ieeexplore.ieee.org/document/5650993/}, year = {2010} }
@inproceedings{Martin2010a, author = {Luessi, Martin and Babacan, S Derin and Molina, Rafael and Booth, James R and Katsaggelos, Aggelos K}, booktitle = {16th Annual Meeting of the Organization for Human Brain Mapping}, title = {{Bayesian spatially adaptive EEG/fMRI fusion with application to a word rhyming task}}, year = {2010} }
@inproceedings{Rafael2010, author = {Molina, Rafael and Vega, Miguel and Mateos, Javier and Katsaggelos, Aggelos K}, booktitle = {ADA 6-Sixth Conference on Astronomical Data Analysis}, pages = {17}, title = {{Pansharpening of Multispectral Images using Variational Methods and Model Combination}}, year = {2010} }
@inproceedings{RangaRaju2010, abstract = {With increasing understanding and availability of nuclear technologies, and increasing persuasion of nuclear technologies by several new countries, it is increasingly becoming important to monitor the nuclear proliferation activities. There is a great need for developing technologies to automatically or semi-automatically detect nuclear proliferation activities using remote sensing. Images acquired from earth observation satellites is an important source of information in detecting proliferation activities. High-resolution remote sensing images are highly useful in verifying the correctness, as well as completeness of any nuclear program. DOE national laboratories are interested in detecting nuclear proliferation by developing advanced geospatial image mining algorithms. In this paper we describe the current understanding of geospatial image mining techniques and enumerate key gaps and identify future research needs in the context of nuclear proliferation. {\textcopyright} 2010 IEEE.}, author = {Vatsavai, Ranga Raju and Bhaduri, Budhendra and Cheriyadat, Anil and Arrowood, Lloyd and Bright, Eddie and Gleason, Shaun and Diegert, Carl and Katsaggelos, Aggelos and Pappas, Thrasos and Porter, Reid and Bollinger, Jim and Chen, Barry and Hohimer, Ryan}, booktitle = {2010 IEEE International Geoscience and Remote Sensing Symposium}, doi = {10.1109/IGARSS.2010.5649811}, isbn = {978-1-4244-9565-8}, keywords = {Geospatial ontology,Low-level features,Nuclear proliferation,Semantic classification}, month = {jul}, pages = {48--51}, publisher = {IEEE}, title = {{Geospatial image mining for nuclear proliferation detection: Challenges and new opportunities}}, url = {http://ieeexplore.ieee.org/document/5649811/}, year = {2010} }
@inproceedings{Miguel2010, abstract = {Photographs acquired under low-lighting conditions require long exposure times and therefore exhibit significant blurring due to the shaking of the camera. Using shorter exposure times results in sharper images but with a very high level of noise. By taking a pair of blurred/noisy images it is possible to reconstruct a sharp image without noise. This paper is devoted to the combination of observation models in the blurred/noisy image pair reconstruction problem. By examining the difference between the blurred image and the blurred version of the noisy image a third observation model is obtained. Based on the minimization of a linear convex combination of Kullback-Leibler divergences between posterior distributions, a procedure to combine the three observation models is proposed in the paper. The estimated images are compared with images provided by other reconstruction methods. {\textcopyright} EURASIP, 2010.}, author = {Tall{\'{o}}n, M. and Mateos, J. and Babacan, S. D. and Molina, R. and Katsaggelos, A. K.}, booktitle = {European Signal Processing Conference}, issn = {22195491}, pages = {323--327}, title = {{Combining observation models in dual exposure problems using the Kullback-Leibler divergence}}, year = {2010} }
@inproceedings{Glafkos2010, author = {Stratis, Glafkos and Samuel, Alphonso and Bellofiore, Salvatore and Cassabaum, Mary and Maalouli, Ghassan and Taflove, Allen and Katsaggelos, Aggelos K. and Penney, Chris}, booktitle = {Radar Sensor Technology XIV}, doi = {10.1117/12.851396}, editor = {Ranney, Kenneth I. and Doerry, Armin W.}, isbn = {9780819481337}, issn = {0277786X}, month = {apr}, pages = {766913}, title = {{Quantization of polarization states through scattering mechanisms}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?doi=10.1117/12.851396}, volume = {7669}, year = {2010} }
@inproceedings{Jiang2010, abstract = {Initializing hand/finger articulation for tracking is a very challenging problem, mainly because hand articulation is complicated and it has a large number of degrees of freedom. Most existing algorithms initialize tracking manually, or use a nearest-neighbor search with restricting the number of possible hand gestures. This paper presents a new solution to this problem by increasing the dimensionality but taking advantage of the sparseness. The basic idea is to divide the set of phalange joint angles into many overlapping subsets. As each subset has a much smaller number of joint angles, it is much easier to design a smaller-scale articulation estimator. The estimation of the whole hand is done by the collaboration of a network of dependent smaller-scale estimators. This paper describes a novel way of designing the smaller-scale estimators as well as a principled way of fusing the estimates. A tracking system is also shown by using this initialization technique. {\textcopyright} 2010 IEEE.}, author = {Xu, Jiang and Wu, Ying and Katsaggelos, Aggelos}, booktitle = {2010 IEEE International Conference on Image Processing}, doi = {10.1109/ICIP.2010.5651179}, isbn = {978-1-4244-7992-4}, issn = {15224880}, keywords = {Hand tracking initialization}, month = {sep}, pages = {3257--3260}, publisher = {IEEE}, title = {{Part-based initialization for hand tracking}}, url = {http://ieeexplore.ieee.org/document/5651179/}, year = {2010} }
@inproceedings{Martin2010, author = {Luessi, Martin and Babacan, S Derin and Molina, Rafael and Booth, James R. and Katsaggelos, Aggelos K.}, booktitle = {2010 IEEE International Conference on Acoustics, Speech and Signal Processing}, doi = {10.1109/ICASSP.2010.5495153}, isbn = {978-1-4244-4295-9}, pages = {638--641}, publisher = {IEEE}, title = {{Symmetrical EEG/FMRI fusion with spatially adaptive priors using variational distribution approximation}}, url = {http://ieeexplore.ieee.org/document/5495153/}, year = {2010} }
@inproceedings{Soyak2010, author = {Soyak, E. and Tsaftaris, S. A. and Katsaggelos, A. K.}, booktitle = {2010 IEEE International Conference on Image Processing}, doi = {10.1109/ICIP.2010.5652364}, isbn = {978-1-4244-7992-4}, month = {sep}, pages = {1241--1244}, publisher = {IEEE}, title = {{Quantization optimized H.264 encoding for traffic video tracking applications}}, url = {http://ieeexplore.ieee.org/document/5652364/}, year = {2010} }
@inproceedings{Louis2010, abstract = {The phenomenon of anticipatory coarticulation provides a basis for the observed asynchrony between the acoustic and visual onsets of phones in certain linguistic contexts. This type of asynchrony is typically not explicitly modeled in audio-visual speech models. In this work, we study within-word audiovisual asynchrony using manual labels of words in which theory suggests that audio-visual asynchrony should occur, and show that these hand labels confirm the theory. We then introduce a new statistical model of audio-visual speech, the asynchrony-dependent transition (ADT) model. This model allows asynchrony between audio and video states within word boundaries, where the audio and video state transitions depend not only on the state of that modality, but also on the instantaneous asynchrony. The ADT model outperforms a baseline synchronous model in mimicking the hand labels in a forced alignment task, and its behavior as parameters are changed conforms to our expectations about anticipatory coarticulation. The same model could be used for speech recognition, although here we consider it only for the task of forced alignment for linguistic analysis. {\textcopyright} 2010 ISCA.}, address = {ISCA}, author = {Terry, Louis H. and Livescu, Karen and Pierrehumbert, Janet B. and Katsaggelos, Aggelos K.}, booktitle = {Interspeech 2010}, doi = {10.21437/Interspeech.2010-711}, keywords = {Anticipatory coarticulation,Audio-visual asynchrony,Audio-visual speech recognition,Dynamic Bayesian networks}, month = {sep}, pages = {2682--2685}, publisher = {ISCA}, title = {{Audio-visual anticipatory coarticulation modeling by human and machine}}, url = {https://www.isca-speech.org/archive/interspeech_2010/terry10_interspeech.html}, year = {2010} }
@inproceedings{amizic2010fast, abstract = {In this paper we propose two fast Total Variation (TV) based algorithms for image restoration by utilizing variational posterior distribution approximation. The unknown image and the hyperparameters for the image and observation models are formulated and estimated simultaneously within a hierachical Bayesian framework, rendering the algorithms fully-automated without any free parameters. Experimental results demonstrate that the proposed algorithms provide restoration results competitive to existing methods in terms of image quality while achieving superior computational efficiency. {\textcopyright}2010 IEEE.}, author = {Amizic, Bruno and Babacan, S. Derin and Michael, K. Ng and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {2010 IEEE International Conference on Acoustics, Speech and Signal Processing}, doi = {10.1109/ICASSP.2010.5494994}, isbn = {978-1-4244-4295-9}, issn = {15206149}, keywords = {Bayesian methods,Image restoration,Parameter estimation,Total variation,Variational methods}, organization = {IEEE}, pages = {770--773}, publisher = {IEEE}, title = {{Fast total variation image restoration with parameter estimation using bayesian inference}}, url = {http://ieeexplore.ieee.org/document/5494994/}, year = {2010} }
@inproceedings{xin2010novel, abstract = {An image could be described with local features like SIFT and with those features, images could be represented as "Bag-of-Visual-Words"(BVW). This representation has been widely used in content based image retrieval. Comparing BVW of two images is usually done in Euclidean space, like Euclidean distance or weighted variants. Neither of these methods consider the inter cluster relations. If there is a feature in one image without any match in all the clusters of another image's features, there will be no score for that feature. But, there are still some match in neighbor clusters. In this paper, we use dynamic programming to calculate full inter cluster distance map and with the distance, we can evaluate a feature in neighbor clusters. Our proposed method is evaluated in Caltech 101 database and experiments show that our method generally exceeds the method that don't consider inter cluster distance. {\textcopyright} 2010 IEEE.}, author = {Xin, Xin and Katsaggelos, Aggelos K.}, booktitle = {2010 IEEE International Conference on Image Processing}, doi = {10.1109/ICIP.2010.5651817}, isbn = {978-1-4244-7992-4}, issn = {15224880}, keywords = {Bag of visual word,Dynamic programming,ISOMAP,Image retrieval}, month = {sep}, organization = {IEEE}, pages = {3213--3216}, publisher = {IEEE}, title = {{A novel image retrieval framework exploring inter cluster distance}}, url = {http://ieeexplore.ieee.org/document/5651817/}, year = {2010} }
@inproceedings{chantas2010variational, abstract = {In this paper a new image prior is introduced and used in image restoration. This prior is based on products of spatially weighted Total Variations (TV). These spatial weights provide this prior with the flexibilit to better capture local image features than previous TV based priors. Bayesian inference is used for image restoration with this prior via the variational approximation. The proposed algorithm is fully automatic in the sense that all necessary parameters are estimated from the data. Numerical experiments are shown which demonstrate that image restoration based on this prior compares favorably with previous state-of-the-art restoration algorithms. {\textcopyright} 2010 IEEE.}, author = {Chantas, Giannis and Galatsanos, Nikolaos and Molina, Rafael and Katsaggelos, Aggelos}, booktitle = {2010 2nd International Workshop on Cognitive Information Processing}, doi = {10.1109/CIP.2010.5604259}, isbn = {978-1-4244-6459-3}, month = {jun}, organization = {IEEE}, pages = {227--231}, publisher = {IEEE}, title = {{Variational Bayesian inference image restoration using a product of total variation-like image priors}}, url = {http://ieeexplore.ieee.org/document/5604259/}, year = {2010} }
@inproceedings{Salvador2010b, abstract = {In this paper a new combination of image priors is introduced and applied to Super Resolution (SR) image reconstruction. A sparse image prior based on the 1 norms of the horizontal and vertical first order differences is combined with a non-sparse SAR prior. Since, for a given observation model, each prior produces a different posterior distribution of the underlying High Resolution (HR) image, the use of variational posterior distribution approximation on each posterior will produce as many posterior approximations as priors we want to combine. A unique approximation is obtained here by finding the distribution on the HR image given the observations that minimize a linear convex combination of the Kullback-Leibler (KL) divergences associated with each posterior distribution. We find this distribution in closed form. The estimated HR images are compared with images provided by other SR reconstruction methods. {\textcopyright} EURASIP, 2010.}, author = {Villena, Salvador and Vega, Miguel and Molina, Rafael and Katsaggelos, Aggelos K. and Salvador, Villena and Miguel, Vega and Rafael, Molina and Aggelos, K Katsaggelos}, booktitle = {2010 18th European Signal Processing Conference}, issn = {22195491}, pages = {616--620}, title = {{Image prior combination in super-resolution image reconstruction}}, year = {2010} }
@inproceedings{Eren2010b, author = {Soyak, E. and Tsaftaris, S. A. and Katsaggelos, A. K.}, booktitle = {2010 IEEE International Conference on Acoustics, Speech and Signal Processing}, doi = {10.1109/ICASSP.2010.5495044}, isbn = {978-1-4244-4295-9}, pages = {730--733}, publisher = {IEEE}, title = {{Content-aware H.264 encoding for traffic video tracking applications}}, url = {http://ieeexplore.ieee.org/document/5495044/}, year = {2010} }
@inproceedings{Matthew2010, abstract = {This paper presents a computationally efficient method for the measurement of a dense image correspondence vector field using supplementary data from an inertial navigation sensor. The application is suited to airborne imaging systems (such as on a UAV) where size, weight, and power restrictions limit the amount of onboard processing available. The limited processing will typically exclude the use of traditional, but expensive, optical flow algorithms such as Lucas-Kanade. Alternately, the measurements from an inertial navigation sensor lead to a closed-form solution to the correspondence field. Airborne platforms are also well suited to this application because they already possess inertial navigation sensors and global positioning systems (GPS) as part of their existing avionics package. We derive the closed form solution for the image correspondence vector field based on the inertial navigation sensor data. We then show experimentally that the inertial sensor solution outperforms traditional optical flow methods both in processing speed and accuracy. {\textcopyright} EURASIP, 2010.}, author = {Woods, Matthew and Katsaggelos, Aggelos}, booktitle = {European Signal Processing Conference}, issn = {22195491}, pages = {606--610}, title = {{Efficient image correspondence measurements in airborne applications using inertial navigation sensors}}, volume = {30}, year = {2010} }
@inproceedings{Salvador2010a, abstract = {This paper is devoted to the combination of image priors in Super Resolution (SR) image reconstruction. Taking into account that each combination of a given observation model and a prior model produces a different posterior distribution of the underlying High Resolution (HR) image, the use of variational posterior distribution approximation on each posterior will produce as many posterior approximations as priors we want to combine. A unique approximation is obtained here by finding the distribution on the HR image given the observations that minimizes a linear convex combination of the Kullback-Leibler divergences associated with each posterior distribution. We find this distribution in closed form and also relate the proposed approach to other prior combination methods in the literature. The estimated HR images are compared with images provided by other SR reconstruction methods. {\textcopyright} 2010 IEEE.}, author = {Villena, Salvador and Vega, Miguel and Babacan, S. Derin and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {2010 IEEE International Conference on Image Processing}, doi = {10.1109/ICIP.2010.5650444}, isbn = {978-1-4244-7992-4}, issn = {15224880}, keywords = {Bayesian methods,Combination of priors,Parameter estimation,Super resolution,Variational methods}, month = {sep}, pages = {893--896}, publisher = {IEEE}, title = {{Using the Kullback-Leibler divergence to combine image priors in Super-Resolution image reconstruction}}, url = {http://ieeexplore.ieee.org/document/5650444/}, year = {2010} }
@inproceedings{Miguel2009, abstract = {Bayesian methods rely on image priors that encapsulate prior image knowledge and avoid the ill-posedness of image restoration problems. In this paper a new prior based on the l1 norm of vertical and horizontal first order differences of image pixel values is introduced and its parameters are estimated . The results obtained from its application studied and compared with the ones provided by other methods in the literature. {\textcopyright} 2009 IEEE.}, author = {Vega, Miguel and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {2009 16th International Conference on Digital Signal Processing}, doi = {10.1109/ICDSP.2009.5201084}, isbn = {978-1-4244-3297-4}, month = {jul}, pages = {1--6}, publisher = {IEEE}, title = {{L1 prior majorization in Bayesian image restoration}}, url = {http://ieeexplore.ieee.org/document/5201084/}, year = {2009} }
@inproceedings{Ehsan2009a, abstract = {Efficient bit stream adaptation and resilience to packet losses are two critical requirements in scalable video coding for transmission over packet-lossy networks. These requirements have a greater significance in scalable H.264/AVC video bit streams since missing refinement information in a layer propagates to all lower layers in the prediction hierarchy and causes substantial degradation in video quality. This work proposes an algorithm to accurately estimate the overall distortion of the reconstructed frames due to enhancement layer truncation, drift/error propagation, and error concealment in the scalable H.264/AVC video. This ensures low computational cost since it bypasses highly complex pixel-level motion compensation operations. Simulation results show an accurate distortion estimation at various channel loss rates. The estimate is further integrated into a cross-layer optimization framework for optimized bit extraction and content-aware channel rate allocation. Experimental results demonstrate that precise distortion estimation enables our proposed transmission system to achieve a significantly higher average video PSNR compared to a conventional content independent system.}, author = {Maani, Ehsan and Katsaggelos, Aggelos K.}, booktitle = {2009 Picture Coding Symposium}, doi = {10.1109/PCS.2009.5167377}, isbn = {978-1-4244-4593-6}, keywords = {Channel coding,H.264/AVC,Scalable video coding,UEP}, month = {may}, pages = {1--4}, publisher = {IEEE}, title = {{Two-dimensional channel coding for scalable H.264/AVC video}}, url = {http://ieeexplore.ieee.org/document/5167377/}, year = {2009} }
@inproceedings{jiang2009detecting, abstract = {Many works have been proposed on detecting individual anomalies in crowd scenes, i.e., human behaviors anomalous with respect to the rest of the behaviors. In this paper, we introduce a new concept of contextual anomaly into the field of crowd analysis, i.e., the behaviors themselves are normal but they are anomalous in a specific context. Our system follows an unsupervised approach. It automatically discovers important contextual information from the crowd video and detects the blobs corresponding to contextually anomalous behaviors. Our experiments show that the approach works well in detecting contextual anomalies from crowd video with different motion contexts. {\textcopyright}2009 IEEE.}, author = {Jiang, Fan and Wu, Ying and Katsaggelos, Aggelos K. and {Fan Jiang} and {Ying Wu} and Katsaggelos, Aggelos K.}, booktitle = {2009 16th IEEE International Conference on Image Processing (ICIP)}, doi = {10.1109/ICIP.2009.5414535}, isbn = {978-1-4244-5653-6}, issn = {15224880}, keywords = {Anomaly detection,Clustering,Crowd analysis}, month = {nov}, organization = {IEEE}, pages = {1117--1120}, publisher = {IEEE}, title = {{Detecting contextual anomalies of crowd motion in surveillance video}}, url = {http://ieeexplore.ieee.org/document/5414535/}, year = {2009} }
@inproceedings{Martin2009a, abstract = {Methods for motion compensated frame rate upconversion exploit motion in order to generate interpolated frames that are temporally located between the available original frames of a video sequence. When the interpolated frames are inserted into the original sequence, the resulting sequence has a higher visual quality due to the increased frame rate. We propose a method for motion compensated frame rate upconversion which reduces upconversion artifacts by combining multiple intermediate interpolations utilizing median filtering. We use an efficient block based motion estimation method which makes use of motion vectors extracted from an H.264 bitstream. Low computational complexity makes the method suitable for real time operation. {\textcopyright}2009 IEEE.}, author = {Luessi, Martin and Katsaggelos, Aggelos K.}, booktitle = {2009 16th IEEE International Conference on Image Processing (ICIP)}, doi = {10.1109/ICIP.2009.5414501}, isbn = {978-1-4244-5653-6}, issn = {15224880}, keywords = {Frame rate upconversion,Motion estimation}, month = {nov}, pages = {373--376}, publisher = {IEEE}, title = {{Efficient motion compensated frame rate upconversion using multiple interpolations and median filtering}}, url = {http://ieeexplore.ieee.org/document/5414501/}, year = {2009} }
@inproceedings{katsaggelos2009content, author = {Katsaggelos, Aggelos K}, booktitle = {Proceedings of the 6th WSEAS international conference on Engineering education}, number = {2}, organization = {WSEAS}, pages = {15}, title = {{Keynote lecture 3: content-adaptive efficient resource allocation for packet-based video transmission}}, year = {2009} }
@inproceedings{maani2009scalable, author = {Maani, Ehsan and Pahalawatta, Peshala V. and Berry, Randall and Katsaggelos, Aggelos K.}, booktitle = {Applications of Digital Image Processing XXXII}, doi = {10.1117/12.829402}, editor = {Tescher, Andrew G.}, isbn = {9780819477330}, issn = {0277786X}, month = {aug}, pages = {74430C}, title = {{Content-aware packet scheduling for multiuser scalable video delivery over wireless networks}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?doi=10.1117/12.829402}, volume = {7443}, year = {2009} }
@inproceedings{Salvador2009a, abstract = {Abstract: This paper deals with the problem of high-resolution (HR) image reconstruction, from a set of degraded, undersampled, shifted and rotated images, under the Bayesian paradigm, utilizing a variational approximation. Bayesian methods rely on image models that encapsulate prior image knowledge and avoid the ill-posedness of the image restoration problems. In this paper a new prior based on the ℓ1 norm of vertical and horizontal first order differences of image pixel values is introduced and its parameters are estimated. The estimated HR images are compared with images provided by other HR reconstruction methods.}, author = {Villena, Salvador and Vega, Miguel and Molina, Rafael and Katsaggelos, A.K.}, booktitle = {2009 Proceedings of 6th International Symposium on Image and Signal Processing and Analysis}, doi = {10.1109/ISPA.2009.5297740}, isbn = {978-953-184-135-1}, month = {sep}, pages = {152--157}, publisher = {IEEE}, title = {{Bayesian Super-Resolution image reconstruction using an l1 prior}}, url = {http://ieeexplore.ieee.org/document/5297740/}, year = {2009} }
@inproceedings{babacan2009compressive, abstract = {We propose a novel camera design for light field image acquisition using compressive sensing. By utilizing a randomly coded non-refractive mask in front of the aperture, incoherent measurements of the light passing through different regions are encoded in the captured images. A novel reconstruction algorithm is proposed to recover the original light field image from these acquisitions. Using the principles of compressive sensing, we demonstrate that light field images with high angular dimension can be captured with only a few acquisitions. Moreover, the proposed design provides images with high spatial resolution and signal-to-noise-ratio (SNR), and therefore does not suffer from limitations common to existing light-field camera designs. Experimental results demonstrate the efficiency of the proposed system. {\textcopyright}2009 IEEE.}, author = {Babacan, S. Derin and Ansorge, Reto and Luessi, Martin and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {2009 16th IEEE International Conference on Image Processing (ICIP)}, doi = {10.1109/ICIP.2009.5414462}, isbn = {978-1-4244-5653-6}, issn = {15224880}, keywords = {Bayesian methods,Coded aperture imaging,Compressive sensing,Computational photography,Light-fields}, month = {nov}, organization = {IEEE}, pages = {2337--2340}, publisher = {IEEE}, title = {{Compressive sensing of light fields}}, url = {http://ieeexplore.ieee.org/document/5414462/}, year = {2009} }
@inproceedings{Luis2009, author = {Mancera, L. and Babacan, S Derin and Molina, R. and Katsaggelos, A. K.}, booktitle = {2009 16th IEEE International Conference on Image Processing (ICIP)}, doi = {10.1109/ICIP.2009.5413795}, isbn = {978-1-4244-5653-6}, month = {nov}, pages = {3949--3952}, publisher = {IEEE}, title = {{Image restoration by mixture modelling of an overcomplete linear representation}}, url = {http://ieeexplore.ieee.org/document/5413795/}, year = {2009} }
@inproceedings{babacan2009non, abstract = {We propose a novel Bayesian formulation for the reconstruction from compressed measurements. We demonstrate that high-sparsity enforcing priors based on l p-norms, with 0 < p ≤ 1, can be used within a Bayesian framework by majorization-minimization methods. By employing a fully Bayesian analysis of the compressed sensing system and a variational Bayesian analysis for inference, the proposed framework provides model parameter estimates along with the unknown signal, as well as the uncertainties of these estimates. We also show that some existing methods can be derived as special cases of the proposed framework. Experimental results demonstrate the high performance of the proposed algorithm in comparison with commonly used methods for compressed sensing recovery. {\textcopyright} EURASIP, 2009.}, author = {Babacan, S. Derin and Mancera, Luis and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {European Signal Processing Conference}, issn = {22195491}, organization = {IEEE}, pages = {110--114}, title = {{Non-convex priors in Bayesian compressed sensing}}, year = {2009} }
@inproceedings{Javier2009, abstract = {In this paper we present a new Bayesian methodology for the restoration of blurred and noisy images. Bayesian methods rely on image priors that encapsulate prior image knowledge and avoid the ill-posedness of image restoration problems. We use a spatially varying image prior utilizing a Gamma-Normal hyperprior distribution on the local precision parameters. This kind of hyperprior distribution, which to our knowledge has not been used before in image restoration, allows for the incorporation of information on local as well as global image variability, models correlation of the local precision parameters and is a conjugate hyperprior to the image model used in the paper. The proposed restoration technique is compared with other image restoration approaches, demonstrating its improved performance. {\textcopyright}2009 IEEE.}, author = {Mateos, Javier and Bishop, Tom E. and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {2009 16th IEEE International Conference on Image Processing (ICIP)}, doi = {10.1109/ICIP.2009.5414169}, isbn = {978-1-4244-5653-6}, issn = {15224880}, keywords = {Bayes procedures,Gamma-normal distributions,Image restoration,Variational methods}, month = {nov}, pages = {129--132}, publisher = {IEEE}, title = {{Local Bayesian image restoration using variational methods and Gamma-Normal distributions}}, url = {http://ieeexplore.ieee.org/document/5414169/}, year = {2009} }
@inproceedings{Li2009, abstract = {In this paper, we propose a fast and accurate video retrieval algorithm using random projections, an indexing structure and parallel computing. The video sequences are represented by low dimensional temporal trajectories in a set of low dimensional spaces through scaling and random projections. A kd-tree structure is used for efficient data access. We also develop an efficient retrieval algorithm. Simulation results demonstrate that the proposed algorithm is very fast and accurate in retrieval performance. {\textcopyright}2009 IEEE.}, author = {Gao, Li and Li, Zhu and Katsaggelos, Aggelos K.}, booktitle = {2009 16th IEEE International Conference on Image Processing (ICIP)}, doi = {10.1109/ICIP.2009.5414223}, isbn = {978-1-4244-5653-6}, issn = {15224880}, keywords = {Compressive sensing,Kd-tree,Random projections,Video indexing and retrieval}, month = {nov}, pages = {797--800}, publisher = {IEEE}, title = {{A video retrieval algorithm using random projections}}, url = {http://ieeexplore.ieee.org/document/5414223/}, year = {2009} }
@inproceedings{Esteban2009, abstract = {In this paper, we propose a novel algorithm for image reconstruction from compressive measurements of wavelet coefficients. By incorporating independent Laplace priors on separate wavelet sub-bands, the inhomogeneity of wavelet coefficient distributions and therefore the structural sparsity within images are modeled effectively. We model the problem by adopting a Bayesian formulation, and develop a fast greedy reconstruction algorithm. Experimental results demonstrate that the reconstruction performance of the proposed algorithm is competitive with state-of-the-art methods while outperforming them in terms of running times. {\textcopyright} 2009 IEEE.}, author = {Vera, Esteban and Mancera, Luis and Babacan, S. Derin and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {2009 IEEE/SP 15th Workshop on Statistical Signal Processing}, doi = {10.1109/SSP.2009.5278598}, isbn = {978-1-4244-2709-3}, keywords = {Bayesian methods,Compressive sensing,Signal reconstruction,Wavelet transforms}, month = {aug}, pages = {229--232}, publisher = {IEEE}, title = {{Bayesian compressive sensing of wavelet coefficients using multiscale Laplacian priors}}, url = {http://ieeexplore.ieee.org/document/5278598/}, year = {2009} }
@inproceedings{Louis2008, abstract = {This work extends and improves a recently introduced (Dec. 2007) dynamic Bayesian network (DBN) based audio-visual automatic speech recognition (AVASR) system. That system models the audio and visual components of speech as being composed of the same sub-word units when, in fact, this is not psycholinguistically true. We extend the system to model the audio and visual streams as being composed of separate, yet related, sub-word units. We also introduce a novel stream weighting structure incorporated into the model itself In recognition accuracy in a large vocabulary continuous speech recognition task (LVCSR). The "best" performing proposed system attains a WER of 66.71% whereas the "best" baseline system performs at a WER of 64.30%. The proposed system also improves accuracy to 45.95%from 39.40%. {\textcopyright} 2008 IEEE.}, author = {Terry, Louis and Katsaggelos, Aggelos K.}, booktitle = {2008 19th International Conference on Pattern Recognition}, doi = {10.1109/ICPR.2008.4761927}, isbn = {978-1-4244-2174-9}, issn = {1051-4651}, month = {dec}, pages = {1--4}, publisher = {IEEE}, title = {{A phone-viseme dynamic Bayesian network for audio-visual automatic speech recognition}}, url = {http://ieeexplore.ieee.org/document/4761927/}, year = {2008} }
@inproceedings{gao2008kd, abstract = {Efficient indexing is a key in content-based video retrieval solutions. In this paper we propose a new dynamic indexing scheme based on the kd-tree structure. Video sequences are first represented as traces in an appropriate low dimensional space via luminance field scaling and PCA projection. Then, the indexing scheme is applied to give the video database a manageable structure. Being able to handle dynamic video clip insertions and deletions is an essential part of this solution. At the beginning, an ordinary kd-tree is created for the initial database. As new video traces are added to the database, they will be added to the indexing tree structure as well. A tree node will be split if its size exceeds a certain threshold. If the tree structure un-balance level exceeds a threshold, merging and re-splitting will be performed. Preliminary experiments showed that merging and re-splitting will ensure the efficiency of the indexing scheme. {\textcopyright} 2008 IEEE.}, author = {{Li Gao} and {Zhu Li} and Katsaggelos, Aggelos K A.K. and Gao, Li and Li, Zhu and Katsaggelos, Aggelos K A.K.}, booktitle = {2008 Proceedings of 17th International Conference on Computer Communications and Networks}, doi = {10.1109/ICCCN.2008.ECP.174}, isbn = {978-1-4244-2389-7}, issn = {10952055}, month = {aug}, organization = {IEEE}, pages = {1--5}, publisher = {IEEE}, title = {{A kd-tree based dynamic indexing scheme for video retrieval and geometry matching}}, url = {http://ieeexplore.ieee.org/document/4674333/}, year = {2008} }
@inproceedings{Sotirios2008, abstract = {In this paper an algorithm to detect and elastically match the contours of the epicardial walls of the left ventricle (LV) in cardiac phase-resolved 2-D Magnetic Resonance (MR) images is presented. For both tasks, dynamic programming (DP) is used. A mask conforming to the six segment model of the LV is fitted on a reference image and propagated utilizing the elastic matching information. At its present form the algorithm requires minimal parameter corrections among different sets of cine MRI images. Future extensions include comparisons with contours hand labeled by imaging experts. {\textcopyright} 2008 IEEE.}, author = {Tsaftaris, S.A. and Andermatt, V. and Schlegel, A. and Katsaggelos, A.K. and Li, D. and Dharmakumar, R.}, booktitle = {2008 15th IEEE International Conference on Image Processing}, doi = {10.1109/ICIP.2008.4712421}, isbn = {978-1-4244-1765-0}, issn = {15224880}, keywords = {Detection,Dynamic programming,Magnetic resonance imaging,Matching,Registration}, pages = {2980--2983}, publisher = {IEEE}, title = {{A dynamic programming solution to tracking and elastically matching left ventricular walls in cardiac cine MRI}}, url = {http://ieeexplore.ieee.org/document/4712421/}, year = {2008} }
@inproceedings{Sotirios2008b, abstract = {Due to the mechanics of the Atomic Force Microscope (AFM), there is a curvature distortion (bowing effect) present in the acquired images. At present, flattening such images requires human intervention to manually segment object data from the background, which is time consuming and highly inaccurate. In this paper, an automated algorithm to flatten lines from AFM images is presented. The proposed method classifies the data into objects and background, and fits convex lines in an iterative fashion. Results on real images from DNA wrapped carbon nanotubes (DNACNTs) and synthetic experiments are presented, demonstrating the effectiveness of the proposed algorithm in increasing the resolution of the surface topography. In addition a link between the flattening problem and MRI inhomogeneity (shading) is given and the proposed method is compared to an entropy based MRI inhomogeniety correction method. copyright by EURASIP.}, author = {Tsaftaris, S. A. and Zujovic, J. and {K. Katsaggelos}, A.}, booktitle = {European Signal Processing Conference}, issn = {22195491}, pages = {1--5}, title = {{Restoration of the cantilever bowing distortion in Atomic Force Microscopy images}}, year = {2008} }
@inproceedings{babacan2008combination, abstract = {For most MR imaging applications multiple surface coils are used to obtain images with high signal-to-noise ratios (SNR). However, signal intensity strongly diminishes with distance. Although there are a number of approaches to combine the surface coil images to obtain a high SNR and bias-free image, most of them are developed in an ad hoc manner and lack a systematic treatment. In this work we propose a new approach, an iterative weighted constrained least squares (WCLS) restoration method, for combining surface coil images. The algorithm is fully automated and outperforms approaches which appeared in the literature. {\textcopyright} 2008 IEEE.}, author = {Babacan, S. Derin and {Xiaoming Yin} and Larson, Andrew C. and Katsaggelos, Aggelos K.}, booktitle = {2008 15th IEEE International Conference on Image Processing}, doi = {10.1109/ICIP.2008.4712235}, isbn = {978-1-4244-1765-0}, issn = {15224880}, keywords = {Image restoration,Least squares methods,Magnetic resonance imaging,Parameter estimation}, organization = {IEEE}, pages = {2236--2239}, publisher = {IEEE}, title = {{Combination of MR surface coil images using weighted constrained least squares}}, url = {http://ieeexplore.ieee.org/document/4712235/}, year = {2008} }
@inproceedings{Louis2008b, abstract = {We describe a vector quantizer (VQ) with memory for automatic speech recognition (ASR) and compare the recognition performance results to those obtained with traditional mem-oryless VQ for ASR. Standard VQ for ASR quantizes the speech data independently of any past information. We introduce memory in a probabilistic framework for quantization state modeling. This is accomplished in the form of an ergodic hidden Markov model (HMM) in which the state occupied by the HMM represents the quantization label. We evaluate this approach in the context of video-only isolated digit ASR and implement both single stream (single labeling) and multi-stream (multi-labeling) systems. For single stream recognition, our approach increases the recognition rate from 62.67% to 66.95%. When using multi-labeling, our proposed vector quantizer with memory consistently outperforms the memoryless vector quantizer. {\textcopyright} 2008 IEEE.}, author = {Terry, Louis H. and Shiell, Derek J. and Katsaggelos, Aggelos K.}, booktitle = {2008 15th IEEE International Conference on Image Processing}, doi = {10.1109/ICIP.2008.4712006}, isbn = {978-1-4244-1765-0}, issn = {15224880}, keywords = {Hidden Markov models,Speech recognition,Vector quantization}, pages = {1320--1323}, publisher = {IEEE}, title = {{Vector quantization with memory and multi-labeling for isolated video-only automatic speech recognition}}, url = {http://ieeexplore.ieee.org/document/4712006/}, year = {2008} }
@inproceedings{Bruno2008, abstract = {In this paper we examine the use of logarithmic opinion pooling techniques to combine two observations models that are normally used in multi-channel image restoration techniques. The combined observation model is used together with simultaneous autoregression prior models for the image and blurs to define the joint distribution of image, blurs and observations. Assuming that all the unknown parameters are previously estimated we use variational techniques to approximate the posterior distribution of the real underlying image and the unknown blurs. We will examine the use of two approximations of the posterior distribution. Experimental results are used to validate the proposed approach.}, author = {Amizic, Bruno and Katsaggelos, Aggelos K. and Molina, Rafael}, booktitle = {Proceedings of the Third International Conference on Computer Vision Theory and Applications}, doi = {10.5220/0001091405650570}, isbn = {978-989-8111-21-0}, keywords = {Bayesian framework,Blind multi-channel restoration,Logarithmic opinion pooling,Variational methods}, pages = {565--570}, publisher = {SciTePress - Science and and Technology Publications}, title = {{USING LOGARITHMIC OPINION POOLING TECHNIQUES IN BAYESIAN BLIND MULTI-CHANNEL RESTORATION}}, url = {http://www.scitepress.org/DigitalLibrary/Link.aspx?doi=10.5220/0001091405650570}, volume = {1}, year = {2008} }
@inproceedings{Derek2008, author = {Shiell, Derek J. and Xiao, Jing and Katsaggelos, Aggelos K.}, booktitle = {Applications of Digital Image Processing XXXI}, doi = {10.1117/12.796748}, editor = {Tescher, Andrew G.}, isbn = {9780819472939}, issn = {0277786X}, month = {aug}, pages = {70730Q}, title = {{Sub-component modeling for face image reconstruction in video communications}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?doi=10.1117/12.796748}, volume = {7073}, year = {2008} }
@inproceedings{Sotirios2008a, abstract = {In this paper, an automated algorithm to flatten lines from Atomic Force Microscopy (AFM) images is presented. Due to the mechanics of the AFM, there is a curvature distortion (bowing effect) present in the acquired images. At present, flattening such images requires human intervention to manually segment object data from the background, which is time consuming and highly inaccurate. The proposed method classifies the data into objects and background, and fits convex lines in an iterative fashion. Results on real images from DNA wrapped carbon nanotubes (DNA-CNTs) and synthetic experiments are presented, demonstrating the effectiveness of the proposed algorithm in increasing the resolution of the surface topography. {\textcopyright} 2008 IEEE.}, author = {Tsaftaris, S. A. and Zujovic, J. and Katsaggelos, A. K.}, booktitle = {2008 15th IEEE International Conference on Image Processing}, doi = {10.1109/ICIP.2008.4712418}, isbn = {978-1-4244-1765-0}, issn = {15224880}, keywords = {Curve fitting,Nanotechnology,Object detection,Polynomial approximation}, pages = {2968--2971}, publisher = {IEEE}, title = {{Automated line flattening of Atomic Force Microscopy images}}, url = {http://ieeexplore.ieee.org/document/4712418/}, year = {2008} }
@inproceedings{Louis2008a, abstract = {Most current audio-visual automatic speech recognition (AV-ASR) systems use static weights to leverage between audio and visual information during information fusion. State of the art research has led to using audio reliability metrics for dynamically changing the fusion weights in order to successfully improve overall recognition results. So far, however, incorporating visual reliability metrics into these audio reliability metric based systems have not significantly improved performance. We introduce a new approach to this problem by inferring the "consistency" between the audio and visual information and leveraging the existing audio reliability metrics to create a video reliability metric. Our approach is formulated in the extractedfeature space and, thus, does not rely on analyzing the actual video signalitself. The framework presented in this work competes with the audio-onlyreliability metric based systems and shows promise to consistently outperform. {\textcopyright} 2008 IEEE.}, author = {Terry, Louis H. and Shiell, Derek J. and Katsaggelos, Aggelos K.}, booktitle = {2008 15th IEEE International Conference on Image Processing}, doi = {10.1109/ICIP.2008.4712005}, isbn = {978-1-4244-1765-0}, issn = {15224880}, keywords = {Hidden Markov models,Speech recognition,Vector quantization}, pages = {1316--1319}, publisher = {IEEE}, title = {{Feature space video stream consistency estimation for dynamic stream weighting in audio-visual speech recognition}}, url = {http://ieeexplore.ieee.org/document/4712005/}, year = {2008} }
@inproceedings{Dalei2008, abstract = {Video transport over multi-hop wireless networks has received significant research interests recently. The majority of the research efforts in this field have been conducted taking the approach of cross-layer optimization. However, video content and user perceived quality have been largely ignored in existing work. In this paper, we integrate video content analysis into video transport over wireless mesh networks (WMN). A content-aware quality-driven cross-layer optimization framework is proposed to achieve the best end-to-end user perceived video quality. In our framework, the extracted video regions of interest (ROI) are discriminatingly coded, transmitted and protected in video encoding, network routing and packet scheduling by different network layers. We aim at the optimization of key parameters of each layer while focusing on their interactions across the holistic network protocol stack. The proposed framework is evaluated by H.264/AVC codec and WMN simulations. Experimental results demonstrate that the proposed framework can effectively provide a good user perceived video quality, especially when the delay requirement is stringent. {\textcopyright} 2008 IEEE.}, author = {Wu, Dalei and Luo, Haiyan and Ci, Song and Wang, Haohong and Katsaggelos, Aggelos}, booktitle = {IEEE GLOBECOM 2008 - 2008 IEEE Global Telecommunications Conference}, doi = {10.1109/GLOCOM.2008.ECP.350}, isbn = {978-1-4244-2324-8}, pages = {1--5}, publisher = {IEEE}, title = {{Quality-Driven Optimization for Content-Aware Real-Time Video Streaming in Wireless Mesh Networks}}, url = {http://ieeexplore.ieee.org/document/4698125/}, year = {2008} }
@inproceedings{babacan2008total, abstract = {In this paper we propose a novel algorithm for super resolution based on total variation prior and variational distribution approximations. We formulate the problem using a hierarchical Bayesian model where the reconstructed high resolution image and the model parameters are estimated simultaneously from the low resolution observations. The algorithm resulting from this formulation utilizes variational inference and provides approximations to the posterior distributions of the latent variables. Due to the simultaneous parameter estimation, the algorithm is fully automated so parameter tuning is not required. Experimental results show that the proposed approach outperforms some of the state-of-the-art super resolution algorithms. {\textcopyright} 2008 IEEE.}, author = {Babacan, S. Derin and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {2008 15th IEEE International Conference on Image Processing}, doi = {10.1109/ICIP.2008.4711836}, isbn = {978-1-4244-1765-0}, issn = {15224880}, keywords = {Bayesian methods,Parameter estimation,Super resolution,Total variation,Variational methods}, organization = {IEEE}, pages = {641--644}, publisher = {IEEE}, title = {{Total variation super resolution using a variational approach}}, url = {http://ieeexplore.ieee.org/document/4711836/}, year = {2008} }
@inproceedings{maani2008local, abstract = {In this paper a new content-based copy identification method for video sequences is presented. It is robust to a number of image transformations and particulary robust to compression artifacts. A scale and rotation invariant local image descriptor for corner points in detected key frames is proposed based on a generalized Radon transform. In addition, a distance similarity metric is used that fuses intensity and geometry information to compare key frames extracted using a scene detection algorithm. Furthermore, to achieve low querying computational complexity a DP approach is employed. Experimental results demonstrate the effectiveness of our approach. {\textcopyright} 2008 IEEE.}, author = {Maani, Ehsan and Tsaftaris, Sotirios A. and Katsaggelos, Aggelos K.}, booktitle = {2008 15th IEEE International Conference on Image Processing}, doi = {10.1109/ICIP.2008.4712105}, isbn = {978-1-4244-1765-0}, issn = {15224880}, keywords = {Copyright protection,Digital video fingerprinting}, organization = {IEEE}, pages = {1716--1719}, publisher = {IEEE}, title = {{Local feature extraction for video copy detection in a database}}, url = {http://ieeexplore.ieee.org/document/4712105/}, year = {2008} }
@inproceedings{jiang2008abnormal, abstract = {Clustering-based approaches for abnormal video event detection have been proven to be effective in the recent literature. Based on the framework proposed in our previous work [1], we have developed in this paper a new strategy for unsupervised trajectory clustering. More specifically, an information-based trajectory dissimilarity measure is proposed, based on the Bayesian information criterion (BIC). In order to minimize BIC, the agglomerative hierarchical clustering is applied using a 2-depth greedy search process. This strategy achieves better clustering results compared to the traditional 1-depth greedy search. The increased computational complexity is addressed with several bounds on the trajectory dissimilarity. {\textcopyright}2008 IEEE.}, author = {{Fan Jiang} and {Ying Wu} and Katsaggelos, Aggelos K. and Jiang, Fan and Wu, Ying and Katsaggelos, Aggelos K.}, booktitle = {2008 IEEE International Conference on Acoustics, Speech and Signal Processing}, doi = {10.1109/ICASSP.2008.4518063}, isbn = {978-1-4244-1483-3}, issn = {1520-6149}, keywords = {Event detection,Unsupervised clustering,Video surveillance}, month = {mar}, organization = {IEEE}, pages = {2129--2132}, publisher = {IEEE}, title = {{Abnormal event detection based on trajectory clustering by 2-depth greedy search}}, url = {http://ieeexplore.ieee.org/document/4518063/}, year = {2008} }
@inproceedings{babacan2008parameter, abstract = {In this paper we present a methodology for parameter estimation in total variation (TV) blind deconvolution. By formulating the problem in a Bayesian framework, the unknown image, blur and the model parameters are simultaneously estimated. The resulting algorithms provide approximations to the posterior distributions of the unknowns by utilizing variational distribution approximations. We show that some of the current approaches towards TV-based blind deconvolution are special cases of our formulation. Experimental results are provided to demonstrate the performance of the algorithms. copyright by EURASIP.}, author = {Babacan, S. Derin and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {European Signal Processing Conference}, issn = {22195491}, organization = {IEEE}, pages = {1--5}, title = {{Parameter estimation in total variation blind deconvolution}}, year = {2008} }
@inproceedings{babacan2008generalized, abstract = {In this paper we propose novel algorithms for image restoration and parameter estimation with a Generalized Gaussian Markov Random Field (GGMRF) prior utilizing variational distribution approximation. The restored image and the unknown hyperparameters for both the image prior and the image degradation noise are simultaneously estimated within a hierarchical Bayesian framework. We develop two algorithms resulting from this formulation which provide approximations to the posterior distributions of the latent variables. Experimental results are provided to demonstrate the performance of the algorithms. {\textcopyright}2008 IEEE.}, author = {{Derin Babacan}, S. and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {2008 IEEE International Conference on Acoustics, Speech and Signal Processing}, doi = {10.1109/ICASSP.2008.4517847}, isbn = {978-1-4244-1483-3}, issn = {1520-6149}, keywords = {Bayesian methods,Generalized gaussian Markov random fields,Image restoration,Parameter estimation,Variational methods}, month = {mar}, organization = {IEEE}, pages = {1265--1268}, publisher = {IEEE}, title = {{Generalized Gaussian Markov random field image restoration using variational distribution approximation}}, url = {http://ieeexplore.ieee.org/document/4517847/}, year = {2008} }
@inproceedings{Rafael2007a, author = {Rafael, Molina and Javier, Mateos and Miguel, Vega and Aggelos, K Katsaggelos}, booktitle = {2007 15th European Signal Processing Conference}, pages = {1497--1501}, title = {{Super resolution of multispectral images using locally adaptive models}}, year = {2007} }
@inproceedings{Derek2007, abstract = {Biometrics has been a topic of great interest since the advent of the information age and will soon lead to a safer and simpler lifestyle where passcodes and keys are inherent to the useR. We describe a system capable of automatically extracting visual features from a human face for use in dynamic visual biometrics. Automatic speech and speaker recognition has recently moved towards incorporating visual information to improve upon audio-only recognition systems. With few exceptions, however, investi-gations into audio-visual and visual-only automatic speech and speaker recognition have utilized ideal visual databases in their audio-visual (AV-ASR) and visual-only automatic speech recognition (V-ASR) experiments. Our system incorporates robust and efficient computer vision algorithms to automatically detect, track and identify a speaker based on visual features extracted from the speaker's mouth region. The features are extracted in real-time, in adverse visual conditions. The system recognition perfor-mance is evaluated by comparing speaker recognition results found using automatic tracking data with those found using ground truth tracking data. Speaker recognition results found using ground truth and automatic tracking data are 52.3% and 59.3%, respectively. The results are discussed and future improvements and experiments are suggested.}, author = {Shiell, Derek J. and Terry, Louis H. and Aleksic, Petar S. and Katsaggelos, Aggelos K.}, booktitle = {45th Annual Allerton Conference on Communication, Control, and Computing 2007}, isbn = {9781605600864}, pages = {869--876}, title = {{An automated system for visual biometrics}}, volume = {2}, year = {2007} }
@inproceedings{Sotirios2007a, abstract = {In this paper a simulation of single query searches in very large DNA-based databases that are capable of storing and retrieving digital signals is presented. Similarly to the digital domain, a signal-to-noise ratio (SNR) measure to assess the performance of the DNA-based retrieval scheme in terms of database size and source statistics is defined. With approximations, it is shown that the SNR of any finite size DNA-based database is upper bounded by the SNR of an infinitely large one with the same source distribution. Computer simulations are presented to validate the theoretical outcomes. {\textcopyright} 2007 EURASIP.}, author = {Tsaftaris, Sotirios A. and Katsaggelos, Aggelos K.}, booktitle = {European Signal Processing Conference}, isbn = {9788392134022}, issn = {22195491}, pages = {1561--1565}, title = {{Retrieval accuracy of very large DNA-based databases of digital signals}}, year = {2007} }
@inproceedings{Rafael2007c, abstract = {Following the Bayesian framework we propose a method to reconstruct emission tomography images which uses gamma mixture prior and variational methods to approximate the posterior distribution of the unknown parameters and image instead of estimating them by using the Evidence Analysis or alternating between the estimation of parameters and image (Iterated Conditional Mode (ICM)) approach. By analyzing the posterior distribution approximation we can examine the quality of the proposed estimates. The method is tested on real Single Positron Emission Tomography (SPECT) images.}, author = {Molina, Rafael and L{\'{o}}pez, Antonio and Martin, Jos{\'{e}} Manuel and Katsaggelos, Aggelos K.}, booktitle = {Proceedings of the Second International Conference on Computer Vision Theory and Applications}, doi = {10.5220/0002066001650173}, isbn = {978-972-8865-75-7}, keywords = {Bayesian framework,Image reconstruction,Parameter estimation,Tomography images,Variational methods}, pages = {165--173}, publisher = {SciTePress - Science and and Technology Publications}, title = {{VARIATIONAL POSTERIOR DISTRIBUTION APPROXIMATION IN BAYESIAN EMISSION TOMOGRAPHY RECONSTRUCTION USING A GAMMA MIXTURE PRIOR}}, url = {http://www.scitepress.org/DigitalLibrary/Link.aspx?doi=10.5220/0002066001650173}, volume = {SP}, year = {2007} }
@inproceedings{Zhu2007, abstract = {Peer-to-Peer (P2P) distribution has becoming an popular solution for IPTV applications. In this work, we define an utility function over the play back buffer content reserve, and develop a utility gradient based video segment transmission scheduling algorithm for uploading bandwidth allocation in P2P live streaming system, with the goal of minimizing play back freezes. Simulation results demonstrated the effectiveness of the proposed solution.}, author = {Li, Zhu and Huang, Jianwei and Katsaggelos, Aggelos K.}, booktitle = {45th Annual Allerton Conference on Communication, Control, and Computing 2007}, isbn = {9781605600864}, pages = {563--567}, title = {{Content reserve utility based video segment transmission scheduling for Peer-to-Peer live video streaming system}}, volume = {1}, year = {2007} }
@inproceedings{Rafael2007, abstract = {In this paper we present a new Bayesian methodology for the restoration of blurred and noisy images. Bayesian methods rely on image priors that encapsulate prior image knowledge and avoid the ill-posedness of the image restoration problems. Some of these priors depend on global variance parameters, unable to account for local characteristics. Here we first use variational methods to approximate probability posterior distributions for the global model to later use those distributions to define local and more realistic image models which lead to better restored images as it is shown in the experimental section. {\textcopyright} 2007 IEEE.}, author = {Molina, Rafael and Vega, Miguel and Katsaggelos, Aggelos K.}, booktitle = {2007 IEEE International Conference on Image Processing}, doi = {10.1109/ICIP.2007.4378906}, isbn = {978-1-4244-1436-9}, issn = {1522-4880}, keywords = {Bayesian models,Image restoration,Parameter estimation,Regularization,Variational methods}, month = {sep}, pages = {I -- 121--I -- 124}, publisher = {IEEE}, title = {{From Global to Local Bayesian Parameter Estimation in Image Restoration using Variational Distribution Approximations}}, url = {http://ieeexplore.ieee.org/document/4378906/}, volume = {1}, year = {2007} }
@inproceedings{Ehsan2007a, abstract = {This paper addresses the problem of joint encoder optimization and channel coding for realtime video transmission over wireless channels. An efficient solution is proposed to optimally select macroblock modes and quantizers as well as channel coding rates. The proposed optimization algorithm fully considers error resilience, forward error correction and error concealment. Experimental results demonstrate the effectiveness of the proposed approach. {\textcopyright} 2007 IEEE.}, author = {Maani, Ehsan and Zhai, Fan and Katsaggelos, Aggelos K.}, booktitle = {2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07}, doi = {10.1109/ICASSP.2007.366039}, isbn = {1-4244-0727-3}, issn = {15206149}, keywords = {Error concealment,Error control,Error resilience,Multimedia streaming,Quality of service (QoS),Resource allocation,Unequal error protection (UEP)}, month = {apr}, pages = {I--841--I--844}, publisher = {IEEE}, title = {{Optimal Mode Selection and Channel Coding for Video Transmission Over Wireless Channels using H.264/AVC}}, url = {https://ieeexplore.ieee.org/document/4217211/}, volume = {1}, year = {2007} }
@inproceedings{Sotirios2007, abstract = {DNA microarrays are commonly used in the rapid analysis of gene expression in organisms. Image analysis is used to measure the average intensity of circular image areas (spots), which correspond to the level of expression of the genes. A crucial aspect of image analysis is the estimation of the background noise. Currently, background subtraction algorithms are used to estimate the local background noise and subtract it from the signal. In this paper we use Principal Component Analysis (PCA) to de-correlate the signal from the noise, by projecting each spot on the space of eigenvectors, which we term eigenspots. PCA is well suited for such application due to the structural nature of the images. To compare the proposed method with other background estimation methods we use the industry standard signal-to-noise metric xdev. {\textcopyright} 2007 IEEE.}, author = {Tsaftaris, Sotirios A. and Ahuja, Ramandeep and Shiell, Derek and Katsaggelos, Aggelos K.}, booktitle = {2007 IEEE International Conference on Image Processing}, doi = {10.1109/ICIP.2007.4379572}, isbn = {978-1-4244-1436-9}, issn = {15224880}, keywords = {Biochip,DNA microarray,Eigenspaces,Noise,Segmentation}, pages = {VI -- 265--VI -- 268}, publisher = {IEEE}, title = {{DNA Microarray Image Intensity Extraction using Eigenspots}}, url = {http://ieeexplore.ieee.org/document/4379572/}, volume = {6}, year = {2007} }
@inproceedings{molina2006blind, abstract = {In this paper we propose novel algorithms for total variation (TV) based blind deconvolution and parameter estimation utilizing a variational framework. Within a hierarchical Bayesian formulation, the reconstructed image, the blur and the unknown hyperparameters for the image prior, the blur prior and the image degradation noise are simultaneously estimated. We develop two algorithms resulting from this formulation which provide approximations to the posterior distributions of the latent variables. Different values can be drawn from these distributions as estimates to the latent variables and the uncertainty of these estimates can be measured. Experimental results are provided to demonstrate the performance of the algorithms. {\textcopyright} 2007 EURASIP.}, author = {Babacan, S. Derin and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {European Signal Processing Conference}, isbn = {9788392134022}, issn = {22195491}, number = {12}, pages = {2164--2168}, publisher = {IEEE}, title = {{Total variation blind deconvolution using a variational approach to parameter, image, and blur estimation}}, volume = {15}, year = {2007} }
@inproceedings{Stelios2007, abstract = {In this paper, the problem of optimum data detection in OFDM under severe phase noise (PHN) is addressed. Since direct maximization of the likelihood function is infeasible, the expectation-maximization (EM) algorithm is invoked as an iterative, feasible method of data detection. Two algorithms are proposed, one derived by direct application of the standard EM algorithm in the present context of OFDM data detection, whereas the other employs soft data estimates resulting in enhanced performance. The use of Kalman filtering is also examined as a means of complexity reduction and handling of the case of a non-negligible frequency offset (FO). The performance of the proposed algorithms is evaluated by simulations which show significant gains over the PHN-compensation method employed by OFDM-based standards.}, author = {Stefanatos, Stelios and Polydoros, Andreas and Katsaggelos, Aggelos K.}, booktitle = {2007 16th IST Mobile and Wireless Communications Summit}, doi = {10.1109/ISTMWC.2007.4299096}, isbn = {1-4244-1662-0}, month = {jul}, pages = {1--5}, publisher = {IEEE}, title = {{On the Detection of OFDM Signals in the Presence of Strong Phase Noise}}, url = {http://ieeexplore.ieee.org/document/4299096/}, year = {2007} }
@inproceedings{Babacan2007, abstract = {In this paper we propose novel algorithms for total variation (TV) based image restoration and parameter estimation utilizing variational distribution approximations. By following the hierarchical Bayesian framework, we simultaneously estimate the reconstructed image and the unknown hyperparameters for both the image prior and the image degradation noise. Our algorithms provide an approximation to the posterior distributions of the unknowns so that both the uncertainty of the estimates can be measured and different values from these distributions can be used for the estimates. We also show that some of the current approaches to TV-based image restoration are special cases of our variational framework. Experimental results show that the proposed approaches provide competitive performance witiiout any assumptions about unknown hyperparameters and clearly outperform existing methods when additional information is included. {\textcopyright} 2007 IEEE.}, author = {Babacan, S. Derin and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {2007 IEEE International Conference on Image Processing}, doi = {10.1109/ICIP.2007.4378900}, isbn = {978-1-4244-1436-9}, issn = {1522-4880}, keywords = {Bayesian methods,Image restoration,Parameter estimation,Total variation,Variational methods}, month = {sep}, pages = {I -- 97--I -- 100}, publisher = {IEEE}, title = {{Total Variation Image Restoration and Parameter Estimation using Variational Posterior Distribution Approximation}}, url = {http://ieeexplore.ieee.org/document/4378900/}, volume = {1}, year = {2007} }
@inproceedings{Aggelos2007g, author = {Katsaggelos, Aggelos K.}, booktitle = {2007 16th International Conference on Computer Communications and Networks}, doi = {10.1109/ICCCN.2007.4317781}, isbn = {978-1-4244-1250-1}, month = {aug}, pages = {xix--xix}, publisher = {IEEE}, title = {{Challenges and Opportunities in Video Transmission}}, url = {http://ieeexplore.ieee.org/document/4317781/}, year = {2007} }
@inproceedings{Zhu2007a, author = {Zhu, Li and Huang, J and Aggelos, K Katsaggelos}, booktitle = {Proceedings of 45th Annual Allerton Conference on Communication, Control, and Computing}, title = {{Utility driven video segment scheduling for peer-to-peer live video streaming system}}, year = {2007} }
@inproceedings{Ehsan2007, abstract = {Video streaming applications have gained in popularity in recent years. The quality of service offered by such applications is limited by the available transmission rates as well as timevarying conditions, such as, channel fading and network congestion, which lead to packet losses. Scalable video coding techniques that allow for the flexible adaptation of temporal resolution as well as quality of an encoded bitstream can be immensely useful in developing video streaming applications that can adapt to time-varying network and channel conditions. Scalable coding techniques, however, are generally designed to offer progressive refinement, which introduces dependencies between encoded video packets. Therefore, when determining a packet scheduling technique for scalable coded video, the possibility of random packet losses, which might affect the decodability of subsequent packets, must be taken into account. In this paper, we take into account the available transmission rate, possibly time-varying channel conditions, and the possibility of random packet losses, to design a scheduling technique for video packets in a scalable bitstream. Since the optimal solution to the scheduling problem requires an exhaustive, and therefore, intractable computation, we propose a greedy algorithm that will schedule the optimal packet for transmission at a given transmission opportunity based on the encoded content and the available channel state information. Simulation results show significant gains in performance when the proposed technique is compared to content and channel independent packet scheduling techniques.}, author = {Maani, Ehsan and Luo, Yijing and Pahalawatta, Peshala and Katsaggelos, Aggelos}, booktitle = {2007 16th International Conference on Computer Communications and Networks}, doi = {10.1109/ICCCN.2007.4317882}, isbn = {978-1-4244-1250-1}, issn = {10952055}, month = {aug}, pages = {591--596}, publisher = {IEEE}, title = {{Packet Scheduling for Scalable Video Streaming Over Lossy Packet Access Networks}}, url = {http://ieeexplore.ieee.org/document/4317882/}, year = {2007} }
@inproceedings{Jiang2007, abstract = {The clustering-based approach for detecting abnormalities in surveillance video requires the appropriate definition of similarity between events. The HMM-based similarity defined previously falls short in handling the overfitting problem. We propose in this paper a multi-sample-based similarity measure, where HMM training and distance measuring are based on multiple samples. These multiple training data are acquired by a novel dynamic hierarchical clustering (DHC) method. By iteratively reclassifying and retraining the data groups at different clustering levels, the initial training and clustering errors due to overfitting will be sequentially corrected in later steps. Experimental results on real surveillance video show an improvement of the proposed method over a baseline method that uses single-sample-based similarity measure and spectral clustering. {\textcopyright}2007 IEEE.}, author = {Jiang, Fan and Wu, Ying and Katsaggelos, Aggelos K.}, booktitle = {2007 IEEE International Conference on Image Processing}, doi = {10.1109/ICIP.2007.4379786}, isbn = {978-1-4244-1436-9}, issn = {15224880}, keywords = {Clustering,Event detection,Surveillance}, pages = {V -- 145--V -- 148}, publisher = {IEEE}, title = {{Abnormal Event Detection from Surveillance Video by Dynamic Hierarchical Clustering}}, url = {http://ieeexplore.ieee.org/document/4379786/}, volume = {5}, year = {2007} }
@inproceedings{Shengyang2007, abstract = {Component-based detection methods have demonstrated their promise by integrating a set of part-detectors to deal with large appearance variations of the target. However, an essential and critical issue, i.e., how to handle the imperfectness of part-detectors in the integration, is not well addressed in the literature. This paper proposes a detector ensemble model that consists of a set of substructure-detectors, each of which is composed of several part-detectors. Two important issues are studied both in theory and in practice, (1) finding an optimal detector ensemble, and (2) detecting targets based on an ensemble. Based on some theoretical analysis, a new model selection strategy is proposed to learn an optimal detector ensemble that has a minimum number of false positives and satisfies the design requirement on the capacity of tolerating missing parts. In addition, this paper also links ensemble-based detection to the inference in Markov random field, and shows that the target detection can be done by a max-product belief propagation algorithm. {\textcopyright} 2007 IEEE.}, author = {Dai, Shengyang and Yang, Ming and Wu, Ying and Katsaggelos, Aggelos}, booktitle = {2007 IEEE Conference on Computer Vision and Pattern Recognition}, doi = {10.1109/CVPR.2007.383274}, isbn = {1-4244-1179-3}, issn = {10636919}, month = {jun}, pages = {1--8}, publisher = {IEEE}, title = {{Detector Ensemble}}, url = {http://ieeexplore.ieee.org/document/4270299/}, year = {2007} }
@inproceedings{Fan2007, abstract = {Much attention has been paid to the problem of optimally utilizing resources such as spectrum, power and time in order to achieve the best video delivery quality in wireless communications system, due to the fueling demand for such applications. In this work, we present a joint source coding and data adaptation scheme for downlink video transmission in a multi-user wireless network. We formulate a rate-distortion optimization problem, where the source coding and data rate are jointly designed according to the changing channel conditions. In addition, transmissions of video packets are optimally scheduled through exploiting the multi-user diversity. We solve the problem using a backward stochastic dynamical programming approach, and the simulation results have shown the advantage of the joint selection of source coding parameter and transmission rate coupled with optimal packet scheduling. {\textcopyright} 2007 IEEE.}, author = {Zhai, Fan and Li, Zhu and Katsaggelos, Aggelos K.}, booktitle = {Multimedia and Expo, 2007 IEEE International Conference on}, doi = {10.1109/ICME.2007.4284811}, isbn = {1-4244-1016-9}, month = {jul}, pages = {959--962}, publisher = {IEEE}, title = {{Joint Source Coding and Data Rate Adaptation for Multi-User Wireless Video Transmission}}, url = {http://ieeexplore.ieee.org/document/4284811/}, volume = {21}, year = {2007} }
@inproceedings{Li2007, abstract = {Efficient indexing and robust retrieval are key features for an effective video retrieval system. In this paper we represent video sequences as traces in an appropriate low dimensional space via luminance field scaling and PCA projection, and introduce a combination of top-down and bottom-up strategies for indexing. Various means of introducing distortions in query clips are considered and several heuristics are developed to achieve robustness in retrieval performance. Simulation results demonstrate the effectiveness of the proposed solutions. {\textcopyright} 2007 IEEE.}, author = {Gao, Li and Li, Zhu and Katsaggelos, Aggelos K.}, booktitle = {2007 International Workshop on Content-Based Multimedia Indexing}, doi = {10.1109/CBMI.2007.385398}, isbn = {1-4244-1010-X}, month = {jun}, pages = {99--105}, publisher = {IEEE}, title = {{Robust Video Retrieval with Luminance Field Trace Indexing and Geometry Matching}}, url = {http://ieeexplore.ieee.org/document/4275061/}, year = {2007} }
@inproceedings{Peshala2007, abstract = {Wireless video transmission is prone to unpredictable degradations due to time-varying channel conditions, Such degradations are difficult to overcome using conventional video coding techniques. Scalable video coding offers a flexible bitstream that can be dynamically adapted to fit the prevailing channel conditions. Within a scalable video coding framework, we develop simple packet prioritization strategies, which, when combined with a reasonable error concealment scheme and a content-aware resource allocation technique, provide for robust video transmission over time-varying channels. The packet prioritization as well as the calculation of the contentaware scheduling metric can be performed offline and signaled to the wireless scheduler. {\textcopyright} 2007 IEEE.}, author = {Pahalawatta, Peshala V. and Pappas, Thrasyvoulos N. and Berry, Randall and Katsaggelos, Aggelos K.}, booktitle = {2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07}, doi = {10.1109/ICASSP.2007.366042}, isbn = {1-4244-0727-3}, issn = {15206149}, keywords = {Cross-layer design,Scalable video coding,Wireless video streaming}, month = {apr}, pages = {I--853--I--856}, publisher = {IEEE}, title = {{Content-Aware Resource Allocation for Scalable Video Transmission to Multiple Users Over a Wireless Network}}, url = {https://ieeexplore.ieee.org/document/4217214/}, volume = {1}, year = {2007} }
@inproceedings{Rafael2006, author = {Molina, Rafael and Vega, Miguel and Mateos, Javier and Katsaggelos, Aggelos K.}, booktitle = {2006 International Conference on Image Processing}, doi = {10.1109/ICIP.2006.312720}, isbn = {1-4244-0480-0}, month = {oct}, pages = {1749--1752}, publisher = {IEEE}, title = {{Parameter Estimation in Bayesian Reconstruction of Multispectral Images using Super Resolution Techniques}}, url = {https://ieeexplore.ieee.org/document/4106888/}, year = {2006} }
@inproceedings{Ehsan2006, author = {Ehsan, Maani and Aggelos, K Katsaggelos}, booktitle = {CCNC 2006. 2006 3rd IEEE Consumer Communications and Networking Conference, 2006.}, pages = {949--953}, title = {{Joint source-channel coding and power allocation for video transmission over wireless fading channels}}, volume = {2}, year = {2006} }
@inproceedings{Andrew2006, abstract = {Resampling is a fundamental issue in the design of a spatially scalable video codec. The resampling procedure is responsible for down-sampling the high-resolution video sequence to generate lower resolution data, as well as upsampling the transmitted lower resolution data to predict the original high-resolution frames. In both cases, the resampling operation must make trade-offs between coding efficiency, image quality and computational complexity. In this paper, we consider the resampling design problem within an optimization framework. {\textcopyright}2006 IEEE.}, author = {Segall, Andrew and Katsaggelos, Aggelos}, booktitle = {2006 International Conference on Image Processing}, doi = {10.1109/ICIP.2006.312364}, isbn = {1-4244-0480-0}, issn = {15224880}, keywords = {Adaptive filters,Interpolation,Video coding}, month = {oct}, pages = {181--184}, publisher = {IEEE}, title = {{Resampling for Spatial Scalability}}, url = {https://ieeexplore.ieee.org/document/4106496/}, year = {2006} }
@inproceedings{Zhu2006b, abstract = {Video streaming is becoming an important application in wireless communications. In a typical scenario, a base station needs to serve multiple video users with a total transmitting power constraint. How to make appropriate video coding decisions and allocate limited transmitting power among users to achieve optimal total utility is an important problem. In this paper we develop a pricing based downlink power allocation scheme with collaborative video summarization among users. The scheme exploits the multi-user diversity in channel states and utility-resource tradeoff characteristics in video contents to achieve better resource utilization. The computational burden can be distributed among video sources and base station. Simulation results demonstrate the effectiveness of the proposed algorithm. {\textcopyright} 2006 IEEE.}, author = {{Zhu Li} and {Jianwei Huang} and Katsaggelos, Aggelos K A.K. and Li, Zhu and Huang, Jianwei and Katsaggelos, Aggelos K A.K.}, booktitle = {2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings}, doi = {10.1109/ICASSP.2006.1661292}, isbn = {1-4244-0469-X}, issn = {15206149}, organization = {IEEE}, pages = {V--381--V--384}, publisher = {IEEE}, title = {{Pricing based collaborative multi-user video streamming over power constrained wireless downlink}}, url = {http://ieeexplore.ieee.org/document/1661292/}, volume = {5}, year = {2006} }
@inproceedings{Zhu2006, abstract = {Efficient indexing is a key in content-based video retrieval solutions. In this paper we represent video sequences as traces via scaling and linear transformation of the frame luminance field. Then an appropriate lower dimensional subspace is identified for video trace indexing. We also develop a trace geometry matching algorithm for retrieval based on average projection distance with a locally embedded distance metric. Simulation results demonstrated the high accuracy and very fast retrieval speed for the proposed solution. {\textcopyright} 2006 IEEE.}, author = {Li, Zhu and Gao, Li and Katsaggelos, Aggelos}, booktitle = {2006 IEEE International Conference on Multimedia and Expo}, doi = {10.1109/ICME.2006.262893}, isbn = {1-4244-0366-7}, keywords = {Component analysis,High dimensional indexing,Manifold learning,Video retrieval}, month = {jul}, pages = {1765--1768}, publisher = {IEEE}, title = {{Locally Embedded Linear Subspaces for Efficient Video Indexing and Retrieval}}, url = {http://ieeexplore.ieee.org/document/4036962/}, volume = {2006}, year = {2006} }
@inproceedings{Li2006, author = {{Li Gao} and {Zhu Li} and Katsaggelos, Aggelos K A.K. and Gao, Li and Li, Zhu and Katsaggelos, Aggelos K A.K.}, booktitle = {IET International Conference on Visual Information Engineering (VIE 2006)}, doi = {10.1049/cp:20060540}, isbn = {0 86341 671 3}, pages = {267--271}, publisher = {IET Digital Library}, title = {{LUFT (luminance field trace) tree: a video shot segmentation and indexing scheme for fast retrieval}}, url = {https://digital-library.theiet.org/content/conferences/10.1049/cp_20060540}, volume = {2006}, year = {2006} }
@inproceedings{Shengyang2006, abstract = {Many emerging applications require tracking targets in video. Most existing visual tracking methods do not work well when the target is motion-blurred (especially due to fast motion), because the imperfectness of the target's appearances invalidates the image matching model (or the measurement model) in tracking. This paper presents a novel method to track motion-blurred targets by taking advantage of the blurs without performing image restoration. Unlike the global blur induced by camera motion, this paper is concerned with the local blurs that are due to target's motion. This is a challenging task because the blurs need to be identified blindly. The proposed method addresses this difficulty by integrating signal processing and statistical learning techniques. The estimated blurs are used to reduce the search range by providing strong motion predictions and to localize the best match accurately by modifying the measurement models. {\textcopyright}2006 IEEE.}, author = {Dai, Shengyang and Yang, Ming and Wu, Ying and Katsaggelos, Aggelos K.}, booktitle = {2006 International Conference on Image Processing}, doi = {10.1109/ICIP.2006.312943}, isbn = {1-4244-0480-0}, issn = {15224880}, keywords = {Frequency domain analysis,Image deblurring,Pattern recognition,Tracking}, month = {oct}, pages = {2389--2392}, publisher = {IEEE}, title = {{Tracking Motion-Blurred Targets in Video}}, url = {https://ieeexplore.ieee.org/document/4107048/}, year = {2006} }
@inproceedings{molina2006toward, abstract = {The term super-resolution is typically used in the literature to describe the process of obtaining a high resolution (HR) image or a sequence of HR images from a set of low resolution (LR) observations. This term has been applied primarily to spatial and temporal resolution enhancement. However, intentional pre-processing and downsampling can be applied during encoding and super-resolution techniques to upsample the image can be applied during decoding when video compression is the main objective. In this paper we consider the following three video compression models. The first one simply compresses the sequence using any of the available standard compression methods, the second one pre-processes (without downsampling) the image sequence before compression, so that post-processing (without upsampling) is applied to the compressed sequence. The third model includes downsampling in the pre-processing stage and the application of a super resolution technique during decoding. In this paper we describe these three models but concentrate on the application of super-resolution techniques as a way to post-process and upsample a compressed video sequences. Experimental results are provided on a wide range of bitrates for two very important applications: format conversion between different platforms and scalable video coding. {\textcopyright} 2006 SPIE-IS&T.}, author = {Molina, R. and Katsaggelos, A. K. and Alvarez, L. D. and Mateos, J.}, booktitle = {Visual Communications and Image Processing 2006}, doi = {10.1117/12.660794}, editor = {Apostolopoulos, John G. and Said, Amir}, isbn = {0819461172}, issn = {0277786X}, month = {jan}, organization = {SPIE}, pages = {607706}, title = {{Toward a new video compression scheme using super-resolution}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?doi=10.1117/12.660794}, volume = {6077}, year = {2006} }
@inproceedings{Sotirios2006, abstract = {We demonstrate via simulation that hybridization of DNA molecules can be used as a similarity criterion for retrieving digital signals encoded and stored in a synthesized DNA database. After introducing some necessary DNA terminology, we briefly explain how digital signals are transformed to DNA sequences. Since retrieval is achieved through hybridization of query and data carrying DNA molecules, we present a mathematical model to estimate hybridization efficiency (also known as selectivity annealing). We show that selectivity annealing is inversely proportional to the mean squared error (MSE) of the encoded signal values. In addition, we show that the concentration of the molecules plays the same role as the decision threshold employed in digital signal matching algorithms. Finally, similar to the digital domain, we define a DNA signal-to-noise ratio (SNR) measure to assess the performance of the DNA-based retrieval scheme. Simulations are presented to validate our arguments. {\textcopyright} 2006 IEEE.}, author = {Tsaftaris, S.A. and Hatzimanikatis, V. and Katsaggelos, A.K.}, booktitle = {2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings}, doi = {10.1109/ICASSP.2006.1660535}, isbn = {1-4244-0469-X}, issn = {15206149}, pages = {II--1084--II--1087}, publisher = {IEEE}, title = {{DNA Hybridization as a Similarity Criterion for Querying Digital Signals Stored in DNA Databases}}, url = {http://ieeexplore.ieee.org/document/1660535/}, volume = {2}, year = {2006} }
@inproceedings{Jianwei2006, author = {Jianwei, Huang and Zhu, Li and Mung, Chiang and Aggelos, K Katsaggelos}, booktitle = {Proc. IEEE Packet Video Workshop}, title = {{Pricing-based rate control and joint packet scheduling for multi-user wireless uplink video streaming}}, year = {2006} }
@inproceedings{Peshala2006, abstract = {There is a rapidly growing interest in high speed data transmission over digital cellular networks. This interest is fueled mainly by the need to provide multimedia content to mobile users. In this paper, we present a packet scheduling scheme that can be used for real-time streaming of pre-encoded video over downlink packet access wireless networks. We consider a gradient-based scheduling scheme in which user data rates are dynamically adjusted based on their channel quality as well as the gradients of a utility function. The utility functions are designed by taking into account the distortion of the received video. They allow for content-aware packet scheduling both within and across multiple users. Simulation results show that the gradient-based scheduling framework, when combined with the distortion-aware utility functions, significantly outperforms conventional content-independent packet scheduling schemes.}, author = {Pahalawatta, Peshala V. and Berry, Randall and Pappas, Thrasyvoulos N. and Katsaggelos, Aggelos K.}, booktitle = {European Signal Processing Conference}, issn = {22195491}, pages = {1--5}, title = {{A content-aware scheduling scheme for video streaming to multiple users over wireless networks}}, year = {2006} }
@inproceedings{Li2006a, author = {Gao, Li and Li, Zhu and Katsaggelos, Aggelos K.}, booktitle = {2006 International Conference on Image Processing}, doi = {10.1109/ICIP.2006.312566}, isbn = {1-4244-0480-0}, month = {oct}, pages = {1497--1500}, publisher = {IEEE}, title = {{Fast Video Shot Retrieval with Luminance Field Trace Indexing and Geometry Matching}}, url = {https://ieeexplore.ieee.org/document/4106825/}, year = {2006} }
@inproceedings{Sotirios2006a, abstract = {Motivated by the storage capacity and efficiency of the DNA molecule in this paper we propose to utilize DNA molecules to store digital signals. We show that hybridization of DNA molecules can be used as a similarity criterion for retrieving digital signals encoded and stored in a DNA database. Since retrieval is achieved through hybridization of query and data carrying DNA molecules, we present a mathematical model to estimate hybridization efficiency (also known as selectivity annealing). We show that selectivity annealing is inversely proportional to the mean squared error (MSE) of the encoded signal values. In addition, we show that the concentration of the molecules plays the same role as the decision threshold employed in digital signal matching algorithms. Finally, similarly to the digital domain, we define a DNA signal-to-noise ratio (SNR) measure to assess the performance of the DNA-based retrieval scheme. Simulations are presented to validate our arguments.}, author = {Tsaftaris, Sotirios A and Hatzimanikatis, Vassily and Katsaggelos, Aggelos K}, booktitle = {Artificial Life X. Proceedings of the Tenth International Conference on the Simulation and Synthesis of Living Systems}, pages = {303--309}, publisher = {MIT Press}, title = {{DNA as a Medium for Storing Digital Signals}}, year = {2006} }
@inproceedings{Martin2006, abstract = {Image thresholding is one of the most common image processing operations, since almost all image processing schemes need some sort of separation of the pixels into different classes. In order to find the thresholds, almost all methods analyze the histogram of the image. In most cases, the optimal thresholds are found by either minimazing or maximazing an objective function, which depends on the positions of the thresholds. We identify two classes of objective functions for which the optimal thresholds can be found by algorithms with low time complexity. We show, that for example the method proposed by Otsu [1] and other well known methods have objective functions belonging to these classes. By implementing the algorithms in ANSI C and comparing their execution times, we can make a quantitative statement about their performance. {\textcopyright}2006 IEEE.}, author = {Luessi, M. and Eichmann, M. and Schuster, G. M. and Katsaggelos, Aggelos K.}, booktitle = {2006 International Conference on Image Processing}, doi = {10.1109/ICIP.2006.312426}, isbn = {1-4244-0480-0}, issn = {15224880}, keywords = {Dynamic programming,Image segmentation}, month = {oct}, pages = {773--776}, publisher = {IEEE}, title = {{New Results on Efficient Optimal Multilevel Image Thresholding}}, url = {https://ieeexplore.ieee.org/document/4106644/}, year = {2006} }
@inproceedings{Rafael2006a, abstract = {In this paper we present a super resolution Bayesian methodology for pansharpening of multispectral images which: a) incorporates prior knowledge on the expected characteristics of the multispectral images, b) uses the sensor characteristics to model the observation process of both panchromatic and multispectral images, c) includes information on the unknown parameters in the model, and d) allows for the estimation of both the parameters and the high resolution multispectral image. Using real data, the pansharpened multispectral images are compared with the images obtained by other parsharpening methods and their quality assessed both qualitatively and quantitatively.}, author = {Molina, Rafael and Vega, Miguel and Mateos, Javier and Katsaggelos, Aggelos K.}, booktitle = {European Signal Processing Conference}, issn = {22195491}, pages = {1--5}, title = {{Hierarchical Bayesian super resolution reconstruction of multispectral images}}, year = {2006} }
@inproceedings{aleksic2005comparison, abstract = {In this paper, we describe an audio-visual automatic speech recognition (AV-ASR) system that utilizes Facial Animation Parameters (FAPs), supported by the MPEG-4 standard, for the visual representation of speech. We describe the visual feature extraction algorithms used for extracting FAPs, which control outer- and inner-lip movement. Principal component analysis (PCA) is performed on both inner- and outer-lip FAP vector in order to decrease their dimensionality and decorrelate them. The PCA-based projection weights of the extracted FAP vectors are used as visual features. Multi-stream Hidden Markov Models (HMMs) and a late integration approach are used to integrate audio and visual information and train a continuous AV-ASR system. We compare the performance of the developed AV-ASR system utilizing outer- and inner lip FAPs, individually and jointly. Experiments were performed for different dimensionalities of the visual features, at various SNRs (0-30dB) with additive white Gaussian noise, on a relatively large vocabulary (approximately 1000 words) database. The proposed system reduces the word error rate (WER) by 20% to 23% relatively to audio-only ASR WERs. Conclusions are drawn on the individual and combined effectiveness of the inner- and outer-lip FAPs, the trade off between the dimensionality of the visual features and the amount of speechreading information contained in them and its influence on the AV-ASR performance. {\textcopyright} 2005 IEEE.}, author = {Aleksic, P.S. and Katsaggelos, K.}, booktitle = {IEEE International Conference on Image Processing 2005}, doi = {10.1109/ICIP.2005.1530438}, isbn = {0-7803-9134-9}, issn = {15224880}, organization = {IEEE}, pages = {III--501}, publisher = {IEEE}, title = {{Comparison of MPEG-4 facial animation parameter groups with respect to audio-visual speech recognition performance}}, url = {http://ieeexplore.ieee.org/document/1530438/}, volume = {3}, year = {2005} }
@inproceedings{Zhu2005a, abstract = {For video communications over wireless ad hoc networks, multiple paths with limited bandwidth are common. It therefore presents new challenges to the video encoding. In this paper, we formulate the problem as a multiple path video summarization problem under bit rate constraints, where video summaries are generated to satisfy each channel's rate constraint, while the combined summary at the receiving end achieves the minimum summarization distortion. The optimal solution (within a convex hull approximation) is found by Lagrangian relaxation and dynamic programming. Simulation results demonstrate the effectiveness of the approach. {\textcopyright} 2005 IEEE.}, author = {Li, Zhu and Schuster, G.M. Guido M and Katsaggelos, Aggelos K A.K. and {Zhu Li} and Schuster, G.M. Guido M and Katsaggelos, Aggelos K A.K.}, booktitle = {IEEE International Conference on Image Processing 2005}, doi = {10.1109/ICIP.2005.1529723}, isbn = {0-7803-9134-9}, issn = {15224880}, organization = {IEEE}, pages = {I--205}, publisher = {IEEE}, title = {{Video summarization for multiple path communication}}, url = {http://ieeexplore.ieee.org/document/1529723/}, volume = {1}, year = {2005} }
@inproceedings{Zhu2005f, abstract = {In this paper we consider the problem of efficiently serving multiple uplink video users in a wideband CDMA wireless communication system with mixed voice and video traffic. Very low available video bit rate (<64kpbs) and multi-user interference are the major limiting factors in the system performance. Our solution is based on video summarization to achieve reasonable video quality at very low bit rate, and multi-user transmission adaptation/scheduling via summarization distortion-rate profile negotiation between base station and mobiles to meet power control constraints and minimize the interference among voice/video users. The simulation results demonstrate the effectiveness of the proposed approach.}, author = {Li, Zhu and Cheng, Alan and Katsaggelos, Aggelos and Ishtiaq, Faisal}, booktitle = {2005 IEEE 7th Workshop on Multimedia Signal Processing}, doi = {10.1109/MMSP.2005.248615}, isbn = {0-7803-9288-4}, keywords = {CDMA,Power control,Transmission adaptation,Video summarization,Wireless video}, month = {oct}, pages = {1--4}, publisher = {IEEE}, title = {{Video Summarization and Transmission Power Adaptation for Very Low Bit Rate Multiuser Wireless Uplink Video Communication}}, url = {http://ieeexplore.ieee.org/document/4014036/}, year = {2005} }
@inproceedings{Cristina2005, abstract = {Mobility, made available by today's communication networks, imposes several limitations in the design of multimedia applications, due to high error rates, reduced bandwidth, strong variability, and mobile terminals lifetime. This paper investigates the use of an energy constrained cross-layer approach for the transmission of progressively coded images over packet-based wireless channels. We propose an optimum power allocation algorithm to enable unequal error protection of a pre-encoded image. Simulations are performed modeling transmission over a Rayleigh fading channel. The investigation focuses on JPEG2000, but it is applicable to other progressively coded bitstreams as well. Our experimental results demonstrate that it is possible to achieve a relevant performance enhancement with the proposed approach over uniform error protection. The optimal solution can also serve as a guideline for developing less computationally intensive empiric approaches.}, author = {Costa, C. and Granelli, F. and Katsaggelos, A.K.}, booktitle = {IEEE International Conference on Image Processing 2005}, doi = {10.1109/ICIP.2005.1529725}, isbn = {0-7803-9134-9}, pages = {I--213}, publisher = {IEEE}, title = {{A cross-layer approach for energy efficient transmission of progressively coded images over wireless channels}}, url = {http://ieeexplore.ieee.org/document/1529725/}, volume = {1}, year = {2005} }
@inproceedings{Aggelos2005a, author = {Katsaggelos, A.K. K and DeNatale, F.G.B. G B and Szabo, C.A. A and da Fonseca, N.L.S. L S}, booktitle = {2005 1st International Conference on Multimedia Services Access Networks, 2005. MSAN '05.}, doi = {10.1109/MSAN.2005.1489925}, isbn = {0-7803-9319-8}, pages = {iii--iii}, publisher = {IEEE}, title = {{Preface}}, url = {https://ieeexplore.ieee.org/document/1489925}, volume = {2005}, year = {2005} }
@inproceedings{wang2005resource, abstract = {In this paper, we describe two major issues in object-based video coding and communications and provide solutions based on the MPEG-4 coding standard. We first consider the general problem of bit allocation among shape, texture and motion in video coding, and provide optimal solutions based on MINMAX (Minimum Maximum) and MINAVE (Minimum Average) distortion criteria, respectively. Then, we discuss the resource allocation problem in video communications, and demonstrate a number of unequal error protection schemes including separated packetization, joint source-channel coding and data hiding. Experimental results demonstrate significant gains by using these algorithms. {\textcopyright} 2005 IEEE.}, author = {{Haohong Wang} and Katsaggelos, Aggelos and Wang, Haohong and Katsaggelos, Aggelos}, booktitle = {2005 1st International Conference on Multimedia Services Access Networks, 2005. MSAN '05.}, doi = {10.1109/MSAN.2005.1489933}, isbn = {0-7803-9319-8}, organization = {IEEE}, pages = {10--14}, publisher = {IEEE}, title = {{Resource-distortion optimal video coding and communications}}, url = {https://ieeexplore.ieee.org/document/1489933}, volume = {2005}, year = {2005} }
@inproceedings{Zhilin2005, author = {Wu, Zhilin and Katsaggelos, Aggelos K. and Pappas, Thrasyvoulos N.}, booktitle = {Image and Video Communications and Processing 2005}, doi = {10.1117/12.596789}, editor = {Said, Amir and Apostolopoulos, John G.}, issn = {0277786X}, month = {mar}, pages = {1077}, title = {{MPEG-4 outer-inner lip FAP interpolation}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?doi=10.1117/12.596789}, volume = {5685}, year = {2005} }
@inproceedings{Rafael2005, author = {Molina, R and Mateos, J and Katsaggelos, AK and Zurita-Milla, R and Liang, S and Liu, J and Li, X}, booktitle = {9th International Symposium on Physical Measurements and Signatures in Remote Sensing (ISPMSRS)}, number = {2}, pages = {3--6}, title = {{A new super resolution Bayesian method for pansharpening Landsat ETM+ imagery}}, url = {http://ivpl.ece.northwestern.edu/files/Anewsuperresolution05.PDF}, year = {2005} }
@inproceedings{Zhu2005c, abstract = {With the proliferation of camera equipped cell phones and the deployment of the higher data rate 2.5G and 3G infra structure systems, providing consumers with video-equipped cellular communication infrastructure is highly desirable, and can drive the development of a large number of valuable applications. However, for an uplink wireless channel, both the bandwidth and battery energy in a mobile phone are limited for video communications. In this paper, we pursue an energy efficient video communication solution through joint video summarization and transmission adaptation over a slow fading wireless channel. Coding and modulation schemes and packet transmission strategy are optimized and adapted to the unique packet arrival and delay characteristics of the video summaries. In additional to the optimal solution, we also propose a heuristic solution that is greedy but has close to optimal performance. Operational energy efficiency - summary distortion performance is characterized under an optimal summarization setting. Simulation results show the advantage of the proposed scheme with respect to energy efficiency and video transmission quality.}, author = {Li, Zhu and Zhai, Fan and Katsaggelos, Aggelos K.}, booktitle = {Visual Communications and Image Processing 2005}, doi = {10.1117/12.631646}, isbn = {9780819459763}, issn = {0277786X}, month = {jun}, pages = {81}, publisher = {SPIE}, title = {{Video summarization for energy efficient wireless streaming}}, url = {https://www.spiedigitallibrary.org/conference-proceedings-of-spie/5960/631646/Video-summarization-for-energy-efficient-wireless-streaming/10.1117/12.631646.full}, volume = {5960}, year = {2005} }
@inproceedings{Xiaohuan2005, abstract = {A multiple global affine motion model is proposed for low bit rate video compression. Block-wise motion segmentation is first performed with the number of motion objects L predefined. The affine motion models for multiple MOs are estimated and coded in the frame header. The scaling parameters al, a2, a4 and a5 are coded with a 4-dimensional vector-quantizer (VQ), whose 16 most recently used code words are maintained on line and searched for VQ match, and the 300-word long main code book stored offline. The translational parameters a3 and a6 are coded predicatively as a classical motion vector. L new macro-block modes are added to the standard's list of 7 infra and inter modes. No segmentation information is transmitted, for the mode already indicates that if one of the affine modes is selected by Lagrange rate-distortion optimization. A metric S is defined to measure locality of the motion and will disable use of affine models when a threshold is surpassed. Simulation shows that abut 20-40% of the MB's choose one of the affine modes. When 100kbps or lower band widths are available, the proposed codec not only saves 1-18% bit rate, but also enhances error-resilience in multiple slice frames and reduces blocking artifacts notably. {\textcopyright} 2005 SPIE and IS&T.}, author = {Li, Xiaohuan and Jackson, Joel R. and Katsaggelos, Aggelos K. and Merserau, Russel M.}, booktitle = {Image and Video Communications and Processing 2005}, doi = {10.1117/12.587328}, editor = {Said, Amir and Apostolopoulos, John G.}, issn = {0277786X}, month = {mar}, pages = {185}, title = {{Multiple global affine motion model for H.264 video coding with low bit rate}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?doi=10.1117/12.587328}, volume = {5685}, year = {2005} }
@inproceedings{Javier2005, abstract = {In this paper the blind deconvolution problem is formulated using the variational framework. With its use approximations of the involved probability distributions are developed resulting in two algorithms for the estimation of the posterior distributions of the hyperparameters, the blur, and the original image. The performance of the two proposed restoration algorithms is demonstrated experimentally. {\textcopyright} 2005 IEEE.}, author = {Mateos, Javier and Molina, Rafael and Katsaggelos, A.K.}, booktitle = {IEEE International Conference on Image Processing 2005}, doi = {10.1109/ICIP.2005.1530169}, isbn = {0-7803-9134-9}, issn = {15224880}, pages = {II--770}, publisher = {IEEE}, title = {{Approximations of posterior distributions in blind deconvolution using variational methods}}, url = {http://ieeexplore.ieee.org/document/1530169/}, volume = {2}, year = {2005} }
@inproceedings{Zhu2005b, abstract = {With the deployment of 2.5G/3G cellular network infrastructure and large number of camera equipped cell phones, the demand for video enabled applications are high. However, for an uplink wireless channel, both the bandwidth and battery energy capability are limited in a mobile phone for the video communication. These technical problems need to be effectively addressed before the practical and affordable video applications can be made available to consumers. In this paper we investigate the energy efficient video communication solution through joint video summarization and transmission adaptation over a slow fading channel. Coding and modulation schemes, as well as packet transmission strategy are optimized and adapted to the unique packet arrival and delay characteristics of the video summaries. Operational energy efficiency - summary distortion performance is characterized under an optimal summarization setting. {\textcopyright} 2005 SPIE and IS & T.}, author = {Li, Zhu and Zhai, Fan and Katsaggelos, Aggelos K. and Pappas, Thrasyvoulos N.}, booktitle = {Image and Video Communications and Processing 2005}, doi = {10.1117/12.587669}, editor = {Said, Amir and Apostolopoulos, John G.}, issn = {0277786X}, month = {mar}, pages = {940}, title = {{Energy efficient video summarization and transmission over a slow fading wireless channel}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?doi=10.1117/12.587669}, volume = {5685}, year = {2005} }
@inproceedings{Sotirios2005a, author = {Sotirios, A Tsaftaris and Aggelos, K Katsaggelos}, booktitle = {Preproceedings of the 11th International Meeting on DNA-based computers DNA 11}, title = {{A new codeword design algorithm for DNA based storage and retrieval of digital signals}}, url = {http://eprints.imtlucca.it/809/}, year = {2005} }
@inproceedings{Peshala2005a, abstract = {The goal of video summarization is to generate a shorter video sequence of a lengthy original sequence using only the key frames of the original sequence. We consider a video summarization scheme that generates a video summary that can be transmitted over an unreliable network such as the Internet with minimum distortion of the original video. We consider two methods of distortion measurement in our optimization scheme, and we apply the methods to a scenario in which feedback is available with the possibility of retransmitting lost packets. Simulation results showing the effectiveness of using the proposed schemes are presented.}, author = {Pahalawatta, Peshala and Li, Zhu and Zhai, Fan and Katsaggelos, Aggelos}, booktitle = {2005 IEEE 7th Workshop on Multimedia Signal Processing}, doi = {10.1109/MMSP.2005.248632}, isbn = {0-7803-9288-4}, month = {oct}, pages = {1--4}, publisher = {IEEE}, title = {{Rate-Distortion Optimization for Internet Video Summarization and Transmission}}, url = {http://ieeexplore.ieee.org/document/4014053/}, year = {2005} }
@inproceedings{Peshala2005, abstract = {The goal of video summarization is to select key frames from a video sequence in order to generate an optimal summary that can accommodate constraints on viewing time, storage, or bandwidth. While video summary generation without transmission considerations has been studied extensively, the problem of rate-distortion optimized summary generation and transmission in a packet-lossy network has gained little attention. We consider the transmission of summarized video over a packet-lossy network such as the Internet. We depart from traditional rate control methods by not sacrificing the image quality of each transmitted frame but instead focusing on the frames that can be dropped without seriously affecting the quality of the video sequence. We take into account the packet loss probability, and use the end-to-end distortion to optimize the video quality given constraints on the temporal rate of the summary. Different network scenarios such as when a feedback channel is not available, and when a feedback channel is available with the possibility of retransmission, are considered. In each case, we assume a strict end-to-end delay constraint such that the summarized video can be viewed in real-time. We show simulation results for each case, and also discuss the case when the feedback delay may not be constant. {\textcopyright} 2005 SPIE and IS & T.}, author = {Pahalawatta, Peshala V. and Li, Zhu and Zhai, Fan and Katsaggelos, Aggelos K.}, booktitle = {Image and Video Communications and Processing 2005}, doi = {10.1117/12.586327}, editor = {Said, Amir and Apostolopoulos, John G.}, issn = {0277786X}, month = {mar}, pages = {801}, title = {{Rate-distortion optimized video summary generation and transmission over packet lossy networks}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?doi=10.1117/12.586327}, volume = {5685}, year = {2005} }
@inproceedings{Ehsan2005, abstract = {Techniques for modeling and simulating channel conditions play an essential role in efficient real-time video transmission over wireless networks. In this paper, we consider a Finite-State Markov Chain (FSMC) as the channel model to perform Joint Source Channel Coding (JSCC). We derive a method to optimally estimate the overall distortion at the decoder. The optimization is done in an integrated manner and in one step. Computer simulations are performed to show the advantages of the proposed model.}, author = {Maani, Ehsan and Katsaggelos, Aggelos K.}, booktitle = {43rd Annual Allerton Conference on Communication, Control and Computing 2005}, isbn = {9781604234916}, pages = {1177--1186}, title = {{An integrated joint source-channel coding framework for video transmission over wireless fading channels}}, volume = {3}, year = {2005} }
@inproceedings{wang2004hybrid, abstract = {In this paper, we study the joint source-channel coding of object-based video, and propose a data hiding scheme that improves the video error resilience by adaptively embedding the shape and motion information in the texture data. Within a rate-distortion theoretical framework, the source coding, channel coding, data embedding, and decoder error concealment are jointly optimized based on the knowledge of transmission channel conditions. The problem is solved using Lagarangian relaxation and dynamic programming. Experimental results indicate that the proposed hybrid source-channel coding scheme significantly outperforms methods without data hiding or unequal error protection.}, author = {{Haohong Wang} and Katsaggelos, Aggelos K A.K. and Wang, Haohong and Katsaggelos, Aggelos K A.K.}, booktitle = {Proceedings. 13th International Conference on Computer Communications and Networks (IEEE Cat. No. 04EX969)}, doi = {10.1109/ICCCN.2004.1401636}, isbn = {0-7803-8814-3}, issn = {10952055}, organization = {IEEE}, pages = {235--240}, publisher = {IEEE}, title = {{A hybrid source-channel coding scheme for object-based wireless video communications}}, url = {http://ieeexplore.ieee.org/document/1401636/}, year = {2004} }
@inproceedings{zhai2005rate, abstract = {We study hybrid error control for real-time video transmission. The study is carried out using a proposed integrated joint source-channel coding framework, which jointly considers error resilient source coding, channel coding, and error concealment, in order to achieve the best video quality. We focus on the performance comparison of several error correction scenarios, such as forward error correction (FEC), retransmission, and the combination of both. Simulation results show that either FEC or retransmission can be optimal depending on the packet loss rates and network round trip time. The proposed hybrid FEC/retransmission scheme outperforms both.}, author = {Zhai, Fan and Eisenberg, Yiftach and Pappas, T.N. Thrasyvoulos N. and Berry, Randall and Katsaggelos, Aggelos K. A.K. and {Fan Zhai} and Eisenberg, Yiftach and Pappas, T.N. Thrasyvoulos N. and Berry, Randall and Katsaggelos, Aggelos K. A.K.}, booktitle = {2004 IEEE International Conference on Communications (IEEE Cat. No.04CH37577)}, doi = {10.1109/icc.2004.1312726}, isbn = {0-7803-8533-0}, issn = {05361486}, number = {1}, pages = {1318--1322}, publisher = {IEEE}, title = {{Rate-distortion optimized hybrid error control for real-time packetized video transmission}}, url = {http://ieeexplore.ieee.org/document/1312726/}, volume = {3}, year = {2004} }
@inproceedings{Haohong2004a, abstract = {In this paper, we consider dynamic resource allocation for object-based wireless video communications. In object-based video coding, a video frame is comprised of objects that are described by their shape as well as their texture. By jointly considering source coding, error concealment, and transmission power management at the physical layer, the proposed framework minimize the expect distortion at the receiver for given energy and delay constraints. In order to provide unequal error protection for the shape and texture information, a new video packetization scheme is proposed. Experimental results indicate that the proposed unequal error protection schemes significantly outperform equal error protection methods. {\textcopyright} 2004 IEEE.}, author = {{Haohong Wang} and Eisenberg, Yiftach and {Fan Zhoi} and Katsuggelos, A.K. and Wang, Haohong and Eisenherg, Y and Zhai, Fan and Katsaggelos, Aggelos K}, booktitle = {2004 International Conference on Image Processing, 2004. ICIP'04.}, doi = {10.1109/ICIP.2004.1421621}, isbn = {0-7803-8554-3}, issn = {15224880}, organization = {IEEE}, pages = {2543--2546}, publisher = {IEEE}, title = {{Joint object-based video encoding and power management for energy efficient wireless video communications}}, url = {http://ieeexplore.ieee.org/document/1421621/}, volume = {4}, year = {2004} }
@inproceedings{alvarez2004motion, abstract = {In order to obtain a high resolution image from a compressed video sequence it is essential to correctly estimate the motion vectors in the sequence. Most of the approaches reported in the literature address this problem using standard motion estimation techniques. In this paper we tackle the correct estimation of the motion vectors by consistently estimating the optical flow across multiple images. Consistency is achieved by adding a regularization term to the classical Lucas-Kanade approach to motion estimation. The proposed algorithm is tested on real video sequences. {\textcopyright} 2004 IEEE.}, author = {Alvarez, L.D. and Molina, Rafael and Katsaggelos, A.K.}, booktitle = {2004 International Conference on Image Processing, 2004. ICIP '04.}, doi = {10.1109/ICIP.2004.1421423}, isbn = {0-7803-8554-3}, issn = {15224880}, organization = {IEEE}, pages = {1795--1798}, publisher = {IEEE}, title = {{Motion estimation in high resolution image reconstruction from compressed video sequences}}, url = {http://ieeexplore.ieee.org/document/1421423/}, volume = {3}, year = {2004} }
@inproceedings{li2004bit, author = {Li, Z and Schuster, G M and Katsaggelos, A K and Gandhi, B}, booktitle = {Proceedings of the IEEE International Conference on Image Processing (ICIP'04)}, title = {{Bit constrained optimal video summarization}}, year = {2004} }
@inproceedings{Reto, author = {Ansorge, Reto and Kirchmeier, Erwin and Li, Zhu and Schuster, Guido M and Katsaggelos, Aggelos K}, title = {{Optimal Intra-Coded Video Summarization for Two Bandwidth Limited Channels}}, url = {https://www.icom.hsr.ch/fileadmin/user_upload/icom.hsr.ch/publikationen/multipathVideoSum2.pdf}, year = {2004} }
@inproceedings{li2004optimal, abstract = {The need for video summarization originates primarily from a viewing time or a bit budget constraint. A shorter version of the original video sequence is desirable in a number of applications. Clearly, a shorter version is also necessary in applications where storage, communication bandwidth and/or power are limited, which translates into a bit budget constraint. Our work is based on a bit rate-summary distortion optimization formulation. New metrics for video summary distortion are introduced. An optimal algorithm based on Lagrangian relaxation and dynamic programming is presented. {\textcopyright} 2004 IEEE.}, author = {{Zhu Li} and Schuster, G.M. and Katsaggelos, A.K. and Gandhi, Bhavan and Li, Zhu and Schuster, Z M and Katsaggelos, L K and Gandhi, Bhavan}, booktitle = {2004 International Conference on Image Processing, 2004. ICIP'04.}, doi = {10.1109/ICIP.2004.1418830}, isbn = {0-7803-8554-3}, issn = {15224880}, organization = {IEEE}, pages = {617--620}, publisher = {IEEE}, title = {{Optimal video summarization with a bit budget constraint}}, url = {http://ieeexplore.ieee.org/document/1418830/}, volume = {1}, year = {2004} }
@inproceedings{Konstantinos2004, abstract = {This paper1 studies the transmission of a continuous source over a two-hop fading channel. The source data traverses at least one intermediate node in order to reach the destination node. We assume a Gaussian source with Rayleigh fading links, and model the effect of each link through its outage capacity. We start with a single link, and optimize the transmission rate to minimize the received distortion. This minimum distortion is characterized as a function of transmission time, average channel gain, and transmitted power. We then consider a two-hop channel and optimize the transmission rates and transmission times over the two links. Two cases are compared: (i) The relay is allowed to optimize the transmission rate over the second link; and (ii) The relay retransmits the received bits over the second link at the same rate. Numerical examples show that both types of relays perform similarly over a wide parameter range of interest We characterize the minimum achievable distortion in each case when the ratio between channel gains becomes large, and show that the former (smart) relay gives a performance gain of at most three dB. {\textcopyright} 2004 IEEE.}, author = {Zachariadis, K.E. and Honig, M.L. and Katsaggelos, A.K.}, booktitle = {IEEE MILCOM 2004. Military Communications Conference, 2004.}, doi = {10.1109/MILCOM.2004.1493258}, isbn = {0-7803-8847-X}, pages = {134--139}, publisher = {IEEE}, title = {{Source fidelity over a two-hop fading channel}}, url = {http://ieeexplore.ieee.org/document/1493258/}, volume = {1}, year = {2004} }
@inproceedings{wang2004optimal, abstract = {In this paper, we propose an optimal unequal error protection scheme for object-based video communications over differentiated services networks. Our goal is to achieve the best video quality (minimum total expected distortion) with constraints on transmission cost and delay. An end-to-end distortion estimation approach for object-based video is proposed, which can be used for different packetization schemes. The problem is solved using Lagarangian relaxation and dynamic programming. Experimental results indicate that the proposed unequal error protection schemes can significantly outperform equal error protection methods. {\textcopyright} 2004 IEEE.}, author = {Wang, Haohong and Zhai, Fan and Eisenberg, Yiftach and Katsaggelos, Aggelos K and {Haohong Wang} and {Fan Zhai} and Eisenberg, Yiftach and Kalsaggelos, Aggelos.K.}, booktitle = {2004 International Conference on Image Processing, 2004. ICIP'04.}, doi = {10.1109/ICIP.2004.1421808}, isbn = {0-7803-8554-3}, issn = {15224880}, organization = {IEEE}, pages = {3257--3260}, publisher = {IEEE}, title = {{Optimal object-based video communications over differentiated services networks}}, url = {http://ieeexplore.ieee.org/document/1421808/}, volume = {5}, year = {2004} }
@inproceedings{Guido2004, abstract = {In this paper we introduce a novel circle detection algorithm based on a weighted minimum mean square error (MSB) formulation. Traditional approaches to circle detections consist of two stages, an edge detection stage and a circle detection stage using the edge detection result. There are several problems with this approach. First, the initial edge detection stage is sensitive to noise. Second, the second stage does not use all the information available in the image and therefore incorrect decisions made by the first stage cannot be corrected in the second stage. The proposed algorithm achieves its robustness by operating in one step, using all pixels of the image (correctly weighted) and not using any thresholds. The detected circle is the solution of several weighted MSE problems. Experimental results demonstrate the performance of the algorithm in noiseless and noisy conditions. {\textcopyright}2004 IEEE.}, author = {Schuster, G.M. and Katsuggelos, A.K.}, booktitle = {2004 International Conference on Image Processing, 2004. ICIP '04.}, doi = {10.1109/ICIP.2004.1421502}, isbn = {0-7803-8554-3}, issn = {15224880}, pages = {2111--2114}, publisher = {IEEE}, title = {{Robust circle detection using a weighted mse estimator}}, url = {http://ieeexplore.ieee.org/document/1421502/}, volume = {3}, year = {2004} }
@inproceedings{pahalawatta2004optimal, abstract = {The use of wireless sensor networks for target tracking is an active area of research. Imaging sensors that obtain video-rate images of a scene can have a significant impact in such networks, as they can measure vital information on the identity, position, and velocity of moving targets. Since wireless networks must operate under stringent energy constraints, it is important to identify the optimal set of imagers to be used in a tracking scenario such that the network lifetime is maximized. We formulate this problem as one of maximizing the information utility gained from a set of sensors subject to a constraint on the average energy consumption in the network. We use an unscented Kalman filter framework to solve the tracking and data fusion problem with multiple imaging sensors in a computationally efficient manner, and use a lookahead algorithm to optimize the sensor selection based on the predicted trajectory of the target. Simulation results show the effectiveness of this method of sensor selection. {\textcopyright} 2004 IEEE.}, author = {Pahalawatta, P.V. and Pappas, T.N. and Katsaggelos, A.K.}, booktitle = {2004 International Conference on Image Processing, 2004. ICIP '04.}, doi = {10.1109/ICIP.2004.1421762}, isbn = {0-7803-8554-3}, issn = {15224880}, organization = {IEEE}, pages = {3073--3076}, publisher = {IEEE}, title = {{Optimal sensor selection for video-based target tracking in a wireless sensor network}}, url = {http://ieeexplore.ieee.org/document/1421762/}, volume = {5}, year = {2004} }
@inproceedings{aleksic2004comparison, abstract = {In this paper, we compare two different groups of visual features that can be used in addition to audio to improve automatic speech recognition (ASR), high- and low-level visual features. Facial Animation Parameters (FAPs), supported by the MPEG-4 standard for the visual representation of speech are used as high-level visual features in this work. Principal component analysis (PCA) based projection weights of the intensity images of the mouth area were used as low-level visual features. PCA was also applied on the FAPs. We developed an audio-visual ASR (AV-ASR) system and compared its performance for two different visual feature groups, following two approaches, The first approach assumes the same dimensionality for both high- and low-level visual features, while in the second approach the percentage of statistical variance described by the visual features used was the same. Multi-stream Hidden Markov Models (HMMs) and a late integration approach were used to integrate audio and visual information and perform continuous AV-ASR experiments. Experiments were performed at various SNRs (0-30dB) with additive white Gaussian noise on a relatively large vocabulary (approximately 1000 words) database. Conclusions were drawn on the trade off between the dimensionality of the visual features and the amount of speechreading information contained in them and its influence on the AV-ASR performance.}, author = {Aleksic, P.S. and Katsaggelos, A.K.}, booktitle = {2004 IEEE International Conference on Acoustics, Speech, and Signal Processing}, doi = {10.1109/ICASSP.2004.1327261}, isbn = {0-7803-8484-9}, issn = {15206149}, organization = {IEEE}, pages = {V--917--20}, publisher = {IEEE}, title = {{Comparison of low- and high-level visual features for audio-visual continuous automatic speech recognition}}, url = {http://ieeexplore.ieee.org/document/1327261/}, volume = {5}, year = {2004} }
@inproceedings{zhai2004rate, abstract = {The problem of encoding and transmitting a video sequence over an IP-based wireless network consisting of both wired and wireless links is addressed. To combat the different types of packet loss in the heterogeneous network, the use of a product code forward error correction (FEC) scheme capable of providing unequal error protection is considered. At the transport layer, Reed-Solomon (RS) coding is used to provide inter-packet protection. In addition, rate-compatible punctured convolutional (RCPC) coding is used at the link layer to provide unequal intra-packet protection. Optimal bit allocation is performed in a rate-distortion optimized joint source-channel coding and power allocation framework to achieve the best video quality. Simulation results illustrate the advantage of the proposed product code FEC scheme over previously studied approaches.}, author = {Zhai, Fan and Eisenberg, Yiftach and Poppas, Thrasyvoulos N. and Berry, Randall and Katsaggelos, Aggelos K. A.K. and {Fan Zhai} and Eisenberg, Yiftach and Pappas, T.N. and Berry, Randall and Katsaggelos, Aggelos K. A.K.}, booktitle = {ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings}, doi = {10.1109/ICASSP.2004.1327246}, isbn = {0-7803-8484-9}, issn = {15206149}, organization = {IEEE}, pages = {V--857--60}, publisher = {IEEE}, title = {{Rate-distortion optimized product code forward error correction for video transmission over ip-based wireless networks}}, url = {http://ieeexplore.ieee.org/document/1327246/}, volume = {5}, year = {2004} }
@inproceedings{Sotirios2004, abstract = {Adleman with his pioneering work set the stage for the new field of bio-computing research. His main idea was to use actual chemistry to solve problems that are either unsolvable by conventional computers, or require an enormous amount of computation. The main focus of our research is to consider the application of molecular computing to the domain of digital signal processing (DSP). In this paper we consider matching problems that arise in signal processing applications and are amenable to a DNA-based solution. Digital data are encoded in DNA sequences using a sophisticated codeword set that satisfies the Noise Tolerance Constraint (NTC) that we introduce. NTC, one of the main contributions of our work, takes into account the presence of noise in digital signals by exploiting the annealing between non-perfect complementary sequences. We propose an algorithm to map binary values into DNA codewords by satisfying a number of constraints, including the NTC. Using that algorithm we retrieved 128 codewords that enables us to use a DNA based approach to digital signal matching.}, author = {Tsaftaris, S.A. and Katsaggelos, A.K. and Pappas, T.N. and Papoutsakis, T.E.}, booktitle = {2004 IEEE International Conference on Acoustics, Speech, and Signal Processing}, doi = {10.1109/ICASSP.2004.1327177}, isbn = {0-7803-8484-9}, issn = {15206149}, pages = {V--581--4}, publisher = {IEEE}, title = {{DNA-based matching of digital signals}}, url = {http://ieeexplore.ieee.org/document/1327177/}, volume = {5}, year = {2004} }
@inproceedings{CristinaEmilia2004, abstract = {Fine granular scalability is a coding tool, recently introduced in the emerging MPEG-4 standard, which enables the creation of very flexible scalable video bitstreams. This paper investigates the transmission of fine granular scalable (FGS) video over wireless links, using power management for unequal error protection of the bitstream. In wireless systems, energy may be a limited resource, and a wise use of it is important for system efficiency. An algorithm is proposed which is able to optimally distribute the total available power for the transmission of the enhancement layer, given a distortion or energy constraint. Experimental results demonstrate the performance advantage of the proposed algorithm over fixed power schemes and heuristic approaches.}, author = {Costa, C.E. and Eisenberg, Yiftach and {Fan Zhai} and Katsaggelos, A.K.}, booktitle = {2004 IEEE International Conference on Communications (IEEE Cat. No.04CH37577)}, doi = {10.1109/ICC.2004.1313101}, isbn = {0-7803-8533-0}, issn = {05361486}, pages = {3096--3100 Vol.5}, publisher = {IEEE}, title = {{Energy efficient wireless transmission of MPEG-4 fine granular scalable video}}, url = {http://ieeexplore.ieee.org/document/1313101/}, volume = {5}, year = {2004} }
@inproceedings{Zhu2004a, abstract = {The need for video summarization originates primarily from a viewing time constraint. A shorter version of the original video sequence is desirable in a number of applications. Clearly, a shorter version is also necessary in applications where storage, communication bandwidth and/or power are limited. Our work is based on a temporal rate-distortion optimization formulation for optimal summary generation. New metrics for video summary distortion are introduced. Optimal algorithms based on dynamic programming are presented along with the results from heuristic algorithms that can produce near optimal results in real time.}, author = {{Zhu Li} and Schuster, G.M. Guido M and Katsaggelos, Aggelos K A.K. and Gandhi, Bhavan and Li, Zhu and Schuster, G.M. Guido M and Katsaggelos, Aggelos K A.K. and Gandhi, Bhavan}, booktitle = {2004 IEEE International Conference on Acoustics, Speech, and Signal Processing}, doi = {10.1109/ICASSP.2004.1326580}, isbn = {0-7803-8484-9}, issn = {15206149}, organization = {IEEE}, pages = {iii----457}, publisher = {IEEE}, title = {{Rate-Distortion optimal video summarization: A dynamic programming solution}}, url = {http://ieeexplore.ieee.org/document/1326580/}, volume = {3}, year = {2004} }
@inproceedings{Yiftach2004, abstract = {A critical component of any video transmission system is an objective metric for evaluating the quality of the video signal as it is seen by the end-user. In packet-based communication systems, such as a wireless channel or the Internet, the quality of the received signal is affected by both signal compression and packet losses. Due to the probabilistic nature of the channel, the distortion in the reconstructed signal is a random variable. In addition, the quality of the reconstructed signal depends on the error concealment strategy. A common approach is to use the expected mean squared error of the end-to-end distortion as the performance metric. It can be shown that this approach leads to unpredictable perceptual artifacts. A better approach is to account for both the mean and the variance of the end-to-end distortion. We explore the perceptual benefits of this approach. By accounting for the variance of the distortion, the difference between the transmitted and the reconstructed signal can be decreased without a significant increase in the expected value of the distortion. Our experimental results indicate that for low to moderate probability of loss, the proposed approach offers significant advantages over strictly minimizing the expected distortion. We demonstrate that controlling the variance of the distortion limits perceptually annoying artifacts such as persistent errors.}, author = {Eisenberg, Yiftach and Zhai, Fan and Pappas, Thrasyvoulos N. and Berry, Randall and Katsaggelos, Aggelos K.}, booktitle = {Human Vision and Electronic Imaging IX}, doi = {10.1117/12.548321}, editor = {Rogowitz, Bernice E. and Pappas, Thrasyvoulos N.}, issn = {0277786X}, month = {jun}, pages = {162}, title = {{Quality metrics for measuring end-to-end distortion in packet-switched video communication systems}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?doi=10.1117/12.548321}, volume = {5292}, year = {2004} }
@inproceedings{Xiaohuan2004, author = {{Xiaohuan Li} and Jackson, Joel R J.R. and Katsaggelos, Aggelos K A.K. and Mersereau, R.M. Russell M and Li, Xiaohuan and Jackson, Joel R J.R. and Katsaggelos, Aggelos K A.K. and Mersereau, R.M. Russell M}, booktitle = {2004 IEEE International Conference on Acoustics, Speech, and Signal Processing}, doi = {10.1109/ICASSP.2004.1326645}, isbn = {0-7803-8484-9}, organization = {IEEE}, pages = {iii--717--20}, publisher = {IEEE}, title = {{An adaptive coding scheme using affine motion model for MPEG P-VOP}}, url = {http://ieeexplore.ieee.org/document/1326645/}, volume = {3}, year = {2004} }
@inproceedings{li2004fast, abstract = {Content-based video retrieval technology holds the key to the efficient management and sharing of video content from different sources, in different scales, across different platforms, and shared over different communication channels. In this work we present a fast retrieval algorithm based on matching the geometry of video sequence traces in the principal component space. Techniques to address scale (spatial and temporal) issues, as well as, noise and other possible distortions, such as frame dropping, are discussed. Experimental results demonstrate the effectiveness of the proposed approach. {\textcopyright} 2004 IEEE.}, author = {{Zhu Li} and Katsaggelos, Aggelos K A.K. and Gandhi, Bhavan and Li, Zhu and Katsaggelos, Aggelos K A.K. and Gandhi, Bhavan}, booktitle = {2004 International Conference on Image Processing, 2004. ICIP'04.}, doi = {10.1109/ICIP.2004.1421374}, isbn = {0-7803-8554-3}, issn = {15224880}, organization = {IEEE}, pages = {1601--1604}, publisher = {IEEE}, title = {{Fast video shot retrieval by trace geometry matching in principal component space}}, url = {http://ieeexplore.ieee.org/document/1421374/}, volume = {3}, year = {2004} }
@inproceedings{Haohong2004c, author = {{Haohong Wang} and Katsaggelos, Aggelos K A.K. and Wang, Haohong and Katsaggelos, Aggelos K A.K.}, booktitle = {2004 IEEE International Conference on Acoustics, Speech, and Signal Processing}, doi = {10.1109/ICASSP.2004.1326528}, isbn = {0-7803-8484-9}, organization = {IEEE}, pages = {iii----249}, publisher = {IEEE}, title = {{Robust network-adaptive object-based video encoding}}, url = {http://ieeexplore.ieee.org/document/1326528/}, volume = {3}, year = {2004} }
@inproceedings{Eren2004, abstract = {A major limitation faced by a mobile user is their dependence on a limited battery supply. For wireless video communications, joint source coding and transmission power management (JSCPM) has recently been considered as a means of efficiently allocating transmission energy. In order to reduce complexity, the design of many of these adaptive resource allocation algorithms utilizes simplified channel models that do not account for the burstiness of the channel. We analyze the effects of such channel model simplifications on the end-to-end distortion. We present a channel model that is based on information theoretic considerations, which captures the bursty nature of wireless channels and accounts for packet lengths when calculating the probability of loss. Given the source coding and transmission parameters derived using a simplified channel model, our goal is to analyze how the end-to-end distortion is affected when a more realistic complex channel model is used to simulate losses. Experimental results suggest that the performance gain predictions for JSCPM using a simpler channel model are also valid when more sophisticated channel simulations are used, provided that a number of additional steps are taken after the optimization to account for the complex characteristics of wireless channels. {\textcopyright} 2004 IEEE.}, author = {Soyak, F. and Eisenberg, Yiftach and {Fan Zhai} and Berry, Randall and Pappas, T.N. and Katsaggelos, A.K.}, booktitle = {2004 International Conference on Image Processing, 2004. ICIP '04.}, doi = {10.1109/ICIP.2004.1421807}, isbn = {0-7803-8554-3}, issn = {15224880}, pages = {3253--3256}, publisher = {IEEE}, title = {{Channel modeling and its effect on the end-to-end distortion in wireless video communications}}, url = {http://ieeexplore.ieee.org/document/1421807/}, volume = {5}, year = {2004} }
@inproceedings{Zhat2004, author = {{Fan Zhat} and Eisenberg, Y. and Pappas, T.N. N and Berry, R. and Katsaggelos, A.K. K and Zhat, Fan and Eisenberg, Y. and Pappas, T.N. N and Berry, R. and Katsaggelos, A.K. K}, booktitle = {2004 International Conference on Image Processing, 2004. ICIP '04.}, doi = {10.1109/ICIP.2004.1421618}, isbn = {0-7803-8554-3}, pages = {2531--2534}, publisher = {IEEE}, title = {{An integrated joint source-channel coding framework for video transmission over packet lossy networks}}, url = {http://ieeexplore.ieee.org/document/1421618/}, volume = {4}, year = {2004} }
@inproceedings{Passant2003, author = {Karunaratne, Passant V. and Katsaggelos, Aggelos K. and Pappas, Thrasyvoulos N.}, booktitle = {Human Vision and Electronic Imaging VIII}, doi = {10.1117/12.485524}, issn = {0277786X}, pages = {137}, title = {{Preprocessing of compressed digital video based on perceptual quality metrics}}, volume = {5007}, year = {2003} }
@inproceedings{Francisco2003, abstract = {This paper deals with the problem of reconstructing high-resolution text images from an incomplete set of under-sampled, blurred, and noisy images shifted with subpixel displacement. We derive mathematical expressions for the calculation of the maximum a posteriori estimate of the high resolution image and the estimation of the parameters involved in the model. The method is tested on real text images and car plates, examining the impact of blurring and the number of available low resolution images on the final estimate. {\textcopyright} 2003 IEEE.}, author = {Cortijo, F.J. and Villena, Salvador and Molina, Rafael and Katsaggelos, Aggelos}, booktitle = {Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings.}, doi = {10.1109/ISSPA.2003.1224730}, isbn = {0-7803-7946-2}, pages = {421--424 vol.1}, publisher = {IEEE}, title = {{Bayesian super-resolution of text image sequences from low resolution observations}}, url = {http://ieeexplore.ieee.org/document/1224730/}, volume = {1}, year = {2003} }
@inproceedings{Guido2003, abstract = {Object-based video coding requires the transmission of the object shape. This shape is sent as a binary $\alpha$-plane. In lossy packet-based networks, such as the Internet, this information has a non-negligible probability of not arriving at the receiver, and hence its loss needs to be concealed. In this paper we propose a shape concealment technique utilizing Hermite splines. The algorithm has the following steps: (I) the received boundary is detected and the lost boundary parts are grouped using the packet loss pattern. (II) for each of these lost boundary parts, the received boundary points that border the area of the lost boundary parts are collected. These boundary points are then modelled by a second order Hermite spline. This model is subsequently used to match the velocity along the received boundary with the velocity of the concealing cubic Hermite spline. (III) since in most cases there are more than one concealing splines we draw every spline combination that does not result in an intersection and keep all possible results until the end. (IV) if there are more than one possible solutions we select the one that results in one overall closed non-intersecting boundary and fill the interior of the boundary to get the concealed $\alpha$-plane, Experimental results which demonstrate and compare the performance of the proposed concealment method are given at the end of the paper.}, author = {Schuster, G.M. and Li, Xiaohuan and Katsaggelos, A.K.}, booktitle = {Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429)}, doi = {10.1109/ICIP.2003.1246769}, isbn = {0-7803-7750-8}, pages = {II--671--4}, publisher = {IEEE}, title = {{Spline-based boundary loss concealment}}, url = {http://ieeexplore.ieee.org/document/1246769/}, volume = {3}, year = {2003} }
@inproceedings{Ryo2003, abstract = {The estimation of the point spread function (PSF) of the degradation system is often a necessary first step in the restoration of blurred images. In this work, a novel Vector Quantization (VQ)-based blur identification algorithm is presented. A number of codebooks are designed corresponding to various versions of the blurring function. Prototype images blurred by each candidate blur are used. Only the non-flat regions for specific frequency bands are represented by the entries of the codebooks. Given a noisy and blurred image, one of the codebooks is chosen based on a similarity measure, therefore providing the identification of the blur. Simulations are performed for various blurring functions and noise levels. The results demonstrate the effectiveness of the proposed algorithms.}, author = {Nakagaki, Ryo and Katsaggelos, A.K.}, booktitle = {2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).}, doi = {10.1109/ICASSP.2003.1199577}, isbn = {0-7803-7663-3}, issn = {15206149}, pages = {III--725--8}, publisher = {IEEE}, title = {{A VQ-based blur identification algorithm}}, url = {http://ieeexplore.ieee.org/document/1199577/}, volume = {3}, year = {2003} }
@inproceedings{Nasser, author = {Nasser, M Nasrabadi and Aggelos, K Katsaggelos}, booktitle = {SPIE proceedings series}, title = {{Applications of artificial neural networks in image processing VIII}}, year = {2003} }
@inproceedings{li2003temporal, abstract = {Video summary work originates from a viewing time constraint. A shorter version of the original video sequence is desirable in some applications. Clearly, a shorter version is necessary in applications where storage or bandwidth is limited. Our work is based on visual significance analysis of frames in a video sequence and a video temporal rate-distortion optimization framework. Temporal rate defines the number of frames allowable into the video summary, while temporal distortion is computed based on MPEG-7 metrics between mismatched frames. Several one-pass and two-pass algorithms are proposed along with discussions on experimental results.}, author = {Li, Zhu and Katsaggelos, K. and Gandhi, Bhavan and {Zhu Li} and Katsaggelos, K. and Gandhi, Bhavan}, booktitle = {2003 International Conference on Multimedia and Expo. ICME'03. Proceedings (Cat. No. 03TH8698)}, doi = {10.1109/ICME.2003.1221711}, isbn = {0-7803-7965-9}, issn = {1945788X}, organization = {IEEE}, pages = {II--693}, publisher = {IEEE}, title = {{Temporal rate-distortion based optimal video summary generation}}, url = {http://ieeexplore.ieee.org/document/1221711/}, volume = {2}, year = {2003} }
@inproceedings{Guido2003a, abstract = {In this paper we introduce a novel line detection algorithm based on a weighted minimum mean square error (MSE) formulation. This algorithm has been developed to enable an autonomous robot to follow a white line drawn on the floor, but is general in nature and widely applicable to line detection problems. Traditional approaches to line detections consist of two stages, an edge detection stage and a line detection stage using the edge detection result. There are several problems with this approach. First, the initial edge detection stage is sensitive to noise. Second, the second stage does not use all the information available in the image and therefore incorrect decisions made by the first stage cannot be corrected in the second stage. The proposed algorithm achieves its robustness by operating in one step, using all pixels of the image (correctly weighted) and not using any thresholds. The detected line is the solution of a weighted MSE problem. The following three questions are answered in the paper: (I) what mathematical model should be used for the line? (II) how should the weighted MSE problem be set up so that the optimal solution results in the parameters of the line model? And (III), how should the pixels in the image be weighted such that a weighted MSE optimal solution results in a robust line detection? Experimental results demonstrate the performance of the algorithm in noiseless and noisy conditions.}, author = {Schuster, G.M. and Katsaggelos, A.K.}, booktitle = {Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429)}, doi = {10.1109/ICIP.2003.1246956}, isbn = {0-7803-7750-8}, pages = {I--293--6}, publisher = {IEEE}, title = {{Robust line detection using a weighted MSE estimator}}, url = {http://ieeexplore.ieee.org/document/1246956/}, volume = {1}, year = {2003} }
@inproceedings{zhai2003rate, abstract = {Video streaming over the Internet is a challenging task due, in part to the wide range of bandwidth variations caused by network congestion. To deal with this challenge, we propose an optimal error control scheme for scalable video transmission over the Internet. The three major components of error controlerror resilience, forward error correction (FEC), and error concealment-are considered in the proposed framework. Rate-distortion (R-D) optimization is carried out to determine the encoding mode for each packet and the channel coding rates, in order to minimize the overall expected end-to-end distortion. Our simulation study demonstrates that the proposed approach is robust to the wide range channel bandwidth variations and greatly outperforms the classical R-D optimization scheme.}, author = {Zhai, Fan and Beryy, R. and Pappas, T.N. Thrasyvoulos N and Katsaggelos, Aggelos K A.K. and {Fan Zhai} and Beryy, R. and Pappas, T.N. Thrasyvoulos N and Katsaggelos, Aggelos K A.K.}, booktitle = {2003 International Conference on Multimedia and Expo. ICME'03. Proceedings (Cat. No. 03Th8698)}, doi = {10.1109/ICME.2003.1221569}, isbn = {0-7803-7965-9}, issn = {1945788X}, organization = {IEEE}, pages = {II--125}, publisher = {IEEE}, title = {{A rate-distortion optimized error control scheme for scalable video streaming over the internet}}, url = {http://ieeexplore.ieee.org/document/1221569/}, volume = {2}, year = {2003} }
@inproceedings{Miguel2003, abstract = {In this paper we consider the estimation of the unknown hyperparameters for the problem of reconstructing a high-resolution image from multiple undersampled, shifted, blurred and degraded frames with subpixel displacement errors. We derive mathematical expressions for the iterative calculation of the maximum likelihood estimate (mle) of the unknown hyperparameters given the low resolution observed images. Finally, the proposed method is tested on a synthetic image.}, author = {Vega, Miguel and Mateos, Javier and Molina, Rafael and Katsaggelos, A.K.}, booktitle = {Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429)}, doi = {10.1109/ICIP.2003.1246845}, isbn = {0-7803-7750-8}, pages = {II--969--72}, publisher = {IEEE}, title = {{Bayesian parameter estimation in image reconstruction from subsampled blurred observations}}, url = {http://ieeexplore.ieee.org/document/1246845/}, volume = {3}, year = {2003} }
@inproceedings{Javier2003b, abstract = {This paper deals with the problem of reconstructing a high-resolution image from an incomplete set of undersampled, blurred and noisy images shifted with subpixel displacement. We derive mathematical expressions for the calculation of the maximum a posteriori estimate of the high resolution image and the estimation of the parameters involved in the model. We also examine the role played by the prior model when this incomplete set of low resolution images is used. The performance of the method is tested experimentally. {\textcopyright} Springer-Verlag Berlin Heidelberg 2003.}, author = {Mateos, Javier and Vega, Miguel and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {IbPRIA 2003: Pattern Recognition and Image Analysis}, doi = {10.1007/978-3-540-44871-6_63}, isbn = {3540402179}, issn = {16113349}, pages = {538--546}, title = {{Bayesian Image Estimation from an Incomplete Set of Blurred, Undersampled Low Resolution Images}}, url = {http://link.springer.com/10.1007/978-3-540-44871-6_63}, volume = {2652}, year = {2003} }
@inproceedings{Nathan2003, author = {Woods, N.A. and Galatsanos, N.P. and Katsaggelos, A.K.}, booktitle = {Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429)}, doi = {10.1109/ICIP.2003.1246677}, isbn = {0-7803-7750-8}, pages = {II--303--6}, publisher = {IEEE}, title = {{EM-based simultaneous registration, restoration, and interpolation of super-resolved images}}, url = {http://ieeexplore.ieee.org/document/1246677/}, volume = {3}, year = {2003} }
@inproceedings{zhai2003packetization, author = {Zhai, Fan and Eisenberg, Yiftach and Luna, Carlos E and Pappas, Thrasyvoulos N and Berry, R and Katsaggelos, Agggelos K}, booktitle = {PROCEEDINGS OF THE ANNUAL ALLERTON CONFERENCE ON COMMUNICATION CONTROL AND COMPUTING}, number = {3}, organization = {The University; 1998}, pages = {1612--1613}, title = {{Packetization schemes for forward error correction in internet video streaming}}, volume = {41}, year = {2003} }
@inproceedings{wang2003object, abstract = {In object-based video, the encoding of the video data is decoupled into the encoding of shape, motion and texture information, which enables certain functionalities like content-based interactivity and scalability. However, the problem of how to jointly encode these separate signals to reach the best coding efficiency has never been solved thoroughly. In this paper, we present an operational rate-distortion optimal bit allocation scheme that provides a solution to this problem. Our approach is based on the Lagrangian relaxation and dynamic programming. Experimental results indicate that the proposed optimal encoding approach has considerable gains over an ad-hoc method without optimization. Furthermore the proposed algorithm is much more efficient than exhaustive search.}, author = {{Haohong Wang} and Schuster, G.M. Guido M and Katsaggelos, Aggelos K A.K. and Wang, Haohong and Schuster, G.M. Guido M and Katsaggelos, Aggelos K A.K.}, booktitle = {Proceedings 2003 International Conference on Image Processing (Cat. No. 03CH37429)}, doi = {10.1109/ICIP.2003.1247362}, isbn = {0-7803-7750-8}, organization = {IEEE}, pages = {III----785}, publisher = {IEEE}, title = {{Object-based video compression scheme with optimal bit allocation among shape, motion and texture}}, url = {http://ieeexplore.ieee.org/document/1247362/}, volume = {3}, year = {2003} }
@inproceedings{wang2003minmax, author = {{Haohong Wang} and Schuster, G.M. Guido M and Katsaggelos, Aggelos K A.K. and Wang, Haohong and Schuster, G.M. Guido M and Katsaggelos, Aggelos K A.K.}, booktitle = {2003 International Conference on Multimedia and Expo. ICME'03. Proceedings (Cat. No. 03TH8698)}, doi = {10.1109/ICME.2003.1221599}, isbn = {0-7803-7965-9}, organization = {IEEE}, pages = {II----245}, publisher = {IEEE}, title = {{Minmax optimal shape coding using skeleton decomposition}}, url = {http://ieeexplore.ieee.org/document/1221599/}, volume = {2}, year = {2003} }
@inproceedings{Javier2003, abstract = {In this paper we consider the problem of reconstructing a high-resolution image from an incomplete set of undersampled, shifted, degraded frames with subpixel displacement errors. We derive mathematical expressions for the calculation of the maximum a posteriori (MAP) estimate of the high resolution image given the low resolution observed images. We also examine the role played by the prior model when an incomplete set of low resolution images is used. Finally, the proposed method is tested on real and synthetic images.}, author = {Mateos, Javier and Molina, Rafael and Katsaggelos, A.K.}, booktitle = {2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).}, doi = {10.1109/ICASSP.2003.1199572}, isbn = {0-7803-7663-3}, issn = {15206149}, pages = {III--705--8}, publisher = {IEEE}, title = {{Bayesian high resolution image reconstruction with incomplete multisensor low resolution systems}}, url = {http://ieeexplore.ieee.org/document/1199572/}, volume = {3}, year = {2003} }
@inproceedings{abad2003parameter, abstract = {In this paper we consider the estimation of the unknown hyperparameters for the problem of reconstructing a high-resolution image from multiple undersampled, shifted, degraded frames with subpixel displacement errors. We derive mathematical expressions for the iterative calculation of the maximum likelihood estimate (mle) of the unknown hyperparameters given the low resolution observed images. Experimental results are presented for evaluating the accuracy of the proposed method.}, author = {Abad, Javier and Vega, Miguel and Molina, Rafael and Katsaggelos, A.K.}, booktitle = {2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).}, doi = {10.1109/ICASSP.2003.1199573}, isbn = {0-7803-7663-3}, issn = {15206149}, organization = {IEEE}, pages = {III--709--12}, publisher = {IEEE}, title = {{Parameter estimation in super-resolution image reconstruction problems}}, url = {http://ieeexplore.ieee.org/document/1199573/}, volume = {3}, year = {2003} }
@inproceedings{zhai2003novel, abstract = {This paper presents a novel framework for streaming video over a Differentiated Services (DiffServ) network that jointly considers video source coding, packet classification and error concealment within the scope of cost-distortion optimization. Our formulation incorporates the random network delay for each packet into the calculation of the probability of packet loss and manages the end-to-end packet delay by selecting the encoding parameters and packet priority. We formulate two approaches to evaluate the performance of the proposed framework: A minimum distortion approach and a minimum cost approach, in which the encoding mode and priority class for each packet are optimally selected so as to minimize the total distortion subject to cost constraints, or to minimize the total cost subject to end-to-end distortion constraints. Simulation results demonstrate the advantage of jointly adapting the source coding and packet classification.}, author = {{Fan Zhai} and Luna, Carlos E C.E. and Eisenberg, Yiftach and Pappas, T.N. Thrasyvoulos N and Berry, Randall and Katsaggelos, Aggelos K A.K. and Zhai, Fan and Luna, Carlos E C.E. and Eisenberg, Yiftach and Pappas, T.N. Thrasyvoulos N and Berry, Randall and Katsaggelos, Aggelos K A.K.}, booktitle = {Proceedings 2003 International Conference on Image Processing (Cat. No. 03CH37429)}, doi = {10.1109/ICIP.2003.1247239}, isbn = {0-7803-7750-8}, organization = {IEEE}, pages = {III----293}, publisher = {IEEE}, title = {{A novel cost-distortion optimization framework for video streaming over differentiated services networks}}, url = {http://ieeexplore.ieee.org/document/1247239/}, volume = {3}, year = {2003} }
@inproceedings{Tom2003, abstract = {The problem of finding the optimal set of quantized coefficients for a frame-based encoded signal is known to be of very high complexity. This paper presents an efficient method of finding the operational Rate-Distortion (RD) optimal set of coefficients. The major complexity reduction lies in the reformulation of the original RD-tradeoff problem, where a new set of coefficients is used as decision variables. These coefficients are connected to the orthogonalization of the set of selected frame vectors and not to the frame vectors themselves. By organizing all possible solutions as nodes in a solution tree, we use complexity saving techniques to find the optimal solution in an even more efficient way. Using an ordered vector selection process, the complexity can be again significantly reduced and efficient Run-length encoding becomes feasible. Contrary to the original problem, the new problem can be solved optimally in a reasonable amount of time.}, author = {Ryen, Tom and Schuster, G.M. and Katsaggelos, A.K.}, booktitle = {Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429)}, doi = {10.1109/ICIP.2003.1247360}, isbn = {0-7803-7750-8}, pages = {III--777--80}, publisher = {IEEE}, title = {{Efficient frame vector selection based on ordered sets}}, url = {http://ieeexplore.ieee.org/document/1247360/}, volume = {2}, year = {2003} }
@inproceedings{Petar2003, abstract = {The presence of visual information in addition to audio could improve speech understanding in noisy environments. This additional information could be especially useful for people with impaired hearing who are able to speechread. This paper focuses on the problem of synthesizing the Facial Animation Parameters (FAPs), supported by the MPEG-4 standard for the visual representation of speech, from a narrowband acoustic speech (telephone) signal. A correlation Hidden Markov Model (CHMM) system for performing visual speech synthesis is proposed. The CHMM system integrates an independently trained acoustic HMM (AHMM) system and a visual HMM (VHMM) system, in order to realize speech-to-video synthesis. Objective experiments are performed by analyzing the synthesized FAPs and computing the time alignment errors. Time alignment errors are reduced by 40.5% compared to the conventional temporal scaling method.}, author = {Aleksic, P.S. and Katsaggelos, A.K.}, booktitle = {Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429)}, doi = {10.1109/ICIP.2003.1247166}, isbn = {0-7803-7750-8}, pages = {III--1--4}, publisher = {IEEE}, title = {{Speech-to-video synthesis using facial animation parameters}}, url = {http://ieeexplore.ieee.org/document/1247166/}, volume = {2}, year = {2003} }
@inproceedings{wang2003operational, author = {{Haohong Wang} and Schuster, G.M. Guido M and Katsaggelos, Aggelos K A.K. and Wang, Haohong and Schuster, G.M. Guido M and Katsaggelos, Aggelos K A.K.}, booktitle = {2003 International Conference on Multimedia and Expo. ICME'03. Proceedings (Cat. No. 03TH8698)}, doi = {10.1109/ICME.2003.1221602}, isbn = {0-7803-7965-9}, organization = {IEEE}, pages = {II----257}, publisher = {IEEE}, title = {{Operational rate-distortion optimal bit allocation between shape and texture for MPEG-4 video coding}}, url = {http://ieeexplore.ieee.org/document/1221602/}, volume = {2}, year = {2003} }
@inproceedings{Yiftach2003, abstract = {The problem of encoding and transmitting a video sequence over a wireless channel is considered. Our objective is to minimize the end-to-end distortion while using a limited amount of transmission energy and delay. In our approach, we jointly adapt the source-coding parameters and transmission power per packet. We introduce the concept of "Variance-Aware Distortion Estimation" (VADE), and present a framework for controlling both the expected value and the variance of the end-to-end distortion. This framework is based on knowledge of how the video is compressed, the probability of packet loss, and the concealment strategy. To the best of our knowledge, this paper is the first to address the trade-off between the mean and variance of the end-to-end distortion. Experimental results demonstrate the potential of the proposed approach.}, author = {Eisenberg, Yiftach and Zhai, Fan and Luna, C.E. and Pappas, T.N. and Berry, Randall and Katsaggelos, A.K.}, booktitle = {Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429)}, doi = {10.1109/ICIP.2003.1246905}, isbn = {0-7803-7750-8}, pages = {I--89--92}, publisher = {IEEE}, title = {{Variance-aware distortion estimation for wireless video communications}}, url = {http://ieeexplore.ieee.org/document/1246905/}, volume = {1}, year = {2003} }
@inproceedings{aleksic2003product, abstract = {The use of visual information in addition to acoustic can improve automatic speech recognition. In this paper we compare different approaches for audio-visual information integration and show how they affect automatic speech recognition performance. We utilize facial animation parameters (FAPs), supported by the MPEG-4 standard for the visual representation as visual features. We use both single-stream and multi-stream hidden Markov models (HMM) to integrate audio and visual information. We performed both state and phone synchronous multi-stream integration. Product HMM topology is used to model the phone-synchronous integration. ASR experiments were performed under noisy audio conditions using a relatively large vocabulary (approximately 1000 words) audio-visual database. The proposed phone-synchronous system, which performed the best, reduces the word error rate (WER) by approximately 20% relatively to audio-only ASR (A-ASR) WERs, at various SNRs with additive white Gaussian noise.}, author = {Aleksic, P.S. and Katsaggelos, A.K.}, booktitle = {2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698)}, doi = {10.1109/ICME.2003.1221658}, isbn = {0-7803-7965-9}, issn = {1945788X}, organization = {IEEE}, pages = {II--481}, publisher = {IEEE}, title = {{Product HMMs for audio-visual continuous speech recognition using facial animation parameters}}, url = {http://ieeexplore.ieee.org/document/1221658/}, volume = {2}, year = {2003} }
@inproceedings{segall2002reconstruction, abstract = {A framework for recovering high-resolution information from a sequence of sub-sampled and compressed observations is presented. Compression schemes that describe a video sequence through a combination of motion vectors and transform coefficients are the focus (e.g. the MPEG and ITU family of standards), and we consider the influence of both the motion vectors and transform coefficients within the reconstruction algorithm. A Bayesian approach is utilized to incorporate the information, and results show a discernable improvement in resolution, as compared to standard interpolation methods.}, author = {Segall, C. Andrew and Molina, Rafael and Katsaggelos, Aggelos K. and Mateos, Javier}, booktitle = {IEEE International Conference on Acoustics Speech and Signal Processing}, doi = {10.1109/ICASSP.2002.5744948}, isbn = {0-7803-7402-9}, issn = {15206149}, month = {may}, organization = {IEEE}, pages = {II--1701--II--1704}, publisher = {IEEE}, title = {{Reconstruction of high-resolution image frames from a sequence of low-resolution and compressed observations}}, url = {http://ieeexplore.ieee.org/document/5744948/}, volume = {2}, year = {2002} }
@inproceedings{luna2002joint, author = {Luna, C E and Eisenberg, Y and Berry, R and Pappas, T N and Katsaggelos, A K}, booktitle = {Tyrrhenian International Workshop on Digital Communications (IWDC)}, title = {{Joint source coding and packet marking for video transmission over Diffserv networks}}, year = {2002} }
@inproceedings{Zhu2002, abstract = {Color vector quantization (VQ) has been an efficient still image compression scheme as well as a popular bitmap graphics format for display devices with limited color capability. In this paper we are proposing a color vector quantization-based video coder, exploiting the temporal stationary nature of color distribution among a group of pictures (GOP) over a short period. Color VQ is applied first to reduce the RGB image sequence into a single channel color index image. Motion estimation and compression is then performed in the index space, instead of the separate YCbCr channels. Initial results demonstrated that the proposed coder can provide good compression rates. By eliminating the need for an inverse DCT and color conversion, typical requirements in a JPEG/MPEG type of coders, the decoding is computationally very simple. This makes it suitable for certain applications like media playback, and visual communications with low-end mobile devices.}, author = {Li, Zhu and Katsaggelos, Aggelos K A.K. and {Zhu Li} and Katsaggelos, Aggelos K A.K.}, booktitle = {Proceedings. International Conference on Image Processing}, doi = {10.1109/ICIP.2002.1039060}, isbn = {0-7803-7622-6}, organization = {IEEE}, pages = {III--673--III--676}, publisher = {IEEE}, title = {{A color vector quantization based video coder}}, url = {http://ieeexplore.ieee.org/document/1039060/}, volume = {3}, year = {2002} }
@inproceedings{Yiftach2002, abstract = {We consider the problem of compressing a video sequence for transmission over a wireless channel. In our approach we jointly consider error resilience and concealment techniques, at the source coding level, and transmission power management at the physical layer. We formulate a minimum-maximum distortion problem, where our goal is to either (i) minimize the total transmission energy for a given maximum expected distortion, or (ii) minimize the maximum expected distortion at the receiver for a given maximum transmission energy. Experimental results show that simultaneously adjusting the source coding and transmission power is more energy efficient than considering these factors separately.}, author = {Eisenberg, Yiftach and Luna, C.E. and Pappas, T.N. and Berry, R. and Katsaggelos, A.K.}, booktitle = {Proceedings. International Conference on Image Processing}, doi = {10.1109/ICIP.2002.1038079}, isbn = {0-7803-7622-6}, pages = {I--537--I--540}, publisher = {IEEE}, title = {{Optimal source coding and transmission power management using a min-max expected distortion approach}}, url = {http://ieeexplore.ieee.org/document/1038079/}, volume = {1}, year = {2002} }
@inproceedings{Yiftach2002a, abstract = {In the future, digital set-top boxes may serve as the primary access point for wireless home networks, enabling mobile users to use video conferencing as well as streaming applications on hand-held devices. In this scenario, an important issue that must be addressed is the limited energy supply of a mobile device. This is of course a relevant issue for any wireless device. We focus on methods for efficiently utilizing transmission energy in wireless video communications. We present a general framework for the problem of minimizing the transmission energy required to provide an acceptable level of video quality. We discuss two special cases in which communication resources are adjusted simultaneously with the source coding parameters in order to provide (i) packet loss adaptation and (ii) transmission rate adaptation.}, author = {Eisenberg, Yiftach and Luna, C.E. and Pappas, T.N. and Berry, Randall and Katsaggelos, A.K.}, booktitle = {Proceedings. International Conference on Image Processing}, doi = {10.1109/ICIP.2002.1039878}, isbn = {0-7803-7622-6}, pages = {II--25--II--28}, publisher = {IEEE}, title = {{Energy efficient wireless video communications for the digital set-top box}}, url = {http://ieeexplore.ieee.org/document/1039878/}, volume = {2}, year = {2002} }
@inproceedings{Tom2002, author = {Ryen, Tom and Schuster, Guido M and Katsaggelos, Aggelos K}, booktitle = {Proc. of Nordic Signal Processing Symposium}, title = {{A frame-based rate-distortion optimal coding system using a lower bound depth-first-search strategy}}, url = {http://ivpl.ece.northwestern.edu/sites/default/files/cr1073.pdf}, year = {2002} }
@inproceedings{Rafael2002, abstract = {In this paper we present a multichannel image restoration method using Compound Gauss Markov Random Field (CGMRF) models. Information regarding the objects present in the scene is shared via the line process in the CGMRF. Two new iterative algorithms to estimate the underlying multichannel image are presented, which can be considered as extensions of the classical simulated annealing and ICM methods. Experimental results demonstrate the effectiveness of the proposed approach. {\textcopyright} 2002 IEEE.}, author = {Molina, Rafael and Mateos, Javier and Katsaggelos, A.K. and Vega, Miguel}, booktitle = {Object recognition supported by user interaction for service robots}, doi = {10.1109/ICPR.2002.1048153}, isbn = {0-7695-1695-X}, issn = {10514651}, number = {3}, pages = {835--838}, publisher = {IEEE Comput. Soc}, title = {{A general multichannel image restoration method using compound models}}, url = {http://ieeexplore.ieee.org/document/1048153/}, volume = {3}, year = {2002} }
@inproceedings{Stavros2002a, author = {Tzavidas, Stavros and Katsaggelos, Aggelos K}, booktitle = {Three-Dimensional Image Capture and Applications V}, doi = {10.1117/12.460180}, editor = {Corner, Brian D. and Pargas, Roy P. and Nurre, Joseph H.}, month = {mar}, organization = {SPIE}, pages = {47--58}, title = {{Multicamera setup for generating stereo panoramic video}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=876109}, volume = {4661}, year = {2002} }
@inproceedings{SungCheolPark2002, abstract = {The problem of recovering a high-resolution image from a sequence of low-resolution DCT-based compressed images is considered in this paper. The presence of the compression system complicates the recovery problem, as the operation reduces the amount of frequency aliasing in the low-resolution frames and introduces a non-linear quantization process. The effect of the quantization error and resulting inaccurate sub-pixel motion information is modeled as a zero-mean additive correlated Gaussian noise. A regularization functional is introduced not only to reflect the relative amount of registration error in each low-resolution image but also to determine the regularization parameter without any prior knowledge in the reconstruction procedure. The effectiveness of the proposed algorithm is demonstrated experimentally.}, author = {Park, Sung Cheol and Kang, Moon Gi and Segall, C.A. Andrew and Katsaggelos, Aggelos K. A.K. and {Sung Cheol}, Park and {Moon Gi}, Kang and Segall, C.A. Andrew and Aggelos, K Katsaggelos and {Sung Cheal}, Park and {Moon Gi}, Kang and Segall, C.A. Andrew and Aggelos, K Katsaggelos and {Sung Cheol Park} and {Moon Gi Kang} and Segall, C.A. Andrew and Katsaggelos, Aggelos K. A.K.}, booktitle = {Proceedings. International Conference on Image Processing}, doi = {10.1109/ICIP.2002.1040087}, isbn = {0-7803-7622-6}, issn = {10577149}, keywords = {DCT-based compression,High-resolution image reconstruction,Quantization noise,Regularization}, number = {4}, organization = {IEEE}, pages = {II----II}, pmid = {15376591}, publisher = {IEEE}, title = {{Spatially adaptive high-resolution image reconstruction of low-resolution DCT-based compressed images}}, url = {http://ieeexplore.ieee.org/document/1040087/}, volume = {2}, year = {2002} }
@inproceedings{Zhilin2002, abstract = {It is very important to accurately track the mouth of a talking person for many applications, such as face recognition and human computer interaction. This is in general a difficult problem due to the complexity of shapes, colors, textures, and changing lighting conditions. We develop techniques for outer and inner lip tracking. From the tracking results FAPs are extracted which are used to drive an MPEG-4 decoder. A novel method consisting of a Gradient Vector Flow (GVF) snake with a parabolic template as an additional external force is proposed. Based on the results of the outer lip tracking, the inner lip is tracked using a similarity function and a temporal smoothness constraint. Numerical results are presented using the Bernstein database.}, author = {Wu, Zhilin and Aleksic, P.S. S. and Katsaggelos, A.K. K. and {Zhilin Wu} and Aleksic, P.S. S. and Katsaggelos, A.K. K.}, booktitle = {Proceedings. Fourth IEEE International Conference on Multimodal Interfaces}, doi = {10.1109/ICMI.2002.1167009}, isbn = {0-7695-1834-6}, organization = {IEEE}, pages = {293--298}, publisher = {IEEE Comput. Soc}, title = {{Lip tracking for MPEG-4 facial animation}}, url = {http://ieeexplore.ieee.org/document/1167009/}, year = {2002} }
@inproceedings{Laura2002, author = {Drake, L. and Katsaggelos, A.K. and Rutledge, J.C. and {Jun Zhang}}, booktitle = {Sensor Array and Multichannel Signal Processing Workshop Proceedings, 2002}, doi = {10.1109/SAM.2002.1191040}, isbn = {0-7803-7551-3}, pages = {259--263}, publisher = {IEEE}, title = {{Sound source separation via computational auditory scene analysis-enhanced beamforming}}, url = {http://ieeexplore.ieee.org/document/1191040/}, year = {2002} }
@inproceedings{Xiaohuan2002a, author = {Xiaohuan, Li and Guido, M Schuster and Katsaggelos, A K}, booktitle = {Proceedings of the 5th Nordic Signal Processing Symposium}, pages = {4--7}, title = {{Curve-fitting algorithms for shape error concealment}}, year = {2002} }
@inproceedings{Stavros2002, abstract = {In this paper we study the problem of generating stereo panoramic video. We propose a setup based on the theory of circular projections and we demonstrate that it is capable of generating stereo panoramic images at video rates. We further study some of the limitations involved in a practical implementation of the proposed setup, with an emphasis on the effects on the disparity, as perceived by human observers.}, author = {Tzavidas, Stavros and Katsaggelos, A.K.}, booktitle = {Proceedings. International Conference on Image Processing}, doi = {10.1109/ICIP.2002.1039104}, isbn = {0-7803-7622-6}, pages = {845--848}, publisher = {IEEE}, title = {{Disparity variation in stereo-panoramic video}}, url = {http://ieeexplore.ieee.org/document/1039104/}, volume = {1}, year = {2002} }
@inproceedings{Ryo2002, abstract = {In this paper, we develop a novel VQ-based image restoration algorithm. The mapping between high frequency information in the original images and low frequency information in the corresponding degraded ones is established and stored in the VQ codebooks. Prototype images are used, which belong to the same class of images. During restoration, the high frequency information of a given degraded image is estimated from its low frequency information based on the designed codebook. To make the restoration process computationally efficient, the Principal Component Analysis (PCA) and VQ-Nearest Neighborhood approaches are utilized. Simulation results are presented to demonstrate the effectiveness of the proposed algorithm.}, author = {Nakagaki, Ryo and Katsaggelos, A.K.}, booktitle = {Proceedings. International Conference on Image Processing}, doi = {10.1109/ICIP.2002.1038020}, isbn = {0-7803-7622-6}, pages = {I--305--I--308}, publisher = {IEEE}, title = {{A VQ-based image restoration algorithm}}, url = {http://ieeexplore.ieee.org/document/1038020/}, volume = {1}, year = {2002} }
@inproceedings{Antonio2002a, abstract = {In this work we develop a Bayesian reconstruction method for SPECT (Single Photon Emission Computed Tomography) images, using as prior GGMRF (Generalized Gaussian Markov Random Fields) distributions and estimating the scale hyperparameter following the Evidence Analysis. Preconditioning methods are used to estimate this hyperparameter and the approximations used are compared on synthetic images.}, author = {Lopez, A. and Molina, R. and Katsaggelos, A.K.}, booktitle = {2002 14th International Conference on Digital Signal Processing Proceedings. DSP 2002 (Cat. No.02TH8628)}, doi = {10.1109/ICDSP.2002.1028142}, isbn = {0-7803-7503-3}, pages = {521--524}, publisher = {IEEE}, title = {{Scale hyperparameter estimation for GGMRF prior models with application to SPECT images}}, url = {http://ieeexplore.ieee.org/document/1028142/}, volume = {2}, year = {2002} }
@inproceedings{li2002recursive, abstract = {The encoding of shape information is a distinguishing feature of MPEG-4. In error prone communication networks, it is important and efficient to conceal shape errors spatially, so as to avoid propagation of errors in the video frames. The proposed system first defines the missing area's four rectangular neighbors. It then detects in the neighbors the lines that intersect the borders and redefines them in a geometric coordinate system. These lines are paired under some optimization objective so that they connect smoothly in the missing area. Each pair is extrapolated and corrected recursively until a close curve is formed. Test results on various sequences under various error rates are presented and compared with other shape concealment methods.}, author = {Li, Xiaohuan and Katsaggelos, A.K. K and Schuster, G.M. Guido M and {Xiaohuan Li} and Katsaggelos, A.K. K and Schuster, G.M. Guido M}, booktitle = {Proceedings. International Conference on Image Processing}, doi = {10.1109/ICIP.2002.1037988}, isbn = {0-7803-7622-6}, organization = {IEEE}, pages = {I----I}, publisher = {IEEE}, title = {{A recursive shape error concealment algorithm}}, url = {http://ieeexplore.ieee.org/document/1037988/}, volume = {1}, year = {2002} }
@inproceedings{katsaggelos2002applications, author = {Katsaggelos, Aggelos K and Nasrabadi, Nasser M}, organization = {SPIE-International Society for Optical Engineering}, title = {{Applications of Artificial Neural Networks in Image Processing VII}}, year = {2002} }
@inproceedings{wang2002optimal, abstract = {This paper presents an operational rate-distortion (ORD) optimal approach for skeleton-based boundary encoding. The boundary information is first decomposed into skeleton and distance signals, by which a more efficient representation of the original boundary results. Curves of arbitrary order are utilized for approximating the skeleton and distance signals. For a given bit budget for a video frame, we solve the problem of choosing the number and location of the control points for all skeleton and distance signals and for all boundaries within a frame, so that the overall distortion is minimized. The problem is solved with the use of Lagrangian relaxation and a shortest path algorithm in a 4D directed acyclic graph (DAG) we propose. By defining a path selection pattern, we reduce the computational complexity of the 4D DAG shortest path algorithm from O(N/sup-5/) to O(N/sup-4/), where N is the number of admissible control points for a skeleton. A suboptimal solution is also presented for further reducing the computational complexity of the algorithm to O(N/sup-2/). The proposed algorithm outperforms experimentally other competing algorithms.}, author = {{Haohong Wang} and Schuster, G.M. Guido M and Katsaggelos, Aggelos K A.K. and Pappas, T.N. Thrasyvoulos N and Wang, Haohong and Schuster, G.M. Guido M and Katsaggelos, Aggelos K A.K. and Pappas, T.N. Thrasyvoulos N}, booktitle = {2002 IEEE Workshop on Multimedia Signal Processing.}, doi = {10.1109/MMSP.2002.1203254}, isbn = {0-7803-7713-3}, keywords = {optimaL,shape coding,skeleton decomposition}, organization = {IEEE}, pages = {85--88}, publisher = {IEEE}, title = {{An optimal shape encoding scheme using skeleton decomposition}}, url = {http://ieeexplore.ieee.org/document/1203254/}, year = {2002} }
@inproceedings{brailean1993recursive, author = {Brailean, J.C. and Katsaggelos, A.K.}, booktitle = {Proceedings of MILCOM '93 - IEEE Military Communications Conference}, doi = {10.1109/MILCOM.1993.408620}, isbn = {0-7803-0953-7}, organization = {IEEE}, pages = {485--489}, publisher = {IEEE}, title = {{Recursive displacement estimation for use in multiple object tracking}}, url = {http://ieeexplore.ieee.org/document/408620/}, volume = {2}, year = {2002} }
@inproceedings{segall2000preprocessing, abstract = {Pre-processing algorithms improve on the performance of a video compression system by removing spurious noise and insignificant features from the original images. This increases compression efficiency and attenuates coding artifacts. Unfortunately, determining the appropriate amount of pre-filtering is a difficult problem, as it depends on both the content of an image as well as the target bit-rate of compression algorithm. In this paper, we explore a pre-processing technique that is loosely coupled to the quantization decisions of a rate control mechanism. This technique results in a pre-processing system that operates directly on the Displaced Frame Difference (DFD) and is applicable to any standard-compatible compression system. Results explore the effect of several standard filters on the DFD. An adaptive technique is then considered.}, author = {Segall, C A and Karunaratne, P and Katsaggelos, A K}, booktitle = {Visual Communications and Image Processing 2001}, isbn = {0-8194-3988-6}, issn = {0277-786X}, keywords = {pre-processing; image compression; adaptive filter}, organization = {SPIE}, pages = {163--174}, title = {{Pre-processing of compressed digital video}}, volume = {4310}, year = {2001} }
@inproceedings{Ranveig2001, abstract = {In this paper we present a time domain signal compression algorithm based on the coding of line segments which are used to approximate the signal. These segments are fit in a way that is optimal in the rate distortion sense. The approach is applicable to many types of signals, but in this paper we focus on the compression of ElectroCardioGram (ECG) signals. As opposed to traditional time-domain algorithms, where heuristics are used to extract representative signal samples from the original signal, an optimization algorithm is formulated in [1, 2, 3] for sample selection using graph theory, with linear interpolation applied to the reconstruction of the signal. In this paper the algorithm in [1, 2, 3] is generalized by using second order polynomial interpolation for the reconstruction of the signal from the extracted signal samples. The polynomials are fitted in a way that guarantees minimum reconstruction error given an upper bound on the number of bits. The method achieves good performance compared both to the case where linear interpolation is used in reconstruction of the signal and to other state-of-the-art ECG coders.}, author = {Nygaard, R. and Katsaggelos, A.K.}, booktitle = {2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221)}, doi = {10.1109/ICASSP.2001.940538}, isbn = {0-7803-7041-4}, issn = {15206149}, pages = {2617--2620}, publisher = {IEEE}, title = {{Rate distortion optimal signal compression using second order polynomial approximation}}, url = {http://ieeexplore.ieee.org/document/940538/}, volume = {4}, year = {2001} }
@inproceedings{segall2001bayesian, abstract = {A method for simultaneously estimating the high-resolution frames and the corresponding motion field from a compressed low-resolution video sequence is presented. The algorithm incorporates knowledge of the spatio-temporal correlation between low and high-resolution images to estimate the original high-resolution sequence from the degraded low-resolution observation. Information from the encoder is also exploited, including the transmitted motion vectors, quantization tables, coding modes and quantizer scale factors. Simulations illustrate an improvement in the peak signal-to-noise ratio when compared with traditional interpolation techniques and are corroborated with visual results.}, author = {Segall, C.A. and Molina, R. and Katsaggelos, A.K. and Mateos, J.}, booktitle = {Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205)}, doi = {10.1109/ICIP.2001.958415}, isbn = {0-7803-6725-1}, organization = {IEEE}, pages = {25--28}, publisher = {IEEE}, title = {{Bayesian high-resolution reconstruction of low-resolution compressed video}}, url = {http://ieeexplore.ieee.org/document/958415/}, volume = {2}, year = {2001} }
@inproceedings{Passant2001, author = {Karunaratne, P.V. and Segall, C.A. and Katsaggelos, A.K.}, booktitle = {Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205)}, doi = {10.1109/ICIP.2001.959058}, isbn = {0-7803-6725-1}, pages = {481--484}, publisher = {IEEE}, title = {{A rate-distortion optimal video pre-processing algorithm}}, url = {http://ieeexplore.ieee.org/document/959058/}, volume = {1}, year = {2001} }
@inproceedings{segall2001application, abstract = {In this paper, we present a novel fidelity constraint for the image enhancement problem by exploiting the motion vectors of a compressed video bit-stream. These vectors establish a correspondence between image pixels across a series of frames, and our goal is to maintain this relationship during processing. In our past work, we considered algorithms that relied on the sum-of-absolute differences as the match criteria. As we show in this paper, this metric is problematic for the enhancement problem. We then pose the constraint within the context of a sum-of-squared errors criterion for matching. This allows for a more rigorous treatment of the fidelity constraint. Finally, experimental results illustrate the performance of the new constraint.}, author = {Segall, C.A. and Katsaggelos, A.K.}, booktitle = {Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205)}, doi = {10.1109/ICIP.2001.959128}, isbn = {0-7803-6725-1}, organization = {IEEE}, pages = {646--649}, publisher = {IEEE}, title = {{Application of the motion vector constraint to the regularized enhancement of compressed video}}, url = {http://ieeexplore.ieee.org/document/959128/}, volume = {1}, year = {2001} }
@inproceedings{segall2001new, abstract = {A novel fidelity constraint to the image enhancement problem is presented. With this constraint, we exploit the motion vectors of a compressed video bit-stream. These vectors establish a correspondence between image pixels across a series of frames, and we guarantee that processing the decoded sequence does not violate this correspondence. We develop the constraint within the context of MPEG-2 and incorporate the constraint into a regularized enhancement algorithm. Simulations are then performed. Quantitative and qualitative results illustrate an improvement in visual quality.}, author = {Segall, C.A. and Katsaggelos, A.K.}, booktitle = {2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221)}, doi = {10.1109/ICASSP.2001.941303}, isbn = {0-7803-7041-4}, issn = {15206149}, organization = {IEEE}, pages = {1849--1852}, publisher = {IEEE}, title = {{A new constraint for the regularized enhancement of compressed video}}, url = {http://ieeexplore.ieee.org/document/941303/}, volume = {3}, year = {2001} }
@inproceedings{Lisimachos2001b, abstract = {A joint source-channel coding scheme for scalable video is developed in this paper. An SNR scalable video coder is used and Unequal Error Protection (UEP) is allowed for each scalable layer. Our problem is to allocate the available bit rate across scalable layers and, within each layer, between source and channel coding, while minimizing the end-to-end distortion of the received video sequence. The resulting optimization algorithm we propose utilizes universal rate-distortion characteristics plots. These plots show the contribution of each layer to the total distortion as a function of the source rate of the layer and the residual bit error rate (the error rate that remains after the use of channel coding). Models for these plots are proposed in order to reduce the computational complexity of the solution. Experimental results demonstrate the effectiveness of the proposed approach.}, author = {Kondi, L.P. and Katsaggelos, A.K.}, booktitle = {2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221)}, doi = {10.1109/ICASSP.2001.941185}, isbn = {0-7803-7041-4}, issn = {15206149}, pages = {1377--1380}, publisher = {IEEE}, title = {{Joint source-channel coding for scalable video using models of rate-distortion functions}}, url = {http://ieeexplore.ieee.org/document/941185/}, volume = {3}, year = {2001} }
@inproceedings{luna2001joint, author = {Luna, C and Eisenburg, Y and Pappas, T and Berry, Randall and Katsaggelos, A}, booktitle = {Proceedings of 35th Asilomar Conference on Signals, Systems, and Computers}, title = {{Joint Source Channel Coding for Efficient Energy Utilization in Wireless Video Communication}}, url = {http://www.researchgate.net/profile/Aggelos_Katsaggelos/publication/3308395_Joint_Source_Coding_and_Transmission_Power_Management_for_Energy_Efficient_Wireless_Video_Communications/links/54e34a280cf2d618e19635a1/Joint-Source-Coding-and-Transmission-Power-}, year = {2001} }
@inproceedings{Nasser, author = {Nasser, M Nasrabadi and Aggelos, K Katsaggelos}, booktitle = {SPIE proceedings series}, title = {{Applications of artificial neural networks in image processing VI}}, year = {2001} }
@inproceedings{Jay2001, author = {Williams, Jay J and Katsaggelos, Aggelos K and Garstecki, Dean C}, booktitle = {Human Vision and Electronic Imaging VI}, doi = {10.1117/12.429527}, editor = {Rogowitz, Bernice E. and Pappas, Thrasyvoulos N.}, month = {jun}, pages = {544--555}, title = {{Subjective analysis of a HMM-based visual speech synthesizer}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=903817}, volume = {4299}, year = {2001} }
@inproceedings{Haohong2001, author = {Wang, Haohong and Katsaggelos, A.K. and Pappas, T.N.}, booktitle = {Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205)}, doi = {10.1109/ICIP.2001.958665}, isbn = {0-7803-6725-1}, pages = {1001--1004}, publisher = {IEEE}, title = {{Rate-distortion optimal skeleton-based shape coding}}, url = {http://ieeexplore.ieee.org/document/958665/}, volume = {2}, year = {2001} }
@inproceedings{Lisimachos2001, abstract = {A major problem in object oriented video coding and MPEG-4 is the encoding of object boundaries. Traditionally, and within MPEG-4, the encoding of shape and texture information are separate steps (the extraction of shape is not considered by the standards). In this paper, we present a vertex-based shape coding method which is optimal in the operational rate-distortion sense and takes into account the texture information of the video frames. This is accomplished by utilizing a variable-width tolerance band which is proportional to the degree of trust in the accuracy of the shape information at that location. Thus, in areas where the confidence in the estimation of the boundary is not high and/or coding errors in the boundary will not affect the application (object oriented coding, MPEG-4, etc.) significantly, a larger boundary approximation error is allowed. We present experimental results which demonstrate the effectiveness of the proposed algorithm.}, author = {Kondi, L.P. and Melnikov, G. and Katsaggelos, A.K.}, booktitle = {Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205)}, doi = {10.1109/ICIP.2001.958059}, isbn = {0-7803-6725-1}, pages = {94--97}, publisher = {IEEE}, title = {{Jointly optimal coding of texture and shape}}, url = {http://ieeexplore.ieee.org/document/958059/}, volume = {2}, year = {2001} }
@inproceedings{Carlos2001, abstract = {Transmitter energy is a valuable resource in wireless networks. Transmitter power management can have an impact on battery life for mobile users, link level QoS and network capacity. We consider efficient use of transmitter energy in a streaming application. We formulate an optimization problem that corresponds to minimizing the transmission energy required to achieve an acceptable level of distortion subject to a delay constraint. By considering jointly the selection of coding parameters and transmitter power we can formulate an optimal policy. We present results illustrating the advantages of jointly considering these two variables.}, author = {Luna, C.E. and Eisenberg, Yiftach and Berry, Randall and Pappas, Thrasyvoulos and Katsaggelos, Aggelos}, booktitle = {Conference Record of Thirty-Fifth Asilomar Conference on Signals, Systems and Computers (Cat.No.01CH37256)}, doi = {10.1109/ACSSC.2001.986902}, isbn = {0-7803-7147-X}, issn = {10586393}, pages = {185--189 vol.1}, publisher = {IEEE}, title = {{Transmission energy minimization in wireless video streaming applications}}, url = {http://ieeexplore.ieee.org/document/986902/}, volume = {1}, year = {2001} }
@inproceedings{Yiftach2001, abstract = {A key constraint in mobile communications is the reliance on a battery with a limited energy supply. Efficiently utilizing the available energy is therefore an important design consideration. In this paper we consider a situation where a video sequence is to be compressed and transmitted over a wireless channel. The goal is to limit the amount of distortion in the received video sequence while using the minimum required transmission energy. To accomplish this goal we consider error resilience and concealment techniques, at the source coding level, as well as the dynamic allocation of physical layer communication resources. We jointly consider these approaches in a novel framework. In this setting we formulate an optimization problem that corresponds to minimizing the energy required to transmit a video frame with an acceptable level of distortion. We present methods for solving this problem and other extensions.}, author = {Eisenberg, Y. and Pappas, T.N. and Berry, R. and Katsaggelos, A.K.}, booktitle = {Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205)}, doi = {10.1109/ICIP.2001.959206}, isbn = {0-7803-6725-1}, pages = {958--961}, publisher = {IEEE}, title = {{Minimizing transmission energy in wireless video communications}}, url = {http://ieeexplore.ieee.org/document/959206/}, volume = {1}, year = {2001} }
@inproceedings{kondi2001joint, abstract = {In this paper, we extend our previous work on joint source-channel coding to scalable video transmission over wireless direct-sequence code-division-multiple-access (DS-CDMA) multipath fading channels. An SNR scalable video coder is used and unequal error protection (UEP) is allowed for each scalable layer. At the receiver-end an adaptive antenna array Auxiliary-Vector (AV) filter is utilized that provides space-time RAKE-type processing and multiple-access interference suppression. The choice of the AV receiver is dictated by realistic channel fading rates that limit the data record available for receiver adaptation and redesign. Our problem is to allocate the available bit rate of the user of interest between source and channel coding and across scalable layers, while minimizing the end-to-end distortion of the received video sequence. The optimization algorithm that we propose utilizes universal rate-distortion characteristic curves that show the contribution of each layer to the total distortion as a function of the source rate of the layer and the residual bit error rate (the error rate after channel coding). These plots can be approximated using appropriate functions to reduce the computational complexity of the solution.}, author = {Kondi, L.P. and Batalama, S.N. and Pados, D.A. and Katsaggelos, A.K.}, booktitle = {Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205)}, doi = {10.1109/ICIP.2001.959215}, isbn = {0-7803-6725-1}, organization = {IEEE}, pages = {994--997}, publisher = {IEEE}, title = {{Joint source-channel coding for scalable video over DS-CDMA multipath fading channels}}, url = {http://ieeexplore.ieee.org/document/959215/}, volume = {1}, year = {2001} }
@inproceedings{segall2000enhancement, abstract = {The enhancement of compressed video is considered. We present a general algorithm for processing the compressed data, with three variants of the algorithm having practical application. We then consider the algorithm within the context of MPEG-2. Assuming complete knowledge of the compressed bitstream, experiments compare the different realizations of the enhancement algorithm. Our comparisons stress improvements in visual quality, measured by models of the human visual system. Quantitative and qualitative results are provided.}, author = {Segall, C.A. and Katsaggelos, A.K.}, booktitle = {Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101)}, doi = {10.1109/ICIP.2000.899791}, organization = {IEEE}, pages = {645--648 vol.2}, publisher = {IEEE}, title = {{Enhancement of compressed video using visual quality measurements}}, url = {http://ieeexplore.ieee.org/document/899791/}, volume = {2}, year = {2000} }
@inproceedings{Jay2000, abstract = {This paper describes a hidden Markov model (HMM) based visual synthesizer designed to assist persons with impairedhearing. This synthesizer builds on results in the area of audio-visual speech recognition. We describe how a correlation HMM can be used to integrate independent acoustic and visual HMMs for speech-to-visual synthesis. Our results show that an HMM correlating model can significantly improve synchronization errors versus techniques which compensate for rate differences through scaling.}, author = {Williams, J.J. and Katsaggelos, A.K. and Randolph, M.A.}, booktitle = {2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100)}, doi = {10.1109/ICASSP.2000.859323}, isbn = {0-7803-6293-4}, issn = {15206149}, pages = {2393--2396}, publisher = {IEEE}, title = {{A hidden Markov model based visual speech synthesizer}}, url = {http://ieeexplore.ieee.org/document/859323/}, volume = {4}, year = {2000} }
@inproceedings{Aggelos2000b, author = {Aggelos, K Katsaggelos}, booktitle = {Proceedings of Applications of Artificial Neural Networks in Image Processing}, title = {{Applications of Artificial Neural Networks in Image Processing V}}, year = {2000} }
@inproceedings{Javier2000b, abstract = {In this work we propose an iterative algorithm for simultaneously estimating the motion field and high resolution frames from a compressed low resolution video sequence. The algorithm exploits the existing correlation between high and low resolution frames and information provided by the encoder, such as coding modes and motion vectors (when available), to obtain a higher resolution frame. The performance of the algorithm is demonstrated experimentally.}, author = {Mateos, J. and Katsaggelos, A.K. and Molina, R.}, booktitle = {Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101)}, doi = {10.1109/ICIP.2000.899793}, organization = {IEEE}, pages = {653--656 vol.2}, publisher = {IEEE}, title = {{Simultaneous motion estimation and resolution enhancement of compressed low resolution video}}, url = {http://ieeexplore.ieee.org/document/899793/}, volume = {2}, year = {2000} }
@inproceedings{Gerry2000a, abstract = {In this paper, we present a rate-distortion (RD) optimized scalable vertex-based shape coding algorithm. Following the base layer, each successive enhancement layer refines a given shape approximation by optimally (within a layer) placing new vertices and perturbing existing vertices. An efficient low entropy distortion adaptive vertex coding strategy is employed to take advantage of information available from coarser layers. Based on the chosen vertex rate and distortion definitions, a resulting enhancement layer topology is solved by executing a Directed Acyclic Graph (DAG) shortest path algorithm. Finally, an iterative VLC optimization scheme is employed to find both the optimized scalable code and the most efficient set of parameter VLC tables.}, author = {Melnikov, Gerry and Katsaggelos, A.K.}, booktitle = {2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100)}, doi = {10.1109/ICASSP.2000.859211}, isbn = {0-7803-6293-4}, issn = {15206149}, pages = {1947--1950}, publisher = {IEEE}, title = {{A rate-distortion optimal scalable vertex based shape coding algorithm}}, url = {http://ieeexplore.ieee.org/document/859211/}, volume = {4}, year = {2000} }
@inproceedings{Javier2000, abstract = {In this work we propose an algorithm for the estimation of high resolution color frames from a low resolution compressed color video sequence. The algorithm exploits the existing correlation between the high and low resolution frames to obtain a high resolution frame reducing the artifacts introduced by the compression process. The performance of the proposed algorithm is demonstrated experimentally.}, author = {Mateos, Javier and Katsaggelos, Aggelos K. and Molina, Rafael}, booktitle = {European Signal Processing Conference}, issn = {22195491}, number = {March}, pages = {1--4}, title = {{High-resolution color image reconstruction from compressed video sequences}}, volume = {2015-March}, year = {2000} }
@inproceedings{Molina2000, author = {Molina, R. and Mateos, J. and Katsaggelos, A.K.}, booktitle = {2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100)}, doi = {10.1109/ICASSP.2000.861892}, isbn = {0-7803-6293-4}, pages = {141--144}, publisher = {IEEE}, title = {{Multichannel image restoration using compound Gauss-Markov random fields}}, url = {http://ieeexplore.ieee.org/document/861892/}, volume = {1}, year = {2000} }
@inproceedings{segall2000pre, abstract = {Standards-based video compression algorithms are rapidly becoming the preferred method for transmitting image sequences. Prominent examples include the MPEG and ITU family of standards. However, it is important to realize that these standards are not bit-exact, in that only the operation of the decoder is defined by the specification. Development of the rate-control mechanism and pre- and post-processing procedures is completely controlled by the system designer, and these components can introduce discernible differences between two standards compliant realizations. In this paper, we survey the fields of pre- and post-processing techniques for video compression. We then discuss our current work on compression enhancement algorithms. These algorithms are applicable to any compression standard but are discussed within the context of MPEG-2.}, author = {Segall, C.A. and Katsaggelos, A.K.}, booktitle = {Conference Record of the Thirty-Fourth Asilomar Conference on Signals, Systems and Computers (Cat. No.00CH37154)}, doi = {10.1109/ACSSC.2000.911215}, isbn = {0-7803-6514-3}, issn = {10586393}, organization = {IEEE}, pages = {1369--1373}, publisher = {IEEE}, title = {{Pre- and post-processing algorithms for compressed video enhancement}}, url = {http://ieeexplore.ieee.org/document/911215/}, volume = {2}, year = {2000} }
@inproceedings{ogrenci2000fpga, address = {New York, NY, USA}, author = {Ogrenci, F. S. and Katsaggelos, A. K. and Sarrafzadeh, M.}, booktitle = {Proceedings of the 2000 ACM/SIGDA eighth international symposium on Field programmable gate arrays}, doi = {10.1145/329166.329217}, isbn = {1581131933}, month = {feb}, organization = {IEEE Computer Society}, pages = {219}, publisher = {ACM}, title = {{FPGA implementation and analysis of image restoration}}, url = {https://dl.acm.org/doi/10.1145/329166.329217}, year = {2000} }
@inproceedings{Rafael2000, abstract = {In this work we extend the use of Compound Gauss Markov Random Fields to the restoration of color images. While most of the work in color image restoration is concentrated on enforcing similarity between the intensity values of the pixels in the image bands, we propose combining information by means of the line process. In order to find the multichannel restoration modified versions of ICM and SA are proposed. The methods are finally tested on real images.}, author = {Mateos, Javier and Katsaggelos, Aggelos K. and Molina, Rafael}, booktitle = {European Signal Processing Conference}, isbn = {22195491 , issue = March}, issn = {22195491}, number = {March}, pages = {1--4}, title = {{Color image restoration using compound Gauss-Markov Random Fields}}, volume = {2015-March}, year = {2000} }
@inproceedings{Mateos2000, author = {Mateos, J. and Katsaggelos, A.K. and Molina, R.}, booktitle = {2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100)}, doi = {10.1109/ICASSP.2000.859204}, isbn = {0-7803-6293-4}, pages = {1919--1922}, publisher = {IEEE}, title = {{Resolution enhancement of compressed low resolution video}}, url = {http://ieeexplore.ieee.org/document/859204/}, volume = {4}, year = {2000} }
@inproceedings{Lisimachos2000, author = {Kondi, Lisimachos P. and Ishtiaq, Faisal and Katsaggelos, Aggelos K.}, booktitle = {Image and Video Communications and Processing 2000}, doi = {10.1117/12.382965}, editor = {Vasudev, Bhaskaran and Hsing, T. Russell and Tescher, Andrew G. and Stevenson, Robert L.}, month = {apr}, pages = {324--335}, title = {{Joint source-channel coding for scalable video}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=921937}, volume = {3974}, year = {2000} }
@inproceedings{Gerry2000b, abstract = {This paper presents an efficient recursive algorithm for generating operationally optimal intra mode scalable layer decompositions of object contours. The problem is posed in terms of minimizing the shape distortion at full reconstruction subject to the total (for all scalable layers) bit budget constraint. Based on the chosen vertex-based representation, we solve the problem of determining the number and locations of approximating vertices for all scalable layers jointly and optimally. The number of scalable layers is not constrained, but, rather, is a by-product of the proposed optimization. The algorithm employs two different coding strategies: one for the base layer and one for the enhancement layers. By carefully defining scalable layer recursion and base layer segment costs the problem is solved by executing a Directed Acyclic Graph (DAG) shortest path algorithm.}, author = {Melnikov, G. and Katsaggelos, A.K.}, booktitle = {Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101)}, doi = {10.1109/ICIP.2000.899864}, pages = {915--918 vol.2}, publisher = {IEEE}, title = {{Shape approximation through recursive scalable layer generation}}, url = {http://ieeexplore.ieee.org/document/899864/}, volume = {2}, year = {2000} }
@inproceedings{Faisal1999, abstract = {In this paper a novel methodology for temporal scalability within the H.263 video coding standard is presented. Temporal scalability is defined as the transmission of previously dropped frames in the form of a scalable enhancement layer to increase the overall encoded frame rate. The proposed methodology extends the base layer rate control to the enhancement layer and incorporates an adaptive technique for enhancement layer frame selection. Three criteria important in the selection of enhancement frames are identified, allowing us to adaptively choose frames such that the overall temporal resolution of the encoded video sequence is enhanced. Experimental results are provided and compared to a non-adaptive technique where enhancement frames are selected solely on the decay of the enhancement layer buffer.}, author = {Ishtiaq, Faisal and Katsaggelos, A.K.}, booktitle = {Proceedings 1999 International Conference on Image Processing (Cat. 99CH36348)}, doi = {10.1109/ICIP.1999.819595}, isbn = {0-7803-5467-2}, pages = {280--284}, publisher = {IEEE}, title = {{A rate control method for H.263 temporal scalability}}, url = {http://ieeexplore.ieee.org/document/819595/}, volume = {4}, year = {1999} }
@inproceedings{meenikov1999jointly, abstract = {This paper investigates how the between frame correlation of shape information can be exploited within the framework of an operationally rate-distortion (ORD) optimized coder. Contours are approximated either by connected second-order spline segments, each defined by three consecutive control points, or by segments of the motion-compensated reference contours. Consecutive control points are then encoded predictively using angle and run temporal contexts or by tracking the reference contour. We employ a novel criterion for selecting global object motion vectors, which further improves efficiency. The problem is formulated as Lagrangian minimization and solved using Dynamic Programming (DP). Furthermore, we employ an iterative technique to remove dependency on a particular VLC and jointly arrive at the ORD globally optimal solution and an optimized conditional parameter distribution.}, author = {Meenikov, G. and Katsaggelos, A.K. and Schuster, G.M.}, booktitle = {Proceedings 1999 International Conference on Image Processing (Cat. 99CH36348)}, doi = {10.1109/ICIP.1999.823008}, isbn = {0-7803-5467-2}, organization = {IEEE}, pages = {806--810 vol.2}, publisher = {IEEE}, title = {{Jointly optimal inter-mode shape coding and VLC selection}}, url = {https://ieeexplore.ieee.org/document/823008/}, volume = {2}, year = {1999} }
@inproceedings{Rafael1999, abstract = {In this paper the subband decomposition of a single channel image restoration problem is examined. The decomposition is carried out in the image model (prior model) in order to take into account the frequency activity of each band of the original image. The hyperparameters associated with each band together with the original image are rigorously estimated within the Bayesian framework. Finally, the proposed method is tested and compared with other methods on real images.}, author = {Molina, Rafael and Katsaggelos, A.K. and Abad, Javier}, booktitle = {1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258)}, doi = {10.1109/ICASSP.1999.757536}, isbn = {0-7803-5041-3}, issn = {07367791}, pages = {3257--3260 vol.6}, publisher = {IEEE}, title = {{Bayesian image restoration using a wavelet-based subband decomposition}}, url = {http://ieeexplore.ieee.org/document/757536/}, volume = {6}, year = {1999} }
@inproceedings{Ranveig1999, abstract = {Signal compression is an important problem encountered in many applications. Various techniques have been proposed over the years for addressing the problem. In this paper we present a time domain algorithm based on the coding of line segments which are used to approximate the signal. These segments are fit in a way that is optimal in the rate distortion sense. Although the approach is applicable to any type of signal, we focus, in this paper, on the compression of ElectroCardioGram (ECG) signals. ECG signal compression has traditionally been tackled by heuristic approaches. However, it has been demonstrated that exact optimization algorithms outperform these heuristic approaches by a wide margin with respect to reconstruction error. By formulating the compression problem as a graph theory problem, known optimization theory can be applied in order to yield optimal compression. In this paper we present an algorithm that will guarantee the smallest possible distortion among all methods applying linear interpolation given an upper bound on the number of bits. Compared to many other compression methods, we report superior performance for this method.}, author = {Nygaard, Ranveig and Melnikov, Gerry and Katsaggelos, A.K.}, booktitle = {Proceedings 1999 International Conference on Image Processing (Cat. 99CH36348)}, doi = {10.1109/ICIP.1999.822915}, isbn = {0-7803-5467-2}, pages = {348--351 vol.2}, publisher = {IEEE}, title = {{Rate distortion optimal ECG signal compression}}, url = {https://ieeexplore.ieee.org/document/822915/}, volume = {2}, year = {1999} }
@inproceedings{Antonio1999, abstract = {Although many statistical methods have been proposed for the restoration of tomographic images, their use in medical environments has been limited due to two important factors. These factors are the need for greater computational time than deterministic methods and the selection of the hyperparameters in the image models. Consequently, deterministic methods, like the classical filtered back-projection (FBP) and algebraic reconstruction (AR), are commonly used. In this work, we propose a method to estimate, from observed image data in emission tomography, the hyperparameters in a Generalized Gaussian Markov Random Field (GGMRF). We use the hierarchical Bayesian approach and evidence analysis to reconstruct the image and estimate the unknown hyperparameters. The method is tested on synthetic images.}, author = {Lopez, A. and Molina, R. and Katsaggelos, A.K.}, booktitle = {Proceedings 1999 International Conference on Image Processing (Cat. 99CH36348)}, doi = {10.1109/ICIP.1999.822981}, isbn = {0-7803-5467-2}, pages = {677--680 vol.2}, publisher = {IEEE}, title = {{Hyperparameter estimation for emission computed tomography data}}, url = {https://ieeexplore.ieee.org/document/822981/}, volume = {2}, year = {1999} }
@inproceedings{Chun-Jen1999b, author = {Chun-Jen, Tsai and Nikolas, P Galatsanos and Aggelos, K Katsaggelos}, booktitle = {1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No. 99CH36258)}, pages = {3393--3396}, title = {{Optical flow estimation from noisy data using differential techniques}}, volume = {6}, year = {1999} }
@inproceedings{Chun-Jen1999d, abstract = {The problem of the enhancement of a low bit-rate compressed video sequence using the information provided by the encoder is investigated in this paper. The proposed algorithm is spatio-temporally adaptive and enforces different degrees of between-block, within-block, and temporal smoothness of the decompressed frames based on macroblock types. The algorithm uses the projections onto the sets that capture the information conveyed by the transmitted data to constrain the solution space. A partially automatic regularization parameter estimation algorithm is also proposed in this paper. An analysis of PSNR gain per macroblock type is presented to cast insight into the compressed video enhancement problem. The experimental results demonstrate the effectiveness of the proposed approach.}, author = {{Chun-Jen Tsai} and Karunaraine, P. and Galatsanos, N.P. and Katsaggelos, A.K.}, booktitle = {Proceedings 1999 International Conference on Image Processing (Cat. 99CH36348)}, doi = {10.1109/ICIP.1999.817155}, isbn = {0-7803-5467-2}, pages = {454--458}, publisher = {IEEE}, title = {{A compressed video enhancement algorithm}}, url = {http://ieeexplore.ieee.org/document/817155/}, volume = {3}, year = {1999} }
@inproceedings{luna1999maximizing, author = {Luna, C.E. and Katsaggelos, A.K.}, booktitle = {2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221)}, doi = {10.1109/ICASSP.2001.941207}, isbn = {0-7803-7041-4}, number = {1}, organization = {IEEE}, pages = {1465--1468}, publisher = {IEEE}, title = {{Maximizing user utility in video streaming applications}}, url = {http://ieeexplore.ieee.org/document/941207/}, volume = {3}, year = {1999} }
@inproceedings{Lisimachos1999, author = {Kondi, L.P. and Katsaggelos, A.K.}, booktitle = {Proceedings 1999 International Conference on Image Processing (Cat. 99CH36348)}, doi = {10.1109/ICIP.1999.821613}, isbn = {0-7803-5467-2}, pages = {276--280}, publisher = {IEEE}, title = {{An optimal single pass SNR scalable video coder}}, url = {http://ieeexplore.ieee.org/document/821613/}, volume = {1}, year = {1999} }
@inproceedings{Gerry1999, abstract = {This paper investigates the problem of optimal lossy encoding of object contours in the Inter mode. Contours are approximated by connected second-order spline segments, each defined by three consecutive control points. Taking into account correlations in the temporal direction, control points are chosen optimally in the rate-distortion (RD) sense. Applying motion to contours in the reference frame followed by the temporal context extraction, we predict the next control point location, given the previously encoded one. Based on the chosen differential encoding scheme and an additive MPEG4-based distortion metric, the problem is formulated as Lagrangian minimization. We utilize an iterative procedure to jointly find the optimal solution and the associated DPCM parameter probability mass functions.}, author = {Melnikov, Gerry and Schuster, G.M. and Katsaggelos, A.K.}, booktitle = {1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258)}, doi = {10.1109/ICASSP.1999.757503}, isbn = {0-7803-5041-3}, issn = {07367791}, pages = {3125--3128 vol.6}, publisher = {IEEE}, title = {{Inter mode vertex-based optimal shape coding}}, url = {http://ieeexplore.ieee.org/document/757503/}, volume = {6}, year = {1999} }
@inproceedings{Nasser, author = {Nasser, M Nasrabadi and Aggelos, K Katsaggelos}, booktitle = {SPIE proceedings series}, title = {{Applications of artificial neural networks in image processing IV}}, year = {1999} }
@inproceedings{Gerry1999a, author = {Melnikov, G. and Katsaggelos, A.K. and Schuster, G.M.}, booktitle = {1999 IEEE Third Workshop on Multimedia Signal Processing (Cat. No.99TH8451)}, doi = {10.1109/MMSP.1999.793853}, isbn = {0-7803-5610-1}, pages = {303--308}, publisher = {IEEE}, title = {{Context based optimal shape coding}}, url = {http://ieeexplore.ieee.org/document/793853/}, year = {1999} }
@inproceedings{Gerry1998c, abstract = {In this paper a hybrid fractal and discrete cosine transform (DCT) coder is developed. Drawing on the ability of DCT to remove inter-pixel redundancies and on the ability of fractal transforms to capitalize on long-range correlations in the image, the hybrid coder performs an optimal, in the rate-distortion sense, bit allocation among coding parameters. An orthogonal basis framework is used within which an image segmentation and a hybrid block-based transform are selected jointly. A Lagrangian multiplier approach is used to optimize the hybrid parameters and the segmentation. Differential encoding of the DC coefficient is employed, with the scanning path based on a 3rd-order Hilbert curve. Simulation results show a significant improvement in quality with respect to the JPEG standard. {\textcopyright} 1998 IEEE.}, author = {Melnikov, Gerry and Katsaggelos, A.K.}, booktitle = {Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181)}, doi = {10.1109/ICASSP.1998.678048}, isbn = {0-7803-4428-6}, issn = {15206149}, pages = {2573--2576}, publisher = {IEEE}, title = {{A non uniform segmentation optimal hybrid fractal/DCT image compression algorithm}}, url = {http://ieeexplore.ieee.org/document/678048/}, volume = {5}, year = {1998} }
@inproceedings{Kaaren1998a, author = {May, K. and Stathaki, T. and Katsaggelos, A.K.}, booktitle = {Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181)}, doi = {10.1109/ICASSP.1998.678139}, isbn = {0-7803-4428-6}, pages = {2929--2932}, publisher = {IEEE}, title = {{Blind image restoration using local bound constraints}}, url = {http://ieeexplore.ieee.org/document/678139/}, volume = {5}, year = {1998} }
@inproceedings{Damon1998, abstract = {The complex image degradations observed in (video) image sequences are often due to partial-response mechanisms caused by the physical limitations of practical cameras. The restoration of these distortions require more sophisticated image models that consider the underlying image acquisition process. In this work, a broad class of spatially varying distortions is defined. The observed image is modeled as the physically meaningful superposition of K partially degraded images. In areas where the degradation is due to the partial-response of the sensor to multiple object (regions), the distortion is said to be clustered or sporadic. The sporadic distortions under consideration here are spatially varying, object dependent and difficult to estimate from the observed data. A regularized iterative restoration of sporadically degraded images resulting in K restored images is proposed. The algorithm demonstrates a promising (object based) image restoration approach for video editing applications.}, author = {Tull, D.L. and Katsaggelos, A.K.}, booktitle = {Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269)}, doi = {10.1109/ICIP.1998.727362}, isbn = {0-8186-8821-1}, pages = {732--736}, publisher = {IEEE Comput. Soc}, title = {{Regularized restoration of partial-response distortions in sporadically degraded images}}, url = {http://ieeexplore.ieee.org/document/727362/}, volume = {3}, year = {1998} }
@inproceedings{Javier1998, abstract = {In this paper we use the information in the chrominance bands to reconstruct color block transformed compressed images. For the luminance and the two chrominance channels, we define a reconstruction problem and show how to estimate the unknown hyper-parameters and reconstruct each band automatically. The method is tested on real images.}, author = {Mateos, J. and Ilia, C. and Jimenez, B. and Molina, R. and Katsaggelos, A.K.}, booktitle = {Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269)}, doi = {10.1109/ICIP.1998.723511}, isbn = {0-8186-8821-1}, pages = {401--405}, publisher = {IEEE Comput. Soc}, title = {{Reduction of blocking artifacts in block transformed compressed color images}}, url = {http://ieeexplore.ieee.org/document/723511/}, volume = {1}, year = {1998} }
@inproceedings{Andre1998, author = {Redert, Andre and Tsai, Chun-Jen and Hendriks, Emile A. and Katsaggelos, Aggelos K.}, booktitle = {Visual Communications and Image Processing '98}, doi = {10.1117/12.298391}, editor = {Rajala, Sarah A. and Rabbani, Majid}, month = {jan}, pages = {798--808}, title = {{Disparity estimation with modeling of occlusion and object orientation}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=937924}, volume = {3309}, year = {1998} }
@inproceedings{katsaggelos1998error, abstract = {In this paper we review error resilience and concealment techniques which have been developed both within and outside the various videoconferencing standards. We consider the H.324 videoconferencing standard with its accompanying lower level H.263 and H.223 video and multiplexing standards, MPEG 2. and MPEG-4. We then describe an error resilience algorithm commonly used with variable length codewords, and finally review error concealment techniques that have appeared in the literature.}, author = {Katsaggelos, A. K. and Ishtiaq, F. and Kondi, L. P. and Hong, M. C. and Banham, M. and Brailean, J.}, booktitle = {European Signal Processing Conference}, issn = {22195491}, organization = {IEEE}, pages = {1--8}, title = {{Error resilience & concealment in video coding}}, volume = {1998-Janua}, year = {1998} }
@inproceedings{Kaaren1998, abstract = {In this paper, the problem of how to better estimate spatially adaptive intensity bounds for image restoration is addressed. When the intensity bounds are estimated from a degraded image, blurring leads to underestimation of the bounds in the edge and texture regions. Therefore, an iterative implementation of the restoration algorithm has been proposed in which the intensity bounds are re-estimated from the current image estimate. However, direct update of the bounds leads to over-smoothing in regions where the bounds are active. Furthermore, the resulting algorithm exhibits slow convergence. In this paper, alternative methods of initially estimating and updating the bounds are proposed, and the results for the fixed- and updated-bound implementations are compared. A method for estimation of the bound tightness parameter is also proposed.}, author = {May, Kaaren and Stathaki, Tania and Constantinides, A.G. and Katsaggelos, A.K.}, booktitle = {Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269)}, doi = {10.1109/ICIP.1998.723687}, isbn = {0-8186-8821-1}, pages = {833--837}, publisher = {IEEE Comput. Soc}, title = {{Iterative determination of local bound constraints in iterative image restoration}}, url = {http://ieeexplore.ieee.org/document/723687/}, volume = {2}, year = {1998} }
@inproceedings{hong1998regularized, abstract = {In this paper, we develop a deterministic regularized mixed norm multichannel image restoration algorithm. A functional which combines the least mean squares (LMS), the least mean fourth (LMF), and a smoothing functional using both within- and between-channel deterministic information is proposed. One parameter is defined to control the relative contribution between the LMS and the LMF norms, and a second one (regularization parameter) is defined to control the degree of smoothness of the solution. They are both updated at each iteration step. The novelty of the proposed algorithm is that no knowledge about the noise distribution for each channel is required, and the parameters are adjusted based on the partially restored image.}, author = {Hong, M.-C. and Stathaki, T. and Katsaggelos, A.K.}, booktitle = {Ninth IEEE Signal Processing Workshop on Statistical Signal and Array Processing (Cat. No.98TH8381)}, doi = {10.1109/SSAP.1998.739374}, isbn = {0-7803-5010-3}, organization = {IEEE}, pages = {220--223}, publisher = {IEEE}, title = {{A regularized mixed norm multichannel image restoration approach}}, url = {http://ieeexplore.ieee.org/document/739374/}, volume = {14}, year = {1998} }
@inproceedings{Aggelos1998h, author = {Katsaggelos, A.K. and Kondi, L.P. and Meier, F.W. and Ostermann, J{\"{o}}rn and Schuster, G.M.}, booktitle = {Proceedings of the IEEE}, doi = {10.1109/5.687833}, issn = {00189219}, month = {jun}, number = {6}, pages = {1126--1154}, title = {{MPEG-4 and rate-distortion-based shape-coding techniques}}, url = {http://ieeexplore.ieee.org/document/687833/}, volume = {86}, year = {1998} }
@inproceedings{Marshall1998, author = {Robers, Marshall A. and Kondi, Lisimachos P. and Katsaggelos, Aggelos K.}, booktitle = {Visual Communications and Image Processing '98}, doi = {10.1117/12.298330}, editor = {Rajala, Sarah A. and Rabbani, Majid}, month = {jan}, pages = {201--212}, title = {{SNR scalable video coder using progressive transmission of DCT coefficients}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=937721}, volume = {3309}, year = {1998} }
@inproceedings{Lisimachos1998, abstract = {In this paper, we compare two SNR scalable video codecs. The first codec (CODEC1) is a three-layer single-pass quantization algorithm based on H.263 and extends the work presented in [1, 2]. The second codec (CODEC2) implements three layer SNR scalability as described in Annex O of the H.263 standard by requantizing the DCT coefficients of the encoding error using finer quantizers than those used in the previous layer. By testing the two algorithms at various base and enhancement layer rates on both high and low motion sequences, the advantages and disadvantages of each codec are discussed and suitable applications are suggested for each one.}, author = {Kondi, L.P. and Ishtiaq, Faisal and Katsaggelos, A.K.}, booktitle = {Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269)}, doi = {10.1109/ICIP.1998.999079}, isbn = {0-8186-8821-1}, pages = {934--938}, publisher = {IEEE Comput. Soc}, title = {{On video SNR scalability}}, url = {http://ieeexplore.ieee.org/document/999079/}, volume = {3}, year = {1998} }
@inproceedings{segall1998sampling, author = {Segall, C Andrew and Acton, Scott Thomas and Katsaggelos, Aggelos K}, booktitle = {Visual Communications and Image Processing'99}, organization = {SPIE}, pages = {160--171}, title = {{Sampling conditions for anisotropic diffusion}}, volume = {3653}, year = {1998} }
@inproceedings{tsai1998total, author = {Tsai, Chun-Jen and Galatsanos, N.P. Nikolas P and Katsaggelos, Aggelos K A.K. and {Chun-Jen Tsai} and Galatsanos, N.P. Nikolas P and Katsaggelos, Aggelos K A.K.}, booktitle = {Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No. 98CB36269)}, doi = {10.1109/ICIP.1998.723549}, isbn = {0-8186-8821-1}, organization = {IEEE}, pages = {622--626}, publisher = {IEEE Comput. Soc}, title = {{Total least squares estimation of stereo optical flow}}, url = {http://ieeexplore.ieee.org/document/723549/}, volume = {2}, year = {1998} }
@inproceedings{Mesarovic1998, author = {Mesarovic, V. and Galatsanos, N. and Molina, R. and Katsaggelos, A.}, booktitle = {Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181)}, doi = {10.1109/ICASSP.1998.678133}, isbn = {0-7803-4428-6}, pages = {2905--2908}, publisher = {IEEE}, title = {{Hierarchical Bayesian image restoration from partially-known blurs}}, url = {http://ieeexplore.ieee.org/document/678133/}, volume = {5}, year = {1998} }
@inproceedings{Nikolas1998, author = {Galatsanos, Nikolas P. and Mesarovic, Vladimir Z. and Molina, Rafael and Katsaggelos, Aggelos K.}, booktitle = {Bayesian Inference for Inverse Problems}, doi = {10.1117/12.323813}, editor = {Mohammad-Djafari, Ali}, month = {sep}, pages = {337--348}, title = {{Hyperparameter estimation using hyperpriors for hierarchical Bayesian image restoration from partially known blurs}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=958905}, volume = {3459}, year = {1998} }
@inproceedings{Gerry1998, abstract = {In this paper an optimal boundary encoding algorithm in the rate-distortion sense is proposed. Second-order B-spline curves are used to model object boundaries. An additive area distortion measure between the original boundary and its approximation is employed in the optimization process. The problem is formulated in a Directed Acyclic Graph (DAG) paradigm, and the shortest path solution is used to optimally select control point locations of the B-spline curve approximation based on the desired rate-distortion tradeoff.}, author = {Melnikov, Gerry and Karunaratne, P.V. and Schuster, G.M. and Katsaggelos, A.K.}, booktitle = {ISCAS '98. Proceedings of the 1998 IEEE International Symposium on Circuits and Systems (Cat. No.98CH36187)}, doi = {10.1109/ISCAS.1998.694468}, isbn = {0-7803-4455-3}, issn = {02714310}, pages = {289--292}, publisher = {IEEE}, title = {{Rate-distortion optimal boundary encoding using an area distortion measure}}, url = {http://ieeexplore.ieee.org/document/694468/}, volume = {5}, year = {1998} }
@inproceedings{Gerry1998b, abstract = {This paper describes efficient and optimal encoding and representation of object contours. Contours are approximated by connected second-order spline segments, each defined by three consecutive control points. The placement of the control points is done optimally in the rate-distortion (RD) sense and jointly with their entropy encoding. We utilize a differential scheme for the rate and an additive area-based metric for the distortion to formulate the problem as Lagrangian minimization. We investigate the sensitivity of the resulting operational RD curve on the variable length codes used and propose an iterative procedure arriving at the entropy representation of the original boundary for any given rate-distortion tradeoff.}, author = {Melnikov, Gerry and Schuster, G.M. and Katsaggelos, A.K.}, booktitle = {Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269)}, doi = {10.1109/ICIP.1998.723468}, isbn = {0-8186-8821-1}, pages = {256--260}, publisher = {IEEE Comput. Soc}, title = {{Simultaneous optimal boundary encoding and variable-length code selection}}, url = {http://ieeexplore.ieee.org/document/723468/}, volume = {1}, year = {1998} }
@inproceedings{Gerry1998a, abstract = {This paper investigates ways to explore the between frame correlation of shape information within the framework of an operationally rate-distortion (ORD) optimal coder. Contours are approximated both by connected second-order spline segments, each defined by three consecutive control points, and by segments of the motion-compensated reference contours. Consecutive control points are then encoded predictively using angle and run temporal contexts. We utilize a novel criterion for selecting global object motion vectors, which further improves efficiency. Formulating this problem as Lagrangian minimization, we employ an iterative technique to remove dependency on a particular VLC and jointly arrive at the ORD optimal solution and its underlying conditional parameter distribution.}, author = {Melnikov, Gerry and Schuster, G.M. and Katsaggelos, A.K.}, booktitle = {Conference Record of Thirty-Second Asilomar Conference on Signals, Systems and Computers (Cat. No.98CH36284)}, doi = {10.1109/ACSSC.1998.751596}, isbn = {0-7803-5148-7}, issn = {10586393}, pages = {1601--1605}, publisher = {IEEE}, title = {{Exploiting temporal correlation in shape coding}}, url = {http://ieeexplore.ieee.org/document/751596/}, volume = {2}, year = {1998} }
@inproceedings{Nasser1998a, author = {Nasser, M Nasrabadi and Aggelos, K Katsaggelos}, booktitle = {Proceedings of SPIE-The International Society for Optical Engineering}, title = {{Applications of artificial neural networks in image processing III}}, volume = {3307}, year = {1998} }
@inproceedings{Min-Cheol1998, author = {Hong, Min-Cheol and Stathaki, Tania and Katsaggelos, Aggelos K}, booktitle = {Visual Communications and Image Processing'98}, doi = {10.1117/12.298374}, editor = {Rajala, Sarah A. and Rabbani, Majid}, month = {jan}, organization = {SPIE}, pages = {603--614}, title = {{Iterative regularized mixed-norm image restoration algorithm}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=937854}, volume = {3309}, year = {1998} }
@inproceedings{Kaaren1998b, abstract = {A new method of incorporating local image constraints into blind image restoration is proposed. The local mean and variance of the degraded image are used to obtain .in initial estimate of the pixel intensity bounds. As the restoration proceeds, the bounds are updated from the current image estimate. I lie iterative-bound algorithm shows an improvement over the use of fixed bounds taken from the blurred image, in which case underestimation of the variance occurs at edges and textures. Simulations are presented for both the fixed-And iterative-bound implementations.}, author = {May, Kaaren and Stathaki, Tania and Katsaggelos, Aggelos}, booktitle = {European Signal Processing Conference}, issn = {22195491}, pages = {1--4}, title = {{Iterative blind image restoration using local constraints}}, volume = {1998-Janua}, year = {1998} }
@inproceedings{Min-Cheol1997a, abstract = {In this paper, we propose an iterative mixed norm image restoration algorithm. A functional which combines the least mean squares (LMS) and the least mean fourth (LMF) functionals is proposed. A function of the kurtosis is used to determine the relative importance between the LMS and the LMF functionals. An iterative algorithm is utilized for obtaining a solution and its convergence is analyzed. Experimental results demonstrate the capability of the proposed approach.}, author = {{Min-Cheol Hong} and Stathaki, Tania and Katsaggelos, Aggelos K A.K. and Hong, Min-Cheol and Stathaki, Tania and Katsaggelos, Aggelos K A.K.}, booktitle = {Proceedings of International Conference on Image Processing}, doi = {10.1109/ICIP.1997.647787}, isbn = {0-8186-8183-7}, organization = {IEEE}, pages = {385--388}, publisher = {IEEE Comput. Soc}, title = {{A mixed norm image restoration}}, url = {http://ieeexplore.ieee.org/document/647787/}, volume = {1}, year = {1997} }
@inproceedings{LisimachosPaul1997, abstract = {In this paper we determine the number of bits to be used for the encoding of the anchor frame in low bit rate video coding in order to improve the quality of the next and subsequent frames to be encoded. We use a progressive method for the transmission of the anchor frame. We develop two methods for determining the optimal number of bits to be allocated to the first frame in on line video communication applications.}, author = {Kondi and Katsaggelos}, booktitle = {International Conference on Consumer Electronics}, doi = {10.1109/ICCE.1997.625850}, isbn = {0-7803-3734-4}, issn = {0747668X}, pages = {18--19}, publisher = {IEEE}, title = {{On The Encoding Of The Anchor Frame In Video Coding}}, url = {http://ieeexplore.ieee.org/document/625850/}, volume = {43}, year = {1997} }
@inproceedings{Javier1997, abstract = {High compression ratios for both still images and sequences of images are usually achieved by quantizing the block discrete cosine transform (BDCT) coefficients of the intensity or displaced frame different values. This block based processing and quantization yields images that exhibit annoying blocking artifacts. In this paper, we propose a method based on the hierarchical Bayesian approach for the reconstruction of BDCT compressed images and the estimation of the related parameters both at the coder and decoder. We examine how to combine the parameters estimated at the coder and decoder and test the method on real images.}, author = {Mateos, J. and Molina, Rafael and Katsaggelos, A.K.}, booktitle = {Proceedings of 13th International Conference on Digital Signal Processing}, doi = {10.1109/ICDSP.1997.628018}, isbn = {0-7803-4137-6}, pages = {209--212}, publisher = {IEEE}, title = {{Estimating and transmitting regularization parameters for reducing blocking artifacts}}, url = {http://ieeexplore.ieee.org/document/628018/}, volume = {1}, year = {1997} }
@inproceedings{Guido1997h, abstract = {We propose a fast and efficient algorithm which finds the optimal quad-tree (QT) decomposition with leaf dependencies in the rate distortion sense. The underlying problem is the encoding of an image by a variable block size scheme, where the block size is encoded using a QT, each block is encoded by one of the admissible quantizers and the quantizers are transmitted using a first order differential pulse code modulation (DPCM) scheme along the scanning path. First we define an optimal scanning path for a QT such that successive blocks are always neighboring blocks. Then we propose a procedure which infers such an optimal path from the QTdecomposition and introduce a special optimal path which is based on a Hilbert curve. Then we consider the case where the image is losslessly encoded using a QT structure and propose a dynamic programming (DP) based multi-level approach to find the optimal QT-decomposition and the optimal quantizer selection. We then apply the Lagrangian multiplier method to solve the lossy case, and show that the unconstrained problem of the Lagrangian multiplier method can be solved using the algorithm introduced for the lossless case. Finally we present a mean value QT-decomposition example, where the mean values are DPCM encoded.}, author = {Schuster, Guido M. and Katsaggelos, Aggelos K.}, booktitle = {Visual Communications and Image Processing '97}, doi = {10.1117/12.263281}, editor = {Biemond, Jan and {Delp III}, Edward J.}, month = {jan}, pages = {59--70}, title = {{Optimal decomposition for quad-trees with leaf dependencies}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=920389}, volume = {3024}, year = {1997} }
@inproceedings{Nassera, author = {Nasser, M Nasrabadi and Aggelos, K Katsaggelos}, booktitle = {SPIE proceedings series}, title = {{Applications of artificial neural networks in image processing II}}, year = {1997} }
@inproceedings{molina1997bayesian, author = {Molina, R and Katsaggelos, A K and Mateos, J}, booktitle = {Data Analysis in Astronomy V,(Di Ges u et al. Editors)}, pages = {289--296}, title = {{Bayesian Deconvolution Methods in Astronomy}}, volume = {1}, year = {1997} }
@inproceedings{Jay1998, abstract = {In the future, multimedia technology will be able to provide video frame rates equal to or better than 30 frames-per-second (FPS). Until that time the hearing impaired community will be using band limited communication systems over un-shielded twisted pair copper wiring. As a result, multimedia communication systems will use a coder/decoder (CODEC) to compress the video and audio signals for transmission. For these systems to be usable by the hearing impaired community, the algorithms within the CODEC have to be designed to account for the perceptual boundaries of the hearing impaired. We investigate the perceptual boundaries of speech reading and multimedia technology, which are the constraints that effect speech reading performance. We analyze and draw conclusions on the relationship between viseme groupings, accuracy of viseme recognition, and presentation rate. These results are critical in the design of multimedia systems for the hearing impaired.}, author = {Williams, J.J. and Rutledge, J.C. and Garstecki, D.C. and Katsaggelos, A.K. and Jay, J Williams and Janet, C Rutledge and Dean, C Garstecki and Aggelos, K Katsaggelos}, booktitle = {Proceedings of First Signal Processing Society Workshop on Multimedia Signal Processing}, doi = {10.1109/MMSP.1997.602606}, isbn = {0-7803-3780-8}, pages = {13--18}, publisher = {IEEE}, title = {{Frame rate and viseme analysis for multimedia applications}}, url = {http://ieeexplore.ieee.org/document/602606/}, volume = {20}, year = {1997} }
@inproceedings{molina1997bayesian, abstract = {This paper deals with the simultaneous identification of the blur and the restoration of a noisy and blurred image. We propose the use of Dirichlet distributions to model our prior knowledge about the blurring function together with smoothness constraints on the restored image to solve the blind deconvolution problem. We show that the use of Dirichlet distributions offers a lot of flexibility in incorporating vague or very precise knowledge about the blurring process into the blind deconvolution process. The proposed MAP estimator offers additional flexibility in modeling the original image. Experimental results demonstrate the performance of the proposed algorithm.}, author = {Molina, Rafael and Katsaggelos, A.K. and Abad, Javier and Mateos, Javier}, booktitle = {1997 IEEE International Conference on Acoustics, Speech, and Signal Processing}, doi = {10.1109/ICASSP.1997.595373}, isbn = {0-8186-7919-0}, issn = {07367791}, organization = {IEEE}, pages = {2809--2812}, publisher = {IEEE Comput. Soc. Press}, title = {{A Bayesian approach to blind deconvolution based on Dirichlet distributions}}, url = {http://ieeexplore.ieee.org/document/595373/}, volume = {4}, year = {1997} }
@inproceedings{hong1997iterative, author = {{Min-Cheol Hong} and Stathaki, Tania and Katsaggelos, Aggelos K A.K. and Hong, Min-Cheol and Stathaki, Tania and Katsaggelos, Aggelos K A.K.}, booktitle = {Proceedings of the IEEE Signal Processing Workshop on Higher-Order Statistics}, doi = {10.1109/HOST.1997.613503}, isbn = {0-8186-8005-9}, organization = {IEEE}, pages = {137--141}, publisher = {IEEE Comput. Soc}, title = {{An iterative mixed norm image restoration algorithm}}, url = {http://ieeexplore.ieee.org/document/613503/}, year = {1997} }
@inproceedings{Marshall1997, abstract = {Vector quantization (VQ) provides a fast, low-power image compression technique for video communication products. However, since VQ techniques operate on each block of the image separately, they have been criticized for producing visually-disturbing blocking artifacts. In this paper, we present a VQ technique which uses hexagonally-shaped vectors to greatly reduce blocking artifacts.}, author = {Robers and Katsaggelos}, booktitle = {International Conference on Consumer Electronics}, doi = {10.1109/ICCE.1997.625905}, isbn = {0-7803-3734-4}, issn = {0747668X}, pages = {144--145}, publisher = {IEEE}, title = {{Reducing Blocking Artifacts Within Vector Quantization Algorithms}}, url = {http://ieeexplore.ieee.org/document/625905/}, volume = {43}, year = {1997} }
@inproceedings{hong1997regularized, abstract = {This paper introduces an iterative regularized approach to obtain a high resolution video sequence. A multiple input smoothing convex functional is defined and used to obtain a globally optimal high resolution video sequence. A mathematical model of multiple inputs is described by using the point spread function between the original and bilinearly interpolated images in the spatial domain, and motion estimation between frames in the temporal domain. Properties of the proposed smoothing convex functional are analyzed. An iterative algorithm is utilized for obtaining a solution. The regularization parameter is updated at each iteration step from the partially restored video sequence. Experimental results demonstrate the capability of the proposed approach.}, author = {Hong, Min-Cheol and Kang, Moon Gi and Katsaggelos, Aggelos K.}, booktitle = {Visual Communications and Image Processing '97}, doi = {10.1117/12.263211}, editor = {Biemond, Jan and {Delp III}, Edward J.}, issn = {0277786X}, month = {jan}, organization = {SPIE}, pages = {1306--1316}, title = {{Regularized multichannel restoration approach for globally optimal high-resolution video sequence}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=920678}, volume = {3024}, year = {1997} }
@inproceedings{tsai1997model, abstract = {In this paper a model-based multi-view image generation system for video conferencing is presented. The system assumes that a 3-D model of the person in front of the camera is available. It extracts texture from a speaking person sequence images and maps it to the static 3-D model during the video conference session. Since only the incrementally updated texture information is transmitted during the whole session, the bandwidth requirement is very small. Based on the experimental results one can conclude that the proposed system is very promising for practical applications.}, author = {Tsai, Chun-Jen and Eisert, Peter and Girod, Bernd and Katsaggelos, Aggelos K A.K. and {Chun-Jen Tsai} and Eisert, Peter and Girod, Bernd and Katsaggelos, Aggelos K A.K.}, booktitle = {Proceedings of International Conference on Image Processing}, doi = {10.1109/ICIP.1997.647802}, isbn = {0-8186-8183-7}, organization = {IEEE}, pages = {444--447}, publisher = {IEEE Comput. Soc}, title = {{Model-based synthetic view generation from a monocular video sequence}}, url = {http://ieeexplore.ieee.org/document/647802/}, volume = {1}, year = {1997} }
@inproceedings{Fabian1997a, author = {Meier, F.W. and Schuster, G.M. and Katsaggelos, A.K.}, booktitle = {Proceedings of International Conference on Image Processing}, doi = {10.1109/ICIP.1997.638660}, isbn = {0-8186-8183-7}, pages = {9--12}, publisher = {IEEE Comput. Soc}, title = {{An efficient boundary encoding scheme which is optimal in the rate distortion sense}}, url = {http://ieeexplore.ieee.org/document/638660/}, volume = {2}, year = {1997} }
@inproceedings{Hong1997, abstract = {n this paper, we propose a spatially adaptive image restoration algorithm, using local statistics. The local variance, mean and maximum value are utilized to constraint the solution space. These parameters are computed at each iteration step using partially restored image. A parameter defined by the user determines the degree of local smoothness imposed on the solution. The resulting iterative algorithm exhibits increased convergence speed when compared with the nonadaptive algorithm.}, author = {Hong, Min-cheol and Stathaki, Tania and Katsaggelos, Aggelos K}, title = {{Iterative Regularized Image Restoration Using Local}}, url = {https://www.academia.edu/2704377/Iterative_regularized_image_restoration_using_local_constraints}, year = {1997} }
@inproceedings{hong1997iterative, abstract = {This paper introduces an iterative regularized approach to increase the resolution of a video sequence. A multiple input smoothing convex functional is defined and used to obtain a globally optimal high resolution video sequence. A mathematical model of multiple inputs is described by using the point spread function between the original and bilinearly interpolated images in the spatial domain, and motion estimation between frames in the temporal domain. An iterative algorithm is utilized for obtaining the solution. The regularization parameter is updated at each iteration step from the partially restored video sequence. Experimental results demonstrate the capability of the proposed approach.}, author = {{Min-Cheol Hong} and {Moon Gi Kang} and Katsaggelos, Aggelos K. A.K. and Hong, Min Cheol and Kang, Moon Gi and Katsaggelos, Aggelos K. A.K.}, booktitle = {Proceedings of International Conference on Image Processing}, doi = {10.1109/ICIP.1997.638811}, isbn = {0-8186-8183-7}, organization = {IEEE}, pages = {474--477}, publisher = {IEEE Comput. Soc}, title = {{Iterative weighted regularized algorithm for improving the resolution of video sequences}}, url = {http://ieeexplore.ieee.org/document/638811/}, volume = {2}, year = {1997} }
@inproceedings{Guido1997g, abstract = {In this paper we introduce an optimal bit allocation scheme for dependent quantizers for the minimum maximum distortion criterion. First we show how minimizing the bit rate for a given maximum distortion can be achieved in a dependent coding framework using dynamic programming (DP). Then we employ an iterative algorithm to minimize the maximum distortion for a given bit rate, which invokes the DP scheme. We prove that it converges to the optimal solution. Finally we present a comparison between the minimum total distortion criterion and the minimum maximum distortion criterion for the encoding of an H.263 Intra frame. In this comparison we also point out the similarities between the proposed minimum maximum distortion approach and the Lagrangian multiplier based minimum total distortion approach.}, author = {Schuster, G.M. and Katsaggelos, A.K.}, booktitle = {1997 IEEE International Conference on Acoustics, Speech, and Signal Processing}, doi = {10.1109/ICASSP.1997.595449}, isbn = {0-8186-7919-0}, issn = {07367791}, pages = {3105--3108}, publisher = {IEEE Comput. Soc. Press}, title = {{Optimal bit allocation among dependent quantizers for the minimum maximum distortion criterion}}, url = {http://ieeexplore.ieee.org/document/595449/}, volume = {4}, year = {1997} }
@inproceedings{Fabian1997, author = {Fabian, W Meier and Guido, M Schuster and Aggelos, K Katsaggelos}, booktitle = {Proc. 2nd Erlangen Symp., Advances in Digital Image Communication}, pages = {75--84}, title = {{An efficient boundary encoding scheme using B-spline curves which is optimal in the rate-distortion sense,}}, url = {https://www.researchgate.net/publication/2587071_An_efficient_boundary_encoding_scheme_using_B-Spline_Curves_which_is_optimal_in_the_rate-distortion_sense}, year = {1997} }
@inproceedings{Chun-Jen1997a, author = {Tsai, Chun-Jen and Katsaggelos, Aggelos K.}, booktitle = {Visual Communications and Image Processing '97}, doi = {10.1117/12.263248}, editor = {Biemond, Jan and {Delp III}, Edward J.}, month = {jan}, pages = {360--368}, title = {{Optical-flow estimation for multichannel video sequences}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=920462}, volume = {3024}, year = {1997} }
@inproceedings{Damon1996, abstract = {Occluded regions and motion boundaries introduce displacement vector field (DVF) discontinuities that must be reconciled to accurately estimate image flow. In this work, the robust regularized estimation of the DVF is considered in the presence of these discontinuities. A robust convex estimation criterion is presented that preserves motion boundaries and allows for a globally optimal estimate of the DVF. A new class of robust convex measures is introduced for edge preserving regularization and an occlusion weighted gradient is proposed as mechanism for managing DVF discontinuities due to occlusion. Results using synthetic image sequences are presented.}, author = {Tull, D.L. and Katsaggelos, A.K.}, booktitle = {1996 IEEE International Symposium on Circuits and Systems. Circuits and Systems Connecting the World. ISCAS 96}, doi = {10.1109/ISCAS.1996.541794}, isbn = {0-7803-3073-0}, issn = {02714310}, pages = {592--595}, publisher = {IEEE}, title = {{Regularized estimation of occluded displacement vector fields}}, url = {http://ieeexplore.ieee.org/document/541794/}, volume = {2}, year = {1996} }
@inproceedings{Serafim1996, author = {Efstratiadis, Serafim N. and Karampatzakis, T. and Sahinoglou, Haralambos and Katsaggelos, Aggelos K.}, booktitle = {Digital Compression Technologies and Systems for Video Communications}, doi = {10.1117/12.251303}, editor = {Ohta, Naohisa}, month = {sep}, pages = {427--437}, title = {{Multiple-candidate hierachical block matching with inherent smoothness properties}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=1026467}, volume = {2952}, year = {1996} }
@inproceedings{Tom1996, author = {Tom, Brian C. and Katsaggelos, Aggelos K.}, doi = {10.1117/12.233218}, editor = {Ansari, Rashid and Smith, Mark J. T.}, month = {feb}, pages = {1430--1438}, title = {{Iterative algorithm for improving the resolution of video sequences}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=1017999}, year = {1996} }
@inproceedings{Taner1996a, abstract = {One of the challenging problems that most existing video codecs face today is the encoding of the information pertaining to the occluded areas, i.e., the areas which are covered or uncovered by moving objects. The existing techniques necessitate the transmission of the position information of the occluded areas following the detection process, which can constitute a large overhead in bandwidth consumption. In addition, these detection techniques fail under noisy conditions. On the other hand, no effort was made to incorporate the spatio-temporal correlation that exists between motion fields of consecutive frames. In this paper, a new method to detect the occluded areas is described. In this method, the decoder is given additional intelligence to extract the position information of the occluded areas, thus reducing the bandwidth needed to transmit the occlusion information significantly. According to the proposed method, the temporal correlation of the motion fields is exploited. The proposed method is robust under noisy conditions and provides a computationally simple solution.}, author = {Ozcelik, Taner and Katsaggelos, A.K.}, booktitle = {1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings}, doi = {10.1109/ICASSP.1996.545725}, isbn = {0-7803-3192-3}, issn = {07367791}, pages = {2068--2071}, publisher = {IEEE}, title = {{Detection and encoding of occluded areas in very low bit rate video coding}}, url = {http://ieeexplore.ieee.org/document/545725/}, volume = {4}, year = {1996} }
@inproceedings{kang1996globally, author = {Kang, Moon Gi and Katsaggelos, Aggelos K. and Park, Kyu Tae}, booktitle = {Visual Communications and Image Processing '96}, doi = {10.1117/12.233226}, editor = {Ansari, Rashid and Smith, Mark J. T.}, month = {feb}, organization = {SPIE}, pages = {1505--1513}, title = {{Globally optimal smoothing functional for edge-enhancing regularized image restoration}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=1018006}, volume = {2727}, year = {1996} }
@inproceedings{Brian1996b, author = {Brian, C Tom and Aggelos, K Katsaggelos}, booktitle = {1996 8th European Signal Processing Conference (EUSIPCO 1996)}, pages = {1--4}, title = {{Resolution enhancement of color video}}, url = {https://ieeexplore.ieee.org/document/7083291}, year = {1996} }
@inproceedings{Aggelos1996a, abstract = {The field of image restoration began primarily with the efforts of scientists involved in the space program of both the United States and the former Soviet Union. Today, considered to be the most exciting and expanding area of application for image restoration is that in the field of image and video coding. Nonetheless, digital image restoration is being used in many other applications as well. From the viewpoint of applications, the future of image restoration depends upon the needs of a variety of video technologies which will require the processing of digital images for a number of reasons.}, author = {Katsaggelos, A.K.}, booktitle = {Proceedings of APCCAS'96 - Asia Pacific Conference on Circuits and Systems}, doi = {10.1109/APCAS.1996.569312}, isbn = {0-7803-3702-6}, pages = {458--459}, publisher = {IEEE}, title = {{Recent trends in image restoration and enhancement techniques}}, url = {http://ieeexplore.ieee.org/document/569312/}, year = {1996} }
@inproceedings{Guido1996c, author = {Guido, M Schuster and Aggelos, K Katsaggelos}, booktitle = {Proceedings of 3rd IEEE International Conference on Image Processing}, doi = {10.1109/ICIP.1996.560606}, pages = {77--80}, title = {{An efficient boundary encoding scheme which is optimal in the rate distortion sense}}, url = {https://ieeexplore.ieee.org/document/560606}, volume = {2}, year = {1996} }
@inproceedings{James1996a, abstract = {In this paper we briefly describe some of our work on the rise of stochastic models to describe the displacement vector field (DVF) in an image sequence. Specifically, autoregresive models are used which describe the abrupt transitions in the DVF with the use of a line process, but also result in spatio-temporally recursive structures. The use of such models in developing maximum a posteriori estimators for the DVF and the line process is subsequently described. Finally, the extension and application of the resulting estimator to the problems of object tracking, video compression and restoration of video sequences is briefly reviewed.}, author = {Brailean, J.C. and Katsaggelos, A.K.}, booktitle = {Proceedings of 3rd IEEE International Conference on Image Processing}, doi = {10.1109/ICIP.1996.559649}, isbn = {0-7803-3259-8}, pages = {917--920}, publisher = {IEEE}, title = {{Recursive map displacement field estimation and its applications}}, url = {http://ieeexplore.ieee.org/document/559649/}, volume = {1}, year = {1996} }
@inproceedings{Guido1996a, author = {Schuster, Guido M and Katsaggelos, Aggelos K}, booktitle = {Digital Compression Technologies and Systems for Video Communications}, doi = {10.1117/12.251317}, editor = {Ohta, Naohisa}, month = {sep}, pages = {50--61}, title = {{Optimal quad-tree-based motion estimator}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=1026428}, volume = {2952}, year = {1996} }
@inproceedings{James1996, abstract = {An important component of any spatial temporal gradient motion estimation algorithm is the accuracy by which spatial gradients are calculated. When an image sequence is corrupted by noise, the problem of determining these spatial gradients becomes extremely difficult. This is immediately apparent, since the magnitude response of the derivative operator is |$\omega$VBAR. In other words, the components of an image are amplified upon differentiation in proportion to their frequency value. Thus, high-frequency noise terms will dominate any low-frequency features in the differentiated image. If this corrupted differentiated image is then used within a spatio-temporal gradient motion estimator, the noise will erroneously influence the estimated motion vector. In this paper, the problem of estimating the spatial gradient is treated as an inverse problem with noise. Formulating the problem in this manner results in a recursive gradient estimator that suppresses the effects of noise.}, author = {Brailean, J.C. and Katsaggelos, A.K.}, booktitle = {Proceedings., International Conference on Image Processing}, doi = {10.1109/ICIP.1995.529583}, isbn = {0-7803-3122-2}, pages = {211--214}, publisher = {IEEE Comput. Soc. Press}, title = {{Noise robust spatial gradient estimation for use in displacement estimation}}, url = {http://ieeexplore.ieee.org/document/529583/}, volume = {1}, year = {1996} }
@inproceedings{Rafael1996, abstract = {In this paper we examine the use of compound Gauss Markov random fields (CGMRF) to restore severely blurred high range images. For this deblurring problem, the convergence of the Simulated Annealing (SA) and Iterative Conditional Mode (ICM) algorithms has not been established. We propose two new iterative restoration algorithms which extend the classical SA and ICM approaches. Their convergence is established and they are tested on real and synthetic images.}, author = {Molina, R. and Katsaggelos, A.K. and Mateos, J. and Abad, J.}, booktitle = {Proceedings of 3rd IEEE International Conference on Image Processing}, doi = {10.1109/ICIP.1996.560889}, isbn = {0-7803-3259-8}, pages = {469--472}, publisher = {IEEE}, title = {{Restoration of severely blurred high range images using compound models}}, url = {http://ieeexplore.ieee.org/document/560889/}, volume = {1}, year = {1996} }
@inproceedings{MoonGi1996, author = {{Moon Gi}, Kang and Aqqelos, K Katsaqqelos}, booktitle = {1996 8th European Signal Processing Conference (EUSIPCO 1996)}, pages = {1--4}, title = {{Deterministic estimation of the bispectrum and its application to image restoration}}, url = {https://ieeexplore.ieee.org/document/7082930}, year = {1996} }
@inproceedings{Aggelos2002, abstract = {The proceedings contains 23 papers. Following topics are discussed: neural network architectures for image coding; fuzzy and neural classification, segmentation and feature extraction; neural networks for object classification and labeling; and optimization and learning.}, author = {Nasrabadi, Nasser M. and Katsaggelos, Aggelos K. (Eds)}, booktitle = {Proceedings of SPIE - The International Society for Optical Engineering}, isbn = {0819420387}, title = {{Applications of Artificial Neural Networks in Image Processing}}, volume = {2664}, year = {1996} }
@inproceedings{Guido1996e, author = {Schuster, G.M. and Katsaggelos, A.K.}, booktitle = {1996 IEEE International Symposium on Circuits and Systems. Circuits and Systems Connecting the World. ISCAS 96}, doi = {10.1109/ISCAS.1996.541806}, isbn = {0-7803-3073-0}, pages = {640--643}, publisher = {IEEE}, title = {{An optimal segmentation encoding scheme in the rate distortion sense}}, url = {http://ieeexplore.ieee.org/document/541806/}, volume = {2}, year = {1996} }
@inproceedings{Javier1996, author = {Mateos, Javier and Katsaggelos, Aggelos K. and Molina, Rafael}, booktitle = {Digital Compression Technologies and Systems for Video Communications}, doi = {10.1117/12.251331}, editor = {Ohta, Naohisa}, month = {sep}, pages = {70--81}, title = {{Parameter estimation in regularized reconstruction of BDCT compressed images for reducing blocking artifacts}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=1026430}, volume = {2952}, year = {1996} }
@inproceedings{Brian1996, abstract = {In this paper a solution is provided to the problem of obtaining a high resolution image from several low resolution images that have been subsampled and displaced by different amounts of sub-pixel shifts. In its most general form, this problem can be broken up into three sub-problems: registration, restoration, and interpolation. Previous work has either solved all three sub-problems independently, or more recently, solved either the first two steps (registration and restoration) or the last two steps together. However, none of the existing methods solve all three sub-problems simultaneously. This paper poses the low resolution to high resolution problem as a Maximum Likelihood (ML) problem which is solved by the Expectation-Maximization (EM) algorithm. By exploiting the structure of the matrices involved, the problem can be solved in the discrete frequency domain. The ML problem is then the estimation of the sub-pixel shifts, the noise variances of each image, the power spectra of the high resolution image, and the high resolution image itself. Experimental results are shown which demonstrate the effectiveness of this approach.}, author = {Tom, B.C. and Katsaggelos, A.K.}, booktitle = {Proceedings., International Conference on Image Processing}, doi = {10.1109/ICIP.1995.537535}, isbn = {0-7803-3122-2}, pages = {539--542}, publisher = {IEEE Comput. Soc. Press}, title = {{Reconstruction of a high-resolution image by simultaneous registration, restoration, and interpolation of low-resolution images}}, url = {http://ieeexplore.ieee.org/document/537535/}, volume = {2}, year = {1996} }
@inproceedings{Min-Cheol1996, author = {Hong, Min-Cheol and Katsaggelos, Aggelos K.}, booktitle = {Digital Compression Technologies and Systems for Video Communications}, doi = {10.1117/12.251262}, editor = {Ohta, Naohisa}, month = {sep}, pages = {82--91}, title = {{Iterative regularized error concealment algorithm}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=1026431}, volume = {2952}, year = {1996} }
@inproceedings{Guido1996b, author = {Schuster, Guido M. and Katsaggelos, Aggelos K.}, booktitle = {Visual Communications and Image Processing '96}, doi = {10.1117/12.233293}, editor = {Ansari, Rashid and Smith, Mark J. T.}, month = {feb}, pages = {784--795}, title = {{Fast and efficient mode and quantizer selection in the rate distortion sense for H.263}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=1017935}, volume = {2727}, year = {1996} }
@inproceedings{Brian1996a, author = {Tom, B.C. and Katsaggelos, A.K.}, booktitle = {Proceedings of 3rd IEEE International Conference on Image Processing}, doi = {10.1109/ICIP.1996.559598}, isbn = {0-7803-3259-8}, pages = {713--716}, publisher = {IEEE}, title = {{Resolution enhancement of video sequences using motion compensation}}, url = {http://ieeexplore.ieee.org/document/559598/}, volume = {1}, year = {1996} }
@inproceedings{katsaggelos1995hybrid, address = {Boston, MA}, author = {Katsaggelos, Aggelos K and {\"{O}}zcelik, Taner}, booktitle = {Multimedia Communications and Video Coding}, doi = {10.1007/978-1-4613-0403-6_28}, pages = {223--231}, publisher = {Springer US}, title = {{Exploitation of Spatio-Temporal Inter-Correlation Among Motion, Segmentation and Intensity Fields for Very Low Bit Rate Coding of Video}}, url = {http://link.springer.com/10.1007/978-1-4613-0403-6_28}, year = {1996} }
@inproceedings{Serafim1995, abstract = {Motion vector field (MVF) prediction methods are presented followed by a restoration method. These methods combined with a proposed motion compensated (MC) video coding scheme are suitable for low bitrate transmission. An expression is derived for the initial estimate of the working MVF based on the preceding MVF. Spatio-temporally adaptive regularization is applied using neighborhood information. The output MVF is used as the initial prediction estimate for a Kalman MVF restoration approach. By applying this method to both the encoder and decoder, the resulting MC MVF and image intensity temporal updates are coded and transmitted. The restoration method produces accurate estimates of the MVF, thus resulting in a significant transmission cost reduction. Experiments with standard video-conference image sequences demonstrate the improved performance of the proposed scheme.}, author = {Efstratiadis, S.N. and Strintzis, M.G. and Katsaggelos, A.K.}, booktitle = {Proceedings., International Conference on Image Processing}, doi = {10.1109/ICIP.1995.537452}, isbn = {0-7803-3122-2}, pages = {213--216}, publisher = {IEEE Comput. Soc. Press}, title = {{Motion field prediction and restoration for low bit-rate video coding}}, url = {http://ieeexplore.ieee.org/document/537452/}, volume = {2}, year = {1996} }
@inproceedings{Guido1996f, abstract = {In this paper, we present a fast and optimal method for the lossy encoding of object boundaries which are givenas8-connectchaincodes.Weapproximatetheboundarybyapolygonandconsidertheproblemoffinding the polygon which can be encoded with the smallest number of bits for a given maximum distortion. To this end, we derive a fast and optimal scheme which is based on a shortest path algorithm for a weighted directed acyclic graph. We further investigate the dual problem of finding the polygonal approximation which leads to the smallest maximum distortion for a given bit rate. We present an iterative scheme which employs the above mentioned shortest path algorithm and prove that it converges to the optimal solution. We then extend the proposed algorithm to the encoding of multiple object boundaries and introduce a vertex encoding scheme which is a combination of an 8-connect chain code and a run-length code. We present results of the proposed algorithm using objects from the "Miss America" sequence.}, author = {Schuster, Guido M. and Katsaggelos, Aggelos K.}, booktitle = {Visual Communications and Image Processing '96}, doi = {10.1117/12.233321}, editor = {Ansari, Rashid and Smith, Mark J. T.}, month = {feb}, pages = {1050--1061}, title = {{Optimal lossy segmentation encoding scheme}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=1017962}, volume = {2727}, year = {1996} }
@inproceedings{Damon1996a, abstract = {Due to the finite acquisition time of practical cameras, objects can move during image acquisition, therefore introducing motion blur degradations. Traditionally, these degradations are treated as undesirable artifacts that should be removed before further processing. In this work, we consider the use of motion blur as an indication of scene motion. We present two robust regularized motion estimation algorithms that consider the use of (motion) blur in their formulation. The first algorithm uses motion blur as prior knowledge for the estimation of the motion field. The second algorithm considers the joint estimation of the motion and motion blur. Each approach results in a motion blur point spread field, a motion field and a restored image in an approach that is different from previous work. Preliminary results are presented.}, author = {Tull, D.L. and Katsaggelos, A.K.}, booktitle = {Proceedings of 3rd IEEE International Conference on Image Processing}, doi = {10.1109/ICIP.1996.560375}, isbn = {0-7803-3259-8}, pages = {85--88}, publisher = {IEEE}, title = {{Regularized blur-assisted displacement field estimation}}, url = {http://ieeexplore.ieee.org/document/560375/}, volume = {3}, year = {1996} }
@inproceedings{Taner1996b, author = {Ozcelik, Taner and Katsaggelos, Aggelos K.}, booktitle = {Visual Communications and Image Processing'96}, doi = {10.1117/12.233297}, editor = {Ansari, Rashid and Smith, Mark J. T.}, month = {feb}, pages = {820--831}, title = {{Detection and encoding of model failures in very low bit rate video coding}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=1017939}, volume = {2727}, year = {1996} }
@inproceedings{Edward1995, abstract = {The proceedings contains 61 papers. Some of the specific topics discussed are: optimization of stack filters under constraints; estimation of morphological degradation parameters; computational representation of lattice operators; morphological feature detection for cervical cancer screening; controlled anisotropic diffusion; Boltzmann machines for image-block coding; infrared boundary-based approach to object recognition; fuzzy similarity measures for ultrasound tissue characterization; comparison of several approaches for segmentation of texture images; and handwriting recognition using a reduced character method and neural nets.}, author = {Edward, R Dougherty and Jaakko, T Astola and Harold, G Longbotham and Nasser, M Nasrabadi and Aggelos, K Katsaggelos}, booktitle = {Proceedings of SPIE - The International Society for Optical Engineering}, isbn = {0819417718}, title = {{Nonlinear Image Processing VI}}, volume = {2424}, year = {1995} }
@inproceedings{tull1995iterative, author = {Tull, Damon L. and Katsaggelos, Aggelos K.}, booktitle = {Visual Communications and Image Processing '95}, doi = {10.1117/12.206640}, editor = {Wu, Lance T.}, month = {apr}, organization = {SPIE INTERNATIONAL SOCIETY FOR OPTICAL}, pages = {1088--1098}, title = {{Iterative restoration of fast moving objects in dynamic image sequences}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=1001881}, volume = {2501}, year = {1995} }
@inproceedings{chan1995occlusion, author = {Chan, Cheuk L. and Brailean, James C. and Katsaggelos, Aggelos K.}, booktitle = {Visual Communications and Image Processing '95}, doi = {10.1117/12.206802}, editor = {Wu, Lance T.}, isbn = {0819418587}, issn = {0277786X}, month = {apr}, organization = {SPIE INTERNATIONAL SOCIETY FOR OPTICAL}, pages = {962--973}, title = {{Occlusion and nonstationary displacement field estimation in quantum-limited image sequences}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=1001857}, volume = {2501}, year = {1995} }
@inproceedings{Ozcelik1995, abstract = {Image and video coding algorithms have found a number of applications ranging from video telephony on the Public Switched Telephone Networks (PSTN) to HDTV. However, as the bit rate is lowered, most of the existing techniques, as well as current standards, such as JPEG, H. 261, and MPEG-1 produce highly visible degradations in the reconstructed images primarily due to the information loss caused by the quantization process. In this paper, we propose an iterative technique to reduce the unwanted degradations, such as blocking and mosquito artifacts while keeping the necessary detail present in the original image. The proposed technique makes use of a priori information about the original image through a nonstationary Gauss-Markov model. Utilizing this model, a maximum a posteriori (MAP) estimate is obtained iteratively using mean field annealing. The fidelity to the data is preserved by projecting the image onto a constraint set defined by the quantizer at each iteration. The proposed solution represents an implementation of a paradigm we advocate, according to which the decoder is not simply undoing the operations performed by the encoder, but instead it solves an estimation problem based on the available bitstream and any prior knowledge about the source image. The performance of the proposed algorithm was tested on a JPEG, as well as on an H.261-type video codec. It is shown to be effective in removing the coding artifacts present in low bit rate compression. {\textcopyright} 1995 IEEE}, author = {Ozcelik, T. and Brailean, J.C. and Katsaggelos, A.K.}, booktitle = {Proceedings of the IEEE}, chapter = {304}, doi = {10.1109/5.364460}, isbn = {00189219}, issn = {00189219}, keywords = {Image and video compression,image and video coding,mean field annealing}, number = {2}, pages = {304--316}, title = {{Image and video compression algorithms based on recovery techniques using mean field annealing}}, url = {http://ieeexplore.ieee.org/document/364460/}, volume = {83}, year = {1995} }
@inproceedings{Damon1995, abstract = {In this paper, the regularized estimation of the displacement vector field (DVF) of a dynamic image sequence is considered. A new class of non-quadratic convex regularization functionals is employed to estimate the motion field in the presence of motion discontinuities and occlusions. The derivation of the functionals is based on entropy considerations and do not require parameter tuning as in previously proposed methods. This new class of functionals is both robust and convex making it possible to preserve motion boundaries and obtain a globally optimum solution. The performance of entropic functionals is compared to previously suggested functionals for motion estimation using real and synthetic image sequences.}, author = {Tull, D.L. and Katsaggelos, A.K.}, booktitle = {Proceedings., International Conference on Image Processing}, doi = {10.1109/ICIP.1995.537618}, isbn = {0-7803-3122-2}, pages = {212--215}, publisher = {IEEE Comput. Soc. Press}, title = {{Regularized motion estimation using robust entropic functionals}}, url = {http://ieeexplore.ieee.org/document/537618/}, volume = {3}, year = {1995} }
@inproceedings{oezcelik1995video, author = {Ozcelik, Taner and Brailean, James C. and Katsaggelos, Aggelos K.}, booktitle = {Visual Communications and Image Processing '95}, doi = {10.1117/12.206733}, editor = {Wu, Lance T.}, month = {apr}, organization = {SPIE INTERNATIONAL SOCIETY FOR OPTICAL}, pages = {284--295}, title = {{Video coding algorithm based on recovery techniques using mean field annealing}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=1001722}, volume = {2501}, year = {1995} }
@inproceedings{John1995, author = {Goyette, John A. and Kang, Moon Gi and Katsaggelos, Aggelos K. and Lapin, Gregory D.}, booktitle = {Proceedings of SPIE}, doi = {10.1117/12.216883}, isbn = {0819419869}, issn = {0277786X}, pages = {811--822}, publisher = {SPIE}, title = {{Spatially adaptive image restoration for autoradiography}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=1011272}, volume = {2622}, year = {1995} }
@inproceedings{Aggelos1995a, author = {Katsaggelos, Aggelos K. and Banham, Mark R.}, booktitle = {Digital Signal Processing Technology: A Critical Review}, doi = {10.1117/12.204202}, issn = {1996756X}, month = {apr}, pages = {102790B}, title = {{Digital restoration of images: recent advances and future trends}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?doi=10.1117/12.204202}, volume = {10279}, year = {1995} }
@inproceedings{molina1994hierarchical, author = {Molina, Rafael and Katsaggelos, Aggelos K}, booktitle = {PROCEEDINGS-SPIE THE INTERNATIONAL SOCIETY FOR OPTICAL ENGINEERING}, doi = {10.1117/12.185966}, editor = {Katsaggelos, Aggelos K.}, month = {sep}, organization = {SPIE INTERNATIONAL SOCIETY FOR OPTICAL}, pages = {244--251}, title = {{Hierarchical Bayesian approach to image restoration and the iterative evaluation of the regularization parameter}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=976075}, year = {1994} }
@inproceedings{Brian1994a, author = {Tom, Brian C. and Katsaggelos, Aggelos K.}, booktitle = {Visual Communications and Image Processing'94}, doi = {10.1117/12.186041}, editor = {Katsaggelos, Aggelos K.}, month = {sep}, pages = {971--981}, title = {{Reconstruction of a high-resolution image from multiple-degraded misregistered low-resolution images}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=976296}, volume = {2308}, year = {1994} }
@inproceedings{MoonGi1994a, author = {Kang, Moon Gi and Katsaggelos, Aggelos K.}, booktitle = {Visual Communications and Image Processing '94}, doi = {10.1117/12.185965}, editor = {Katsaggelos, Aggelos K.}, month = {sep}, organization = {SPIE}, pages = {232--243}, title = {{Globally optimal smoothing functional for multichannel image restoration}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=976072}, volume = {2308}, year = {1994} }
@inproceedings{Aggelos1994, address = {Baltimore, Maryland, USA}, author = {Katsaggelos, Aggelos K and Kang, Moon Gi and Banham, Mark R and Science, Computer}, booktitle = {The Restoration of HST Images and Spectra - II}, pages = {3--13}, publisher = {Proceedings of a workshop held at the Space Telescope Science Institute}, title = {{Adaptive Regularized Restoration Algorithms Applied to HST Images}}, url = {https://adsabs.harvard.edu/full/1994rhis.conf....3K}, year = {1994} }
@inproceedings{Yang1994, author = {Yang, Yongyi and Galatsanos, Nikolas P. and Katsaggelos, Aggelos K.}, doi = {10.1117/12.185906}, editor = {Katsaggelos, Aggelos K.}, month = {sep}, pages = {1477--1488}, title = {{Projection-based spatially adaptive reconstruction of block transform compressed images}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=976452}, year = {1994} }
@inproceedings{kostas1994super, author = {Kostas, Thomas J. and Mugnier, Laurent M. and Katsaggelos, Aggelos K. and Sahakian, Alan V.}, booktitle = {Visual Communications and Image Processing '94}, doi = {10.1117/12.186036}, editor = {Katsaggelos, Aggelos K.}, month = {sep}, organization = {SPIE INTERNATIONAL SOCIETY FOR OPTICAL}, pages = {921--929}, title = {{Super-exponential method for blur identification and image restoration}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=976280}, volume = {2308}, year = {1994} }
@inproceedings{brailean1994restoration, abstract = {Most of the transform-based image compression techniques produce visible artifacts in the reconstructed image, particularly at low bit rates. In this paper, we propose an iterative technique to reduce the unwanted degradations such as blocking artifacts while keeping the necessary detail present in the original image. The proposed technique makes use of a priori information about the original image by using a nonstationary Gauss-Markov model. A MAP estimate is obtained iteratively using mean field annealing. A additional a priori information about the transform of the original image is incorporated into the estimation process by projecting the image onto a set defined by the quantizer at each iteration. The performance of the proposed algorithm was tested on JPEG compressed images. It is shown to be effective in removing the coding artifacts present in the low bit rate compressed images. {\textcopyright} 1994 IEEE.}, author = {Brailean, J.C. and Ozcelik, T. and Katsaggelos, A.K.}, booktitle = {Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing}, doi = {10.1109/ICASSP.1994.389488}, isbn = {0-7803-1775-0}, issn = {15206149}, organization = {IEEE}, pages = {V/237--V/240}, publisher = {IEEE}, title = {{Restoration of low bit rate compressed images using mean field annealing}}, url = {http://ieeexplore.ieee.org/document/389488/}, volume = {v}, year = {1994} }
@inproceedings{banham1994spatially, author = {Banham, Mark R. and Katsaggelos, Aggelos K.}, booktitle = {Visual Communications and Image Processing '94}, doi = {10.1117/12.185885}, editor = {Katsaggelos, Aggelos K.}, month = {sep}, organization = {SPIE}, pages = {1256--1267}, title = {{Spatially adaptive multiscale image restoration using the wavelet transform}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=976383}, volume = {2308}, year = {1994} }
@inproceedings{tom1994reconstruction, abstract = {In applications that demand highly detailed images, it is often not feasible nor sometimes possible to acquire images of such high resolution by just using hardware (high precision optics and charge coupled devices (CCDs)). Instead, image processing methods may be used to construct a high resolution image from multiple, degraded, low resolution images. It is assumed that the low resolution images have been sub-sampled and displaced by sub-pixel shifts. Therefore, the problem can be divided into three sub-problems: registration (estimating the shifts), restoration, and interpolation. This paper focuses on solving the first two sub-problems simultaneously, using the expectation-maximization (EM) algorithm. Experimental results are presented that demonstrate the effectiveness of this approach.}, author = {Tom, B.C. and Katsaggelos, A.K. and Galatsanos, N.P.}, booktitle = {Proceedings of 1st International Conference on Image Processing}, doi = {10.1109/ICIP.1994.413745}, isbn = {0-8186-6952-7}, issn = {15224880}, organization = {IEEE}, pages = {553--557}, publisher = {IEEE Comput. Soc. Press}, title = {{Reconstruction of a high resolution image from registration and restoration of low resolution images}}, url = {http://ieeexplore.ieee.org/document/413745/}, volume = {3}, year = {1994} }
@inproceedings{banham1994multiscale, abstract = {This paper introduces a method for spatially adaptive image restoration based on the detail coefficients of the wavelet transform of a noisy blurred image. A multiscale recursive smoothing filter is applied to the wavelet coefficients ordered onto quadtree structures along different orientations. These coefficients are first prefiltered by a constrained least squares filter in order to remove the spatial correlations due to the blur. An optimal way of choosing the regularization parameters used for this prefiltering operation is introduced here. This is based on an analysis of the detection operations performed by the multiscale filter in order to model edge and non-edge regions of the image differently. Results show that this approach offers a highly adaptive means of preserving edges in a restored image.}, author = {Banham, M.R. and Katsaggelos, A.K.}, booktitle = {Proceedings of 1st International Conference on Image Processing}, doi = {10.1109/ICIP.1994.413862}, isbn = {0-8186-6952-7}, issn = {15224880}, organization = {IEEE}, pages = {187--191}, publisher = {IEEE Comput. Soc. Press}, title = {{Multiscale adaptive image restoration in the wavelet domain}}, url = {http://ieeexplore.ieee.org/document/413862/}, volume = {3}, year = {1994} }
@inproceedings{Aggelos1994a, author = {Aggelos, K Katsaggelos}, booktitle = {Visual Communications and Image Processing'94}, title = {{Visual Communications and Image Processing'94}}, volume = {2308}, year = {1994} }
@inproceedings{Brian1994, author = {Tom, Brian C. and Katsaggelos, Aggelos K.}, booktitle = {Applications of Digital Image Processing XVII}, doi = {10.1117/12.186544}, editor = {Tescher, Andrew G.}, month = {sep}, pages = {316--331}, title = {{Multichannel image identification and restoration using the expectation-maximization algorithm}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=974996}, volume = {2298}, year = {1994} }
@inproceedings{mesarovic1994regularized, author = {Mesarovic, Vladimir Z and Galatsanos, Nikolas P and Katsaggelos, Aggelos K}, booktitle = {PROCEEDINGS-SPIE THE INTERNATIONAL SOCIETY FOR OPTICAL ENGINEERING}, doi = {10.1117/12.185888}, editor = {Katsaggelos, Aggelos K.}, month = {sep}, organization = {SPIE INTERNATIONAL SOCIETY FOR OPTICAL}, pages = {1301--1312}, title = {{Regularized constrained total least-squares image restoration}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=976397}, year = {1994} }
@inproceedings{oezcelik1994low, author = {Ozcelik, Taner and Katsaggelos, Aggelos K.}, booktitle = {Visual Communications and Image Processing '94}, doi = {10.1117/12.185883}, editor = {Katsaggelos, Aggelos K.}, month = {sep}, organization = {SPIE INTERNATIONAL SOCIETY FOR OPTICAL}, pages = {1231--1242}, title = {{Low bit-rate video compression based on maximum a posteriori (MAP) recovery techniques}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=976376}, volume = {2308}, year = {1994} }
@inproceedings{MoonGi1994, abstract = {Proposes a general form of the weighted smoothing functional for regularized image restoration. The weighting matrices which introduce the spatial adaptivity are defined as a function of the (partially) restored image. As a result no prior knowledge about the image is required but the smoothing functional to be minimized is nonlinear with respect to the unknown image. Conditions for the convexity of the functional are established. An iterative algorithm is proposed for obtaining its minimum. Sufficient conditions for the convergence of the algorithm are established. Various forms of the weighting matrices are proposed. Experimental results demonstrate the effectiveness of the approach.}, author = {Kang, Moon Gi and Katsaggelos, Aggelos K A.K. and {Moon Gi Kang} and Katsaggelos, Aggelos K A.K.}, booktitle = {Proceedings of 1st International Conference on Image Processing}, doi = {10.1109/ICIP.1994.413660}, isbn = {0-8186-6952-7}, issn = {15224880}, organization = {IEEE}, pages = {695--699}, publisher = {IEEE Comput. Soc. Press}, title = {{A general formulation of the weighted smoothing functional for regularized image restoration}}, url = {http://ieeexplore.ieee.org/document/413660/}, volume = {2}, year = {1994} }
@inproceedings{molina1994hierarchical, author = {Molina, Rafael and Katsaggelos, Aggelos K}, booktitle = {PROCEEDINGS-SPIE THE INTERNATIONAL SOCIETY FOR OPTICAL ENGINEERING}, doi = {10.1117/12.185966}, editor = {Katsaggelos, Aggelos K.}, month = {sep}, organization = {SPIE INTERNATIONAL SOCIETY FOR OPTICAL}, pages = {244--251}, title = {{Hierarchical Bayesian approach to image restoration and the iterative evaluation of the regularization parameter}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=976075}, year = {1994} }
@inproceedings{MoonGi1993, author = {Kang, Moon Gi and Katsaggelos, Aggelos K.}, booktitle = {Visual Communications and Image Processing '93}, doi = {10.1117/12.157895}, editor = {Haskell, Barry G. and Hang, Hsueh-Ming}, issn = {0277786X}, month = {oct}, pages = {1364--1375}, title = {{Regularized iterative image restoration based on an iteratively updated convex smoothing functional}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=946419}, volume = {2094}, year = {1993} }
@inproceedings{Brailean1993a, author = {Brailean, J.C. and Katsaggelos, A.K.}, booktitle = {IEEE International Conference on Acoustics Speech and Signal Processing}, doi = {10.1109/ICASSP.1993.319800}, isbn = {0-7803-0946-4}, pages = {273--276 vol.5}, publisher = {IEEE}, title = {{Recursive displacement estimation and restoration of noisy-blurred image sequences}}, url = {http://ieeexplore.ieee.org/document/319800/}, year = {1993} }
@inproceedings{Brailean1993, author = {Brailean, James C. and Katsaggelos, Aggelos K.}, doi = {10.1117/12.157957}, editor = {Haskell, Barry G. and Hang, Hsueh-Ming}, month = {oct}, pages = {384--395}, title = {{Recursive MAP displacement estimation and restoration of noisy-blurred image sequences}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=946106}, year = {1993} }
@inproceedings{Chan1993, author = {Chan, Cheuk L. and Brailean, James C. and Katsaggelos, Aggelos K. and Sahakian, Alan V.}, doi = {10.1117/12.157958}, editor = {Haskell, Barry G. and Hang, Hsueh-Ming}, month = {oct}, pages = {396--407}, title = {{Maximum a posteriori displacement field estimation in quantum-limited image sequences}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=946109}, year = {1993} }
@inproceedings{yang1993regularized, author = {Yang, Yongyi and Galatsanos, Nikolas P and Katsaggelos, Aggelos K}, booktitle = {PROCEEDINGS-SPIE THE INTERNATIONAL SOCIETY FOR OPTICAL ENGINEERING}, doi = {10.1117/12.157970}, editor = {Haskell, Barry G. and Hang, Hsueh-Ming}, month = {oct}, organization = {SPIE INTERNATIONAL SOCIETY FOR OPTICAL}, pages = {511--521}, title = {{Regularized reconstruction to remove blocking artifacts from block discrete cosine transform compressed images}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=946143}, year = {1993} }
@inproceedings{yang1993iterative, abstract = {In this paper, iterative projection algorithms are presented to reconstruct visually pleasing images from Block Discrete Cosine Transform (BDCT) compressed image data. Two algorithms are proposed. The first is based on the theory of Projections Onto Convex Sets (POCS). The second is motivated by the theory of POCS. Experimental results are presented which demonstrate that the proposed algorithms yield superior images to those obtained by direct reconstruction from the compressed data only.}, author = {Yang, Yongyi and Galatsanos, N. P. and Katsaggelos, A. K.}, booktitle = {Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing}, doi = {10.1109/icassp.1993.319833}, isbn = {0780309464}, issn = {07367791}, organization = {IEEE}, pages = {405--408}, title = {{Iterative projection algorithms for removing the blocking artifacts of block-DCT compressed images}}, volume = {5}, year = {1993} }
@inproceedings{oezcelik1993robust, author = {Ozcelik, Taner and Katsaggelos, Aggelos K.}, booktitle = {Visual Communications and Image Processing '93}, doi = {10.1117/12.157896}, editor = {Haskell, Barry G. and Hang, Hsueh-Ming}, issn = {0277786X}, month = {oct}, organization = {SPIE INTERNATIONAL SOCIETY FOR OPTICAL}, pages = {1378--1389}, title = {{Robust motion vector prediction algorithms with application to very low bit rate image sequence coding}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=946422}, volume = {2094}, year = {1993} }
@inproceedings{choi1993multichannel, abstract = {Restoration of image sequences is an important problem that can be encountered in many image processing applications, such as visual communications, robot guidance, and target tracking. The independent restoration of each frame in an image sequence is a suboptimal approach because the between-frame correlations are not explicitly taken into consideration. In this paper we address this problem by proposing a multichannel restoration approach. The multiple time-frames (channels) of the image sequence are restored simultaneously by using a multichannel regularized least-squares formulation of the problem. The regularization operator captures both within- and between-frame (channel) properties of the image sequence with the explicit use of the displacement vector field. We propose a number of different approaches to obtain the multichannel regularization operator, as well as an algorithm to iteratively compute the restored images. We present experiments that demonstrate the value of the proposed multichannel approach. {\textcopyright} 1996 Academic Press, Inc.}, author = {Choi, Mun Gi and Erdogan, Ozan E. and Galatsanos, Nikolas P. and Katsaggelos, Aggelos K.}, booktitle = {Journal of Visual Communication and Image Representation}, doi = {10.1117/12.157908}, editor = {Haskell, Barry G. and Hang, Hsueh-Ming}, issn = {10473203}, month = {oct}, number = {3}, organization = {SPIE INTERNATIONAL SOCIETY FOR OPTICAL}, pages = {1486--1497}, title = {{Multichannel regularized iterative restoration of image sequences}}, url = {https://linkinghub.elsevier.com/retrieve/pii/S104732039690022X http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=946456}, volume = {7}, year = {1993} }
@inproceedings{Banham1993, author = {Banham, M.R. and Gonzalez, H. and Galatsanos, N.P. and Katsaggelos, A.K.}, booktitle = {IEEE International Conference on Acoustics Speech and Signal Processing}, doi = {10.1109/ICASSP.1993.319802}, isbn = {0-7803-0946-4}, pages = {281--284 vol.5}, publisher = {IEEE}, title = {{Multichannel restoration of single channel images using a wavelet decomposition}}, url = {http://ieeexplore.ieee.org/document/319802/}, year = {1993} }
@inproceedings{Taner1993, author = {Ozcelik, T and Brailean, J C and Katsaggelos, A K}, booktitle = {Proc. 31st Allerton Conf. on Communications, Control and Computing}, pages = {473}, title = {{Recovery of low bit rate compressed images using Gibbs priors}}, year = {1993} }
@inproceedings{Taner1993b, address = {Reston, Virigina}, author = {Ozcelik, Taner and Katsaggelos, Aggelos}, booktitle = {9th Computing in Aerospace Conference}, doi = {10.2514/6.1993-4690}, month = {oct}, pages = {4690}, publisher = {American Institute of Aeronautics and Astronautics}, title = {{Low bit rate video coding without motion vector transmission}}, url = {https://arc.aiaa.org/doi/10.2514/6.1993-4690}, year = {1993} }
@inproceedings{goyette1993regularized, abstract = {In this paper the point spread function of autoradiography is experimentally measured and used with digital image restoration techniques to improve the resolution of autoradiographs. We compare two regularized iterative image restoration algorithms applied to autoradiography. A nonlinear filter is used for the removal of film grain noise prior to restoration. Our results indicate a 23% improvement in resolution.}, author = {Goyette, J.A. and Lapin, G.D. and Kang, M.G. and Katsaggelos, A.K.}, booktitle = {Proceedings of the 15th Annual International Conference of the IEEE Engineering in Medicine and Biology Societ}, doi = {10.1109/IEMBS.1993.978652}, isbn = {0-7803-1377-1}, issn = {05891019}, number = {pt 1}, organization = {Publ by IEEE}, pages = {490--491}, publisher = {IEEE}, title = {{Regularized iterative image restoration algorithms applied to autoradiography}}, url = {http://ieeexplore.ieee.org/document/978652/}, volume = {15}, year = {1993} }
@inproceedings{Mark, author = {Banham, Mark R. and Brailean, James C. and Katsaggelos, Aggelos K.}, booktitle = {Proceedings Volume 1818, Visual Communications and Image Processing '92}, doi = {10.1117/12.131439}, editor = {Maragos, Petros}, month = {nov}, pages = {210--221}, title = {{Wavelet transform image sequence coder using nonstationary displacement estimation}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=1003191}, volume = {1818}, year = {1992} }
@inproceedings{Aggelos1992b, author = {Katsaggelos, Aggelos K. and Galatsanos, Nikolas P. and Lay, Kuen-Tsair and Zhu, Wenwu}, booktitle = {Inverse Problems in Scattering and Imaging}, doi = {10.1117/12.139009}, editor = {Fiddy, Michael A.}, isbn = {0819409405}, issn = {0277786X}, month = {dec}, pages = {147--158}, title = {{Multichannel image identification and restoration based on the EM algorithm and cross-validation}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=999195}, volume = {1767}, year = {1992} }
@inproceedings{Serafim1992b, author = {Efstratiadis, S.N. and Katsaggelos, A.K.}, booktitle = {[Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing}, doi = {10.1109/ICASSP.1992.226205}, isbn = {0-7803-0532-9}, pages = {245--248 vol.3}, publisher = {IEEE}, title = {{Adaptive multiple-input constrained pel-recursive displacement estimation}}, url = {http://ieeexplore.ieee.org/document/226205/}, volume = {3}, year = {1992} }
@inproceedings{Banham1992, abstract = {In this paper, we develop a multichannel formulation of a single channel filtering problem in the wavelet domain. This technique is based on an orthogonal matrix representation of the 2-D separable wavelet transform. We show that semi-block circulant (SBC) structures resulting from a similarity transformation with this matrix operator permit a multichannel treatment of a noisy blurred image, yielding an adaptive restoration technique in the wavelet frequency domain. This work presents a new formulation of the 2-D separable wavelet decomposition that clearly produces matrices which may be block-diagonalized with an array Fourier transform. The method described here is a new tool, which builds on multichannel image restoration techniques developed in the past, but uses these ideas in the context of a single channel image, and offers much potential for improved adaptive image restoration in the wavelet domain.}, author = {Banham, M.R. and Galatsanos, N.P. and Katsaggelos, A.K. and Gonzalez, Hector}, booktitle = {[Proceedings] 1992 IEEE International Conference on Systems, Man, and Cybernetics}, doi = {10.1109/ICSMC.1992.271518}, isbn = {0-7803-0720-8}, issn = {1062922X}, pages = {1558--1563}, publisher = {IEEE}, title = {{Restoration of single-channel images with multi-channel filtering in the wavelet domain}}, url = {http://ieeexplore.ieee.org/document/271518/}, volume = {1992-Janua}, year = {1992} }
@inproceedings{James1992b, author = {Brailean, James C. and Katsaggelos, Aggelos K.}, booktitle = {Imaging Technologies and Applications}, doi = {10.1117/12.130976}, editor = {Heaston, Robert J.}, month = {aug}, organization = {SPIE}, pages = {170--181}, title = {{Displacement field estimation using a coupled Gauss-Markov model}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=1000008}, volume = {1778}, year = {1992} }
@inproceedings{Nikolas1992, address = {Washington, D.C.}, author = {Galatsanos, Nikolas P and Katsaggelos, Aggelos K}, booktitle = {Signal Recovery and Synthesis IV}, doi = {10.1364/SRS.1992.WC2}, pages = {WC2}, publisher = {Optica Publishing Group}, title = {{An Analysis of Regularized Linear Image Recovery}}, url = {https://opg.optica.org/abstract.cfm?URI=SRS-1992-WC2}, year = {1992} }
@inproceedings{kang1992frequency, author = {Kang, Moon Gi and Katsaggelos, Aggelos K}, booktitle = {PROCEEDINGS-SPIE THE INTERNATIONAL SOCIETY FOR OPTICAL ENGINEERING}, doi = {10.1117/12.131413}, editor = {Maragos, Petros}, month = {nov}, organization = {SPIE INTERNATIONAL SOCIETY FOR OPTICAL}, pages = {1414--1424}, title = {{Frequency domain adaptive iterative image restoration and evaluation of the regularization parameter}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=1003398}, year = {1992} }
@inproceedings{brailean1992simultaneous, abstract = {In this paper, we develop a recursive model-based maximum a posteriori (MAP) estimator that simultaneously estimates the displacement vector field (DVF) and intensity field from a noisy-blurred image sequence. Current motion-compensated spatio-temporal filters treat the estimation of the DVF as a preprocessing step. Thereby, no attempt is made to verify the accuracy of these estimates prior to their use in the filter. By simultaneously estimating these two fields, information is made available to each filter regarding the reliability of estimates that they are dependent upon. Nonstationary models are used for the DVF and the intensity field in the proposed estimator, thus avoiding the smoothing of boundaries present in both. Experimental results are provided which show the effectiveness of the proposed recursive model-based MAP estimator.}, author = {Brailean, James C. and Katsaggelos, Aggelos K. and James, C Brailean and Aggelos, K Katsaggelos}, booktitle = {Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics}, doi = {10.1109/ICSMC.1992.271515}, isbn = {0780307208 1062922X , issue = 9}, issn = {1062922X}, organization = {IEEE}, pages = {1574--1579}, title = {{Simultaneous recursive displacement estimation and restoration of image sequences}}, volume = {1992-Janua}, year = {1992} }
@inproceedings{chan1992enhancement, author = {Chan, Cheuk L. and Katsaggelos, Aggelos K. and Sahakian, Alan V.}, booktitle = {Visual Communications and Image Processing '92}, doi = {10.1117/12.131446}, editor = {Maragos, Petros}, isbn = {0819410187}, issn = {0277786X}, month = {nov}, organization = {SPIE INTERNATIONAL SOCIETY FOR OPTICAL}, pages = {290--298}, title = {{Enhancement of low-dosage cine-angiographic image sequences using a modified expectation maximization algorithm}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=1003205}, volume = {1818}, year = {1992} }
@inproceedings{Wenwu1992, abstract = {Multichannel images are the multiple image planes (channels) obtained by imaging the same scene using multiple sensors. The validity of multichannel restoration where both the within and between channel relations are incorporated has already been established using both stochastic and deterministic restoration filters. However, it has been demonstrated that stochastic multichannel filters are extremely sensitive to the estimates of the between channel statistics. In this paper deterministic multichannel filters are proposed that do not utilize any prior knowledge about the multichannel image and the noise. Regularization based on the multichannel Cross-Validation function is used to obtain these filters. Their relation to stochastic multichannel restoration filters is examined and a technique to estimate the variance of the multichannel noise is proposed. Finally, experiments are shown where proposed filters and noise variance estimators are tested using color images.}, author = {Wenwu, Zhu and Nikolas, P Galatsanos and Aggelos, K Katsaggelos and Zhu, Wenwu and Galatsanos, Nikolas P. and Katsaggelos, Aggelos K.}, booktitle = {Visual Communications and Image Processing '92}, doi = {10.1117/12.131452}, editor = {Maragos, Petros}, month = {nov}, pages = {345--356}, title = {{Regularized multichannel restoration of color images using cross-validation}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=1003217}, volume = {1818}, year = {1992} }
@inproceedings{kwak1991motion, author = {Kwak, J. Y. and Efstratiadis, Serafim N. and Katsaggelos, Aggelos K. and Sahakian, Alan V. and Sullivan, Barry J. and Swiryn, Steven and Hueter, David C. and Frohlich, Thomas}, booktitle = {Applications of Optical Engineering: Proceedings of OE/Midwest '90}, doi = {10.1117/12.25776}, editor = {Guzik, Rudolph P. and Eppinger, Hans E. and Gillespie, Richard E. and Dubiel, Mary K. and Pearson, James E.}, month = {mar}, organization = {SPIE}, pages = {32--44}, title = {{Motion estimation in digital angiographic images using skeletons}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=955365}, volume = {1396}, year = {1991} }
@inproceedings{gonzalez1991cross, author = {Gonzalez, H. and Galatsanos, N.P. and Katsaggelos, A.K.}, booktitle = {Proceedings of the Seventh Workshop on Multidimensional Signal Processing}, doi = {10.1109/MDSP.1991.639290}, isbn = {0-7803-0766-6}, organization = {IEEE}, pages = {1.6--1.6}, publisher = {IEEE}, title = {{Cross-validation And Maximum Likelihood Space Varying Regularized Image Restoration}}, url = {http://ieeexplore.ieee.org/document/639290/}, year = {1991} }
@inproceedings{Nikolas1991, abstract = {The problem of multi-channel restoration using both within and between-channel deterministic information is considered. A multi-channel image is a set of image planes that exhibit cross-plane similarity. Existing optimal restoration filters for single-plane images will yield suboptimal results when applied to multi-channel images, since between-channel information is not utilized. Multi-channel least squares restoration filters are developed using two approaches, the set theoretic and the constrained optimization. A geometric interpretation of the estimates of both filters is given. Color images, that is, three-channel imagery with red, green, and blue components, are considered. Constraints that capture the within and between-channel properties of color images are developed. Issues associated with the computation of the two estimates are addressed. Finally, experiments using color images are shown.}, author = {Galatsanos, N.P. and Katsaggelos, A.K. and Chin, R.T. and Hillery, Allen}, booktitle = {[Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing}, doi = {10.1109/ICASSP.1991.150911}, isbn = {0-7803-0003-3}, issn = {07367791}, pages = {2509--2512 vol.4}, publisher = {IEEE}, title = {{Two methods for least squares multi-channel image restoration}}, url = {http://ieeexplore.ieee.org/document/150911/}, volume = {4}, year = {1991} }
@inproceedings{Serafim1991, author = {Efstratiadis, Serafim N. and Huang, Yunming G. and Xiong, Z. and Galatsanos, Nikolas P. and Katsaggelos, Aggelos K.}, booktitle = {Visual Communications and Image Processing '91: Visual Communication}, doi = {10.1117/12.50244}, editor = {Tzou, Kou-Hu and Koga, Toshio}, month = {nov}, pages = {16--25}, title = {{Motion-compensated priority discrete cosine transform coding of image sequences}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=980247}, volume = {1605}, year = {1991} }
@inproceedings{Nikolas1991b, abstract = {The application of regularization to ill-conditioned problems necessitates the choice of a regularizing parameter which trades fidelity to the data for smoothness of the solution. Methods based on the properties of the residuals and on the generalized cross-validation have been proposed for estimating the regularizing parameter. Alternative methods to compute the regularizing parameter are proposed. The resulting values of the regularizing parameter are compared with the values obtained from the above-mentioned methods. Furthermore, it is shown that under certain conditions all the above-mentioned methods result in the same value for the regularizing parameter. Experimental results are presented which verify theoretical results.}, author = {Galatsanos, N.P. and Katsaggelos, A.K.}, booktitle = {[Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing}, doi = {10.1109/ICASSP.1991.151039}, isbn = {0-7803-0003-3}, issn = {07367791}, pages = {3021--3024 vol.4}, publisher = {IEEE}, title = {{Cross-validation and other criteria for estimating the regularizing parameter}}, url = {http://ieeexplore.ieee.org/document/151039/}, volume = {4}, year = {1991} }
@inproceedings{MoonGi1991, author = {{Moon Gi}, Kang and Kuen-Tsair, Lay and Aggelos, K Katsaggelos}, booktitle = {Visual Communications and Image Processing'91: Image Processing}, pages = {408--418}, title = {{Image restoration algorithms based on the bispectrum}}, volume = {1606}, year = {1991} }
@inproceedings{Nikolas1991a, author = {Galatsanos, Nikolas P. and Katsaggelos, Aggelos K.}, booktitle = {Applications of Optical Engineering: Proceedings of OE/Midwest '90}, doi = {10.1117/12.25861}, editor = {Guzik, Rudolph P. and Eppinger, Hans E. and Gillespie, Richard E. and Dubiel, Mary K. and Pearson, James E.}, issn = {0277786X}, month = {mar}, pages = {590--600}, title = {{Properties of different estimates of the regularizing parameter for the least-squares image restoration problem}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=955577}, volume = {1396}, year = {1991} }
@inproceedings{Cheuk1991, author = {Chan, Cheuk L. and Sullivan, Barry J. and Sahakian, Alan V. and Katsaggelos, Aggelos K. and Frohlich, Thomas and Byrom, Ernest}, booktitle = {Biomedical Image Processing II}, doi = {10.1117/12.44297}, editor = {Bovik, Alan C. and Howard, Vyvyan}, month = {jul}, pages = {208--217}, title = {{Spatiotemporal filtering of digital angiographic image sequences corrupted by quantum mottle}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=960887}, volume = {1450}, year = {1991} }
@inproceedings{katsaggelos1991adaptive, author = {Katsaggelos, Aggelos K. and Kleihorst, Richard P. and Efstratiadis, Serafim N. and Lagendijk, Reginald L.}, booktitle = {Visual Communications and Image Processing '91: Image Processing}, doi = {10.1117/12.50407}, editor = {Tzou, Kou-Hu and Koga, Toshio}, isbn = {0819407437}, issn = {0277786X}, month = {nov}, organization = {SPIE}, pages = {716}, title = {{Adaptive image sequence noise filtering methods}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?doi=10.1117/12.50407}, volume = {1606}, year = {1991} }
@inproceedings{chan1990simulation, abstract = {A method is described for the computer simulation of quantum mottle in digital angiographic images obtained through an image intensifier (II) based system. The model corrupts a "perfect" image—one taken at high exposure levels—with Poisson distributed noise to simulate an image obtained through a lower x-ray dose. A mapping scheme is employed which effectively correlates gray level intensities at the image display to photon fluence at the front end of the II. The utility of the noise model is demonstrated by using it to simulate the effect of variable x-ray exposure conditions on an angiographic sequence. Such a sequence is valuable in the development of temporal filtering techniques for digital angiography.}, author = {Chan, Cheuk L. and Sullivan, Barry J. and Sahakian, Alan V. and Katsaggelos, Aggelos K. and Swiryn, Steven and Hueter, David C. and Frohlich, Thomas}, booktitle = {Biomedical Image Processing}, doi = {10.1117/12.19545}, editor = {Bovik, Alan C. and Higgins, William E.}, isbn = {0819402923}, issn = {0277786X}, month = {may}, organization = {SPIE}, pages = {104}, title = {{Simulation of quantum mottle in digital angiographic images}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?doi=10.1117/12.19545}, volume = {1245}, year = {1990} }
@inproceedings{Aggelos1990, author = {Katsaggelos, Aggelos K. and DeRoux, Tomas E. and Marhic, Michel E.}, booktitle = {Visual Communications and Image Processing '90: Fifth in a Series}, doi = {10.1117/12.24157}, editor = {Kunt, Murat}, month = {sep}, pages = {1428--1439}, title = {{Optical methods for iterative image restoration}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=951505}, volume = {1360}, year = {1990} }
@inproceedings{Joon1989, abstract = {Three parallel iterative image restoration algorithms with and without preconditioning are proposed and analyzed . The first algorithm corresponds to a coarse-grained general-purpose multiprocessor computer, the second to a massively parallel computer with synchronization, and the third to a massively parallel computer without synchronization. It is shown that the second and third algorithms can give a speed-up proportional to the number of processors when proper assumptions are satisfied, while the first one performs the best when simulated by a uniprocessor computer.}, author = {Paik, J.K. and Katsaggelos, A.K.}, booktitle = {Proceedings of the 32nd Midwest Symposium on Circuits and Systems}, doi = {10.1109/MWSCAS.1989.101795}, pages = {63--66}, publisher = {IEEE}, title = {{Parallel iterative image restoration algorithms}}, url = {http://ieeexplore.ieee.org/document/101795/}, volume = {28}, year = {1990} }
@inproceedings{sarrafzadeh1990parallel, abstract = {Mesh of pyramids and pyramid of meshes implementations of an iterative image-restoration algorithm are proposed. These implementations are based on a single-step regularized iterative restoration algorithm. Both architectures are described as a composition of a mesh and a pyramid. They are compared in terms of area of the VLSI chip and its computation time.}, author = {Sarrafzadeh, M. and Kumar, S.P.R. and Katsaggelos, A.K.}, booktitle = {IEEE International Symposium on Circuits and Systems}, doi = {10.1109/ISCAS.1990.112542}, issn = {02714310}, organization = {IEEE}, pages = {2605--2608}, publisher = {IEEE}, title = {{Parallel architectures for an iterative image restoration algorithm}}, url = {http://ieeexplore.ieee.org/document/112542/}, volume = {4}, year = {1990} }
@inproceedings{JoonKi1990a, abstract = {A modified Hopfield network model for image restoration is presented. The proposed network does not require zero autoconnections, which is one of the major drawbacks of the Hopfield network. A new number-representation scheme for implementing the proposed network is given. The proposed network with sequential update is shown to converge. The sufficient conditions for convergence of n-simultaneous updates are also given. When the image-restoration problem does not satisfy the convergence conditions, a greedy algorithm which guarantees convergence (at the expense of the image quality) is used.}, author = {Paik, J.K. and Katsaggelos, A.K.}, booktitle = {International Conference on Acoustics, Speech, and Signal Processing}, doi = {10.1109/ICASSP.1990.115873}, issn = {07367791}, pages = {1909--1912}, publisher = {IEEE}, title = {{Image restoration using the Hopfield network with nonzero autoconnection}}, url = {http://ieeexplore.ieee.org/document/115873/}, volume = {4}, year = {1990} }
@inproceedings{JoonKi1990, author = {Paik, J.K. and Katsaggelos, A.K.}, booktitle = {International Conference on Acoustics, Speech, and Signal Processing}, doi = {10.1109/ICASSP.1990.115962}, pages = {2145--2148}, publisher = {IEEE}, title = {{Edge detection using a neural network}}, url = {http://ieeexplore.ieee.org/document/115962/}, year = {1990} }
@inproceedings{Aggelos1990a, author = {Katsaggelos, Aggelos K.}, booktitle = {Visual Communications and Image Processing'90: Fifth in a Series}, doi = {10.1117/12.24152}, editor = {Kunt, Murat}, month = {sep}, pages = {1381--1392}, title = {{Multiple input adaptive image restoration algorithms}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=951494}, volume = {1360}, year = {1990} }
@inproceedings{Serafim1990, author = {Efstratiadis, S.N. and Katsaggelos, A.K.}, booktitle = {International Conference on Acoustics, Speech, and Signal Processing}, doi = {10.1109/ICASSP.1990.115897}, pages = {1973--1976}, publisher = {IEEE}, title = {{A model-based pel-recursive motion estimation algorithm}}, url = {http://ieeexplore.ieee.org/document/115897/}, year = {1990} }
@inproceedings{Serafim1990a, author = {Efstratiadis, Serafim N. and Katsaggelos, Aggelos K.}, booktitle = {Visual Communications and Image Processing '90: Fifth in a Series}, doi = {10.1117/12.35125}, editor = {Kunt, Murat}, month = {sep}, pages = {1222--1231}, title = {{Distributed detection methods for displacement estimation}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=951458}, volume = {1360}, year = {1990} }
@inproceedings{Joon-Ki1990, author = {Paik, Joon-Ki and Katsaggelos, Aggelos K.}, booktitle = {Parallel Architectures for Image Processing}, doi = {10.1117/12.19589}, editor = {Ghosh, Joydeep and Harrison, Colin G.}, month = {jul}, pages = {298--307}, title = {{Parallel and distributed image restoration using a modified Hopfield network}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=939337}, volume = {1246}, year = {1990} }
@inproceedings{katsaggelos1989spatio, author = {Katsaggelos, A. K. and Driessen, J. N. and Efstratiadis, S. N. and Lagendijk, R. L.}, booktitle = {Visual Communications and Image Processing IV}, doi = {10.1117/12.970019}, editor = {Pearlman, William A.}, issn = {1996756X}, month = {nov}, organization = {SPIE}, pages = {61}, title = {{Spatio-Temporal Motion Compensated Noise Filtering Of Image Sequences}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?doi=10.1117/12.970019}, volume = {1199}, year = {1989} }
@inproceedings{lay1988simultaneous, abstract = {This paper deals with simultaneous identification and restoration of images. By identification, we mean the estimation of the parameters characterizing the degradation mechanisms. The original image and the additive noise are assumed to be zero-mean Gaussian random processes. Their autocovariance ma trices are unknown parameters. Blurring is part of the degradation. It is specified by its point spread function, which is also an unknown parameter to be estimated. Maximum likelihood estimation is used to find those unknown parameters. In turn, the EM algorithm is used to find the maximum likelihood estimates. In applying the EM algorithm, the observed image is treated as the incomplete data, which turns out to be a linear transformation of the complete data. Different choices of complete data are investigated. Under the assumption that the image covariance and distortion matrices are circulant, the estimation of the unknown parameters becomes feasible. Explicit iterative expressions are derived for the estimation. The restored image is computed in the E-step of the EM algorithm.}, author = {Katsaggelos, A.K. and Lay, K.T.}, booktitle = {Proceedings. ICCON IEEE International Conference on Control and Applications}, doi = {10.1109/ICCON.1989.770514}, organization = {IEEE}, pages = {236--240}, publisher = {IEEE}, title = {{Simultaneous identification and restoration of images using maximum likelihood estimation}}, url = {http://ieeexplore.ieee.org/document/770514/}, year = {1989} }
@inproceedings{Aggelos1989, abstract = {Mesh and mesh-of-pyramids implementations of iterative image restoration algorithms are proposed. These implementations are based on a single-step algorithm as well as on a multistep iterative algorithm derived from the single step regularized iterative restoration algorithm. One processor is assigned to each picture element, with local memory depending on the support of the restoration filter. The implementations consist of interprocessor communication and intraprocessor computations. The efficiency of the proposed VLSI algorithms is judged by establishing lower bounds on AT2 , where A is the area of the VLSI and T is its computation time.}, author = {Katsaggelos, A.K. and Kumar, S.P.R. and Sarrafzadeh, M.}, booktitle = {International Conference on Acoustics, Speech, and Signal Processing}, doi = {10.1109/ICASSP.1989.266986}, issn = {07367791}, pages = {2544--2547}, publisher = {IEEE}, title = {{Parallel processing architectures for iterative image restoration}}, url = {http://ieeexplore.ieee.org/document/266986/}, volume = {4}, year = {1989} }
@inproceedings{Katsaggelos1989, author = {Katsaggelos, A. K. and Lay, K. T.}, doi = {10.1117/12.970155}, editor = {Pearlman, William A.}, month = {nov}, pages = {1474}, title = {{Simultaneous Blur Identification And Image Restoration Using The EM Algorithm}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?doi=10.1117/12.970155}, year = {1989} }
@inproceedings{Serafim1989, author = {Efstratiadis, Serafim N. and Katsaggelos, Aggelos K.}, booktitle = {Visual Communications and Image Processing IV}, doi = {10.1117/12.970018}, editor = {Pearlman, William A.}, month = {nov}, pages = {51}, title = {{A Multiple-Frame Pel-Recursive Wiener-Based Displacement Estimation Algorithm}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?doi=10.1117/12.970018}, volume = {1199}, year = {1989} }
@inproceedings{katsaggelos1989maximum, abstract = {Summary form only given. Simultaneous iterative identification and restoration have been treated. The image and the noise have been modeled as multivariate Gaussian processes. Maximum-likelihood estimation has been used to estimate the parameters that characterize the Gaussian processes, where the estimation of the conditional mean of the image represents the restored image. Likelihood functions of observed images are highly nonlinear with respect to these parameters. Therefore, it is in general very difficult to maximize them directly. The expectation-maximization (EM) algorithm has been used to find these parameters.}, author = {Katsaggelos, A.K.}, booktitle = {Sixth Multidimensional Signal Processing Workshop}, doi = {10.1109/MDSP.1989.97107}, organization = {IEEE}, pages = {183--184}, publisher = {IEEE}, title = {{Maximum likelihood image identification and restoration based on the EM algorithm}}, url = {http://ieeexplore.ieee.org/document/97107/}, year = {1989} }
@inproceedings{Aggelos1988a, abstract = {Iterative techniques for restoring color images are presented. These iterative algorithms were originally developed for the restoration of monochromatic images. The color images are modeled as three spatially related monochromatic images or channels, and the interchannel correlation is incorporated into the algorithms in an indirect and in a direct way. Experimental results with simulated and real photographically blurred images are presented. Based on present experiments it is concluded that the incorporation of the interchannel correlation in the algorithms does not necessarily improve the quality of the restored images over the algorithms that ignore the interchannel correlation, but they result in considerable computational savings.}, author = {Katsaggelos, A.K. and Paik, J.K.}, booktitle = {ICASSP-88., International Conference on Acoustics, Speech, and Signal Processing}, doi = {10.1109/ICASSP.1988.196768}, issn = {07367791}, pages = {1028--1031}, publisher = {IEEE}, title = {{Iterative color image restoration algorithms}}, url = {http://ieeexplore.ieee.org/document/196768/}, year = {1988} }
@inproceedings{Aggelos1988, abstract = {A class of iterative image-restoration algorithms is derived. The algorithms are based on a representation theorem for the generalized inverse of a matrix. These algorithms exhibit a first or higher order of convergence and some of them consist of an online and an offline computational part. The conditions for convergence and the rate of convergence of these algorithms are derived. An iterative algorithm is also presented which exhibits a higher rate of convergence than the standard quadratic algorithm with no extra computational load. These algorithms can be applied to the restoration of signals of any dimensionality. Iterative restoration algorithms that have appeared in the literature represent special cases of the class of algorithms described. Therefore, the approach presented unifies a large number of iterative restoration algorithms.}, author = {Katsaggelos, A.K. and Efstratiadis, S.N.}, booktitle = {ICASSP-88., International Conference on Acoustics, Speech, and Signal Processing}, doi = {10.1109/ICASSP.1988.196963}, issn = {07367791}, pages = {1774--1777}, publisher = {IEEE}, title = {{A unified approach to iterative signal restoration}}, url = {http://ieeexplore.ieee.org/document/196963/}, year = {1988} }
@inproceedings{Serafim1988, author = {Efstratiadis, Serafim N. and Katsaggelos, Aggelos K.}, booktitle = {Visual Communications and Image Processing '88: Third in a Series}, doi = {10.1117/12.968933}, editor = {Hsing, T. Russell}, issn = {1996756X}, month = {oct}, pages = {10}, title = {{Fast Adaptive Iterative Image Restoration Algorithms}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?doi=10.1117/12.968933}, volume = {1001}, year = {1988} }
@inproceedings{Aggelos1988b, abstract = {The authors concentrate on regularizing the differentiation operation and incorporating it in an edge-detection scheme. They describe a method for differentiation that addresses its susceptibility to noise, using the language of well-posed and ill-posed problems. Both a direct implementation of Miller regularization and one involving projections onto convex sets are considered. Examples are presented that indicate some directions for future efforts.}, author = {Katsaggelos, A.K. and Sullivan, B.J.}, booktitle = {ICASSP-88., International Conference on Acoustics, Speech, and Signal Processing}, doi = {10.1109/ICASSP.1988.196773}, issn = {07367791}, pages = {1048--1051}, publisher = {IEEE}, title = {{Regularized edge detection}}, url = {http://ieeexplore.ieee.org/document/196773/}, year = {1988} }
@inproceedings{Aggelos1987, author = {Aggelos, K Katsaggelos and Paik, J K}, booktitle = {1987 Conf. on Inf. Sciences and Systems, The Johns Hopkins University}, title = {{Iterative Color Image Restoration Algorithms}}, year = {1987} }
@inproceedings{Aggelos1987a, author = {Katsaggelos, Aggelos K.}, booktitle = {Visual Communications and Image Processing II}, doi = {10.1117/12.976502}, editor = {Hsing, T. Russell}, issn = {1996756X}, month = {oct}, pages = {176}, title = {{A Unified Approach To Iterative Image Restoration}}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?doi=10.1117/12.976502}, volume = {0845}, year = {1987} }
@inproceedings{katsaggelos1987multiple, abstract = {Image-restoration applications where multiple distorted versions of the same original image are available are considered. A general adaptive iterative restoration algorithm is derived based on regularization techniques. The adaptivity of the algorithm is introduced in two ways: a) by a constraint operator which incorporates properties of the response of the human visual system into the restoration process, and b) by a weight matrix which assigns greater importance for the deconvolution process to areas of high spatial activity than to areas of low spatial activity. Different degrees of trust are assigned to the various distorted images, depending on the amount of noise on each image. The proposed algorithms are general and can be used for any type of linear distortion and constraint operators. It can also be used to restore signals other than images.}, author = {Katsaggelos, A.}, booktitle = {ICASSP '87. IEEE International Conference on Acoustics, Speech, and Signal Processing}, doi = {10.1109/ICASSP.1987.1169806}, issn = {07367791}, organization = {IEEE}, pages = {1179--1182}, publisher = {Institute of Electrical and Electronics Engineers}, title = {{Multiple input adaptive iterative image restoration algorithms}}, url = {http://ieeexplore.ieee.org/document/1169806/}, volume = {12}, year = {1987} }
@inproceedings{Aggelos1986a, abstract = {In this paper the general form of adaptive image restoration algorithms is derived. The adaptivity of the algorithm is introduced by the constraint operator which incorporates properties of the response of the human visual system. The properties of the visual system are represented by noise masking and visibility functions. Based on the values of the visibility function the image is divided into classes with similar spatial activity. Then, a regularization technique with a different regularization parameter is applied to each class. The proposed algorithms are general and can be used for any type of linear constraint and distortion operators. The algorithms can also be used to restore signals different than images, since the constraint operator can be interpreted as adapting to the local signal activity.}, author = {Katsaggelos, Aggelos K.}, booktitle = {Proceedings of the Twentieth Conference on Information Sciences and Systems}, pages = {42--46}, title = {{General Formulation of Adaptive Iterative Image Restoration Algorithms.}}, year = {1986} }
@inproceedings{Aggelos1986, abstract = {A synchronous VLSI implementation of an iterative image restoration algorithm is described. The implementation is based on a multistep iterative algorithm derived from the single-step regularized iterative restoration algorithm. One processor is assigned to each picture element, with local memory depending on the support of the restoration filter. Working details of the implementation, which consists of interprocessor communication and intraprocessor computations, are provided.}, author = {Katsaggelos, A. K. and Kumar, S. P.R. and Samatham, M. R.}, pages = {313--318}, title = {{Vlsi Implementation of an Iterative Image Restoration Algorithm.}}, year = {1986} }
@inproceedings{katsaggelos1985nonstationary, abstract = {Different types of nonstationary constrained iterative image restoration algorithms are introduced. The adaptivity of the algorithm is introduced by the constraint operator, which incorporates properties of the response of the human visual system. The properties of the visual system are represented by noise masking and visibility functions. A new way of computing the masking function is also introduced. The proposed algorithms are general and can be used for any type of linear constraint and distortion operators. The algorithms can also be used to restore signals different from images, since the constraint operator can be interpreted as adapting to the local signal activity.}, author = {Katsaggelos, A. and Biemond, J. and Mersereau, R. and Schafer, R.}, booktitle = {ICASSP '85. IEEE International Conference on Acoustics, Speech, and Signal Processing}, doi = {10.1109/ICASSP.1985.1168355}, issn = {07367791}, organization = {IEEE}, pages = {696--699}, publisher = {Institute of Electrical and Electronics Engineers}, title = {{Nonstationary iterative image restoration}}, url = {http://ieeexplore.ieee.org/document/1168355/}, volume = {10}, year = {1985} }
@inproceedings{katsaggelos1985general, abstract = {A general formulation of constrained iterative restoration algorithms is introduced in which deterministic and/or statistical information about the undistorted signal and statistical information about the noises are directly incorporated into the iterative procedure. This a priori information is incorporated into the restoration algorithm by what is called 'soft' or statistical constraints. Their effect on the solution depends on the amount of noise on the data; that is, the constraint operator is 'turned off' for noiseless data. The development of the new iterative algorithm is based on results from regularization techniques for stabilizing ill-posed problems.}, author = {Katsaggelos, A. and Biemond, J. and Mersereau, R. and Schafer, R.}, booktitle = {ICASSP '85. IEEE International Conference on Acoustics, Speech, and Signal Processing}, doi = {10.1109/ICASSP.1985.1168356}, issn = {07367791}, organization = {IEEE}, pages = {700--703}, publisher = {Institute of Electrical and Electronics Engineers}, title = {{A general formulation of constrained iterative restoration algorithms}}, url = {http://ieeexplore.ieee.org/document/1168356/}, volume = {10}, year = {1985} }
@inproceedings{katsaggelos1983iterative, author = {Katsaggelos, A. and Schafer, R.}, booktitle = {ICASSP '83. IEEE International Conference on Acoustics, Speech, and Signal Processing}, doi = {10.1109/ICASSP.1983.1172115}, issn = {07367791}, organization = {IEEE}, pages = {659--662}, publisher = {Institute of Electrical and Electronics Engineers}, title = {{Iterative deconvolution using several different distorted versions of an unknown signal}}, url = {http://ieeexplore.ieee.org/document/1172115/}, volume = {8}, year = {1983} }
@misc{Emeline, author = {Pouyet, Emeline and Chopp, Henry and Cossairt, Oliver and Dai, Qiqin and Katsaggelos, Aggelos and Walton, Marc}, title = {{Innovative Strategies for the use of in-situ and SR-based X-ray Techniques to Reveal Artistic Technology and Relight History}}, year = {2023} }
@misc{Tassos2022, author = {Fragos, Tassos and Andrews, Jeff J and Bavera, Simone S and Berry, Christopher P L and Coughlin, Scott and Dotter, Aaron and Giri, Prabin and Kalogera, Vicky and Katsaggelos, Aggelos and Kovlakas, Konstantinos and Others}, booktitle = {Astrophysics Source Code Library}, keywords = {2022ascl.soft10019F}, mendeley-tags = {2022ascl.soft10019F}, pages = {ascl----2210}, title = {{POSYDON: Single and binary star population synthesis code}}, url = {http://ascl.net/2210.019}, year = {2022} }
@misc{Zevin2021, author = {Zevin, M. and Coughlin, S. and Bahaadini, S. and Besler, E. and Rohani, N. and Allen, S. and Cabero, M. and Crowston, K. and Katsaggelos, A. K. and Larson, S. L. and Lee, T. K. and Lintott, C. and Littenberg, T. B. and Lundgren, A. and {\O}sterlund, C and Smith, J. R. and Trouille, L. and Kalogera, V.}, doi = {https://doi.org/10.5281/zenodo.5911227}, title = {{Gravity Spy machine learning classifications of LIGO glitches from observing runs O1, O2, O3a, and O3b}}, year = {2021} }
@misc{villena2015superresolution, author = {Villena, S. and Vega, M. and Babacan, D. and Mateos, J. and Molina, R. and Katsaggelos, A. K.}, booktitle = {Decsai.Ugr.Es}, pages = {1--17}, publisher = {Academic}, title = {{Superresolution software manual}}, url = {http://decsai.ugr.es/pi/superresolution/manual.pdf}, year = {2015} }
@misc{Abhishek, abstract = {The ongoing MPEG standardization of Compact Descriptors for Visual Search (CDVS) focuses on image search for mobile applications and in that process, the extraction of local descriptors constitutes an important step. These local descriptors extracted from an image are further aggregated into global descriptors that are used for efficient retrieval of matching images from a database for a given query image. Current CDVS Test Model (TM) implements the global descriptor using the uncompressed Scale Invariant Feature Transform (SIFT) points. At the mobile devices, the global descriptor (GD) is computed as the quantized Fisher Vector of up to 300 SIFT points w.r.t a SIFT space Gaussian Mixture Model (GMM). It is noted that such an approach requires significant overhead in communication to transmit the global descriptor, especially at low bit rate. Hence, we propose an alternative and efficient way to re-construct the global descriptor from the local descriptors at the server side. The difference between the reconstructed GD and the original GD, are then selectively coded to strike a balance between bit rate cost and performance. The experiments on CDVS datasets shows around 0.5% increase in true positive rate and 1% decrease in false positive rate.}, author = {Nagar, Abhishek and Srivastava, Gaurav and Fernandes, Felix C A and Katsaggelos, Aggelos K}, doi = {10.1.1.460.7607}, title = {{A Novel Differential Coding Scheme for a Compact Image Descriptor with applications to Mobile Visual Search}}, url = {http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.460.7607&rep=rep1&type=pdf}, year = {2014} }
@misc{Aggelos2013a, author = {Katsaggelos, Aggelos K}, title = {{Pre-and Post-Processing for Video Compression}}, url = {https://technodocbox.com/Entertainment/67798407-Pre-and-post-processing-for-video-compression.html}, year = {2013} }
@misc{Aggelos2010, author = {Soyak, Eren and Tsaftaris, Sotirios A. and Katsaggelos, Aggelos K.}, title = {{iTRAC: Intelligent Video Compression for Automated Trac Surveillance Systems}}, url = {https://rosap.ntl.bts.gov/view/dot/18506}, year = {2010} }
@misc{Byrav2009, author = {Byrav, Ramamurthy and Aggelos, K Katsaggelos}, booktitle = {2009 Proceedings of 18th International Conference on Computer Communications and Networks}, doi = {10.1109/ICCCN.2009.5235412}, month = {aug}, pages = {i--i}, publisher = {IEEE}, title = {{ICCCN 2009 Message from General Chairs}}, url = {http://ieeexplore.ieee.org/document/5235412/}, year = {2009} }
@misc{Fan2009c, abstract = {In this paper we modify our unsupervised anomaly detection algorithm [1,2] and apply it to highway traffic anomaly analysis. We propose a method to identify anomalies under a prob-abilistic framework. Instead of determining anomalies based on the size of each cluster, they are determined in a prob-abilistic framework. Moreover, we present our findings on using different features when analyzing real highway vehicle trajectory data. Based on real highway traffic video data we demonstrate that the inclusion of certain features, brings us closer to identifying events that are both anomalous and abnormal (based on driving rules).}, author = {Jiang, F and Tsaftaris, SA and Wu, Y and Katsaggelos, AK}, booktitle = {CCITT Northwestern University}, title = {{Detecting anomalous trajectories from highway traffic data}}, url = {http://ccitt.northwestern.edu/documents/2009.Jiang_Tsaftaris_Wu_Katsaggelos_pub.pdf}, year = {2009} }
@misc{Rolf2006, author = {Haller, Rolf and Merz, Roger and Schuster, Prof Guido M}, title = {{Fast Motion Compensated Framerate Upsampling}}, url = {https://ivpl.northwestern.edu/wp-content/uploads/2019/02/RH-2006.pdf}, year = {2006} }
@misc{Zhu2003a, author = {Li, Zhu and Katsaggelos, Aggelos and Gandhi, Bhavan}, title = {{Optimal Video Summary Generation and Encoding}}, url = {https://www.academia.edu/2704619/OPTIMAL_VIDEO_SUMMARY_GENERATION_AND_ENCODING}, year = {2003} }
@misc{katsaggelos19993d, author = {Katsaggelos, A.K.}, booktitle = {IEEE Signal Processing Magazine}, doi = {10.1109/MSP.1999.752036}, issn = {1053-5888}, month = {mar}, number = {2}, pages = {2--7}, publisher = {IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC 445 HOES LANE, PISCATAWAY, NJ$\sim${\ldots}}, title = {{From the Editor}}, url = {http://ieeexplore.ieee.org/document/752036/}, volume = {16}, year = {1999} }
@misc{katsaggelos19993d, author = {Katsaggelos, A.K.}, booktitle = {IEEE Signal Processing Magazine}, doi = {10.1109/MSP.1999.752036}, issn = {1053-5888}, month = {mar}, number = {2}, pages = {2--7}, publisher = {IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC 445 HOES LANE, PISCATAWAY, NJ$\sim${\ldots}}, title = {{From the Editor}}, url = {http://ieeexplore.ieee.org/document/752036/}, volume = {16}, year = {1999} }
@misc{Gerry, author = {Melnikov, Gerry and Katsaggelos, Aggelos K}, title = {{On the Minimum Maximum Criterion in Lossy Data Compression}}, url = {https://www.researchgate.net/publication/228814197_On_the_Minimum_Maximum_Criterion_in_Lossy_Data_Compression}, year = {1998} }
@misc{A1998, author = {A, K Katsaggelos and J, Mateos}, booktitle = {Data Analysis In Astronomy: Proceedings Of The Fifth Workshop}, pages = {289}, title = {{Departamento de Ciencias de la Computaci{\'{o}}n e Inteligencia Artificial}}, year = {1998} }
@misc{Hu1997, abstract = {The 50th anniversary celebration of the IEEE Signal Processing Society begins with the July issue of IEEE Signal Processing Magazine. In this issue, the first of nine articles presented by the society's nine technical committees is presented. The contributions in this article include: integrated media systems; media integration; audio-visual interaction; multimodal perceptual quality; networked multimedia; data hiding; neural networks for intelligent multimedia processing; content-based indexing and retrieval of visual information; media processors; and speech, audio and acoustic processing.}, author = {{Yu Hen Hu} and Katsaggelos, Agggelos K and Kung, S. Y. and Hu, Yu Hen and Katsaggelos, Agggelos K and Kung, S. Y.}, booktitle = {IEEE Signal Processing Magazine}, chapter = {28}, doi = {10.1109/MSP.1997.598582}, isbn = {1053-5888}, issn = {1053-5888}, month = {jul}, number = {4}, pages = {28--28}, title = {{50th Anniversary Celebration Chair's Message [The Past, Present, and Future of Multimedia Signal Processing]}}, url = {http://ieeexplore.ieee.org/document/598582/}, volume = {14}, year = {1997} }
@misc{Aggelos1994b, author = {Aggelos, K Katsaggelos}, booktitle = {Proceedings of Visual Communications and Image Processing Conference}, title = {{Proceedings of Visual Communications and Image Processing Conference}}, year = {1994} }
@phdthesis{Zihao2020, abstract = {Computational imaging (CI) is a class of imaging systems that optimize both the opto-electronic hardware and computing software to achieve task-specific improvements. Machine/deep learning models have proven effective in drawing statistical priors from adequate datasets. Yet when designing computational models for CI problems, physics-based models derived from the image formation process (IFP) can be well incorporated into learning-based architectures. In this thesis, we propose a group of synergistic models (synergy between physics-based and learning-based models) and apply such models in several CI tasks. The core idea is to derive differentiable imaging models to approximate the IFP, enabling automatic differentiation and integration into learning-based models. We demonstrate two synergistic models with the use of differentiable imaging models. The first synergistic model combines a differentiable model with residual learning for high frame-rate video frame synthesis based on event cameras. The second one integrates a light transport model with an autoencoder for 3D holographic display design. Additionally, we demonstrate two other synergistic strategies without differentiable imaging models. In solving privacy preserving action recognition task using coded aperture videos, we show that extracting motion features derived from the IFP can improve the performance of deep classifiers. In an on-chip holographic microscopy task, to achieve space-time super resolution, we use sparsely-coded bi-level dictionary for hologram super resolution followed by a phase retrieval algorithm for 3D localization.}, author = {Wang, Zihao}, booktitle = {ProQuest Dissertations and Theses}, isbn = {9798672158341}, keywords = {0752:Optics,0984:Computer science,Computational imaging,Computer science,Event-based vision,Holographic 3D display,Machine learning,Optics}, pages = {182}, title = {{Synergy of Physics and Learning-Based Models in Computational Imaging and Display}}, url = {https://search.proquest.com/dissertations-theses/synergy-physics-learning-based-models/docview/2447509037/se-2?accountid=8058%0Ahttp://eu.alma.exlibrisgroup.com/view/uresolver/44SAL_INST/openurl?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:dissert}, year = {2020} }
@phdthesis{AggelosKonstantinos1985, author = {Katsaggelos, A. K.}, doi = {https://dl.acm.org/doi/book/10.5555/912495}, title = {{Constrained iterative image restoration algorithms}}, url = {https://www.proquest.com/docview/303370506?pq-origsite=gscholar&fromopenview=true#}, year = {1985} }
@unpublished{Kuan2022, annote = {US Patent 11,340,057}, author = {He, Kuan and Cossairt, Oliver Strider and Katsaggelos, Aggelos K and Scherer, Norbert and Hereld, Mark}, title = {{Systems and methods for interferometric multifocus microscopy}}, url = {https://patents.google.com/patent/WO2019246478A1/en?inventor=Katsaggelos&num=100&oq=Katsaggelos&sort=old}, year = {2022} }
@unpublished{OliverStrider2022, annote = {US Patent 11,303,793}, author = {Cossairt, Oliver Strider and Shi, Boxin and Wang, Zihao and Duan, Peiqi and Katsaggelos, Aggelos K and Huang, Tiejun}, title = {{System and method for high-resolution, high-speed, and noise-robust imaging}}, url = {https://patents.google.com/patent/US11303793B2/en?inventor=Katsaggelos&num=100&oq=Katsaggelos&sort=old}, year = {2022} }
@unpublished{Nabil2022, annote = {US Patent 11,222,422}, author = {Alshurafa, Nabil I and Katsaggelos, Aggelos K and Cossairt, Oliver Strider}, title = {{Hyperspectral imaging sensor}}, url = {https://patents.google.com/patent/US11222422B2/en?inventor=Katsaggelos&num=100&oq=Katsaggelos&sort=old}, year = {2022} }
@unpublished{Srutarshi2022, annote = {US Patent App. 17/462,423}, author = {Banerjee, Srutarshi and Chopp, Henry H and P{\'{e}}rez, Juan Gabriel Serra and Wang, Zihao and Cossairt, Oliver Strider and Katsaggelos, Aggelos K}, title = {{Bandwidth limited context based adaptive acquisition of video frames and events for user defined tasks}}, year = {2022} }
@unpublished{AlexanderHans2022, annote = {US Patent App. 17/302,718}, author = {Vija, Alexander Hans and Rodrigues, Miesher and Banerjee, Srutarshi and Katsaggelos, Aggelos}, title = {{Enhancement of weak signal for machine training neural network representing a solid-state detector}}, url = {https://patents.google.com/patent/US20220366232A1/en?inventor=Katsaggelos&num=100&oq=Katsaggelos&sort=old}, year = {2022} }
@unpublished{Reuven2020, abstract = {Using a plurality of distinct behavioral tasks conducted in a functional magnetic resonance imaging (fMRI) scanner, fMRI data acquired from one or more subjects performing working memory tasks can be used for diagnosing psychi atrics and neurological disorders. A classification algorithm can be used to determine a classification model, tune the model, and apply the model. An output indicative of a Subject's clinical condition can then be provided and used to diagnose new cases.}, annote = {US Patent 10,571,539}, author = {Hammer, Rubi and Booth, James R and Borhani, Reza and Katsaggelos, Aggelos K}, title = {{Pattern analysis based on fMRI data collected while subjects perform working memory tasks allowing high-precision diagnosis of ADHD.}}, url = {https://patents.google.com/patent/US20170123028A1/en?inventor=Katsaggelos&num=100&oq=Katsaggelos&sort=old}, year = {2020} }
@unpublished{Armin2020, annote = {From Duplicate 1 (Visual inspection system for automated detection of particulate matter in flexible medical containers - Armin, Kappeler; Aggelos, K Katsaggelos; Georgios Andrea, Bertos; Kirk Andrew, Ashline; Neal Anthony, Zupec) US Patent 10,878,551 From Duplicate 2 (Visual inspection system for automated detection of particulate matter in flexible medical containers - Kappeler, Armin; Katsaggelos, Aggelos K; Bertos, Georgios Andrea; Ashline, Kirk Andrew; Zupec, Neal Anthony) US Patent App. 17/132,812}, author = {Kappeler, Armin and Katsaggelos, Aggelos K and Bertos, Georgios Andrea and Ashline, Kirk Andrew and Zupec, Neal Anthony and Armin, Kappeler and Aggelos, K Katsaggelos and {Georgios Andrea}, Bertos and {Kirk Andrew}, Ashline and {Neal Anthony}, Zupec}, title = {{Visual inspection system for automated detection of particulate matter in flexible medical containers}}, url = {https://patents.google.com/patent/US20150213616A1/en?inventor=Katsaggelos&num=100&oq=Katsaggelos&sort=old}, year = {2020} }
@unpublished{xin2018system, annote = {US Patent 9,875,386}, author = {Xin, Xin and Li, Zhu and Katsaggelos, Aggelos K}, title = {{System and method for randomized point set geometry verification for image identification}}, url = {https://patents.google.com/patent/US9875386B2/en?inventor=Katsaggelos&num=100&oq=Katsaggelos&sort=old}, year = {2018} }
@unpublished{xin2015scalable, annote = {US Patent 8,948,518}, author = {Xin, Xin and Li, Zhu and Katsaggelos, Aggelos K}, title = {{Scalable query for visual search}}, url = {https://patents.google.com/patent/US20130142439A1/en?inventor=Katsaggelos&num=100&oq=Katsaggelos&sort=old}, year = {2015} }
@unpublished{Zhu2014, annote = {US Patent 8,718,378}, author = {Li, Z and Xin, X and Katsaggelos, AK}, booktitle = {US Patent 8,718,378}, title = {{Image topological coding for visual search}}, url = {https://www.google.com/patents/US8718378}, year = {2014} }
@unpublished{xin2014system, annote = {US Patent 8,755,605}, author = {Xin, Xin and Li, Zhu and Katsaggelos, Aggelos K}, title = {{System and method for compact descriptor for visual search}}, url = {https://patents.google.com/patent/US20130016908A1/en?inventor=Katsaggelos&num=100&oq=Katsaggelos&sort=old}, year = {2014} }
@unpublished{Aggelos2012, author = {Katsaggelos, Aggelos}, title = {{Method And System For Scalable Bitstreme Extraction}}, year = {2012} }
@unpublished{Serhan2011, annote = {US Patent App. 12/795,232}, author = {Serhan, Uslubas and Aggelos, K Katsaggelos and Faisal, Ishtiaq and Shih-Ta, Hsiang and Ehsan, Maani}, title = {{Digital image compression by resolution-adaptive macroblock coding}}, year = {2011} }
@unpublished{Serhan2011a, annote = {US Patent App. 12/795,200}, author = {Uslubas, Serhan and Katsaggelos, Aggelos K and Ishtiaq, Faisal and Hsiang, Shih-Ta and Maani, Ehsan}, title = {{Digital image compression by residual decimation}}, year = {2011} }
@unpublished{Martin2010b, abstract = {A system and a method perform frame interpolation for a compressed video bitstream. The system and the method may combine candidate pictures to generate an interpolated video picture inserted between two original video pictures. The system and the method may generate the candidate pictures from different motion fields. The candidate pictures may be generated partially or wholly from motion vectors extracted from the compressed video bitstream. The system and the method may reduce computation required for interpolation of video frames without a negative impact on visual quality of a video sequence.}, annote = {US Patent App. 12/658,470}, author = {Luessi, Martin and Katsaggelos, Aggelos and Veselinovic, Dusan and Lengwehasatit, Krisda and Kosmach, James J}, title = {{System and method for frame interpolation for a compressed video bitstream}}, url = {https://patents.google.com/patent/US20100201870A1/en?q=(%22System+and+method+for+frame+interpolation+for+a+compressed+video+bitstream%22)&oq=%22System+and+method+for+frame+interpolation+for+a+compressed+video+bitstream%22}, year = {2010} }
@unpublished{Faisal2010, annote = {US Patent App. 12/575,156}, author = {Ishtiaq, Faisal and Hsiang, Shih-Ta and Katsaggelos, Aggelos K and Maani, Ehsan and Uslubas, Serhan}, title = {{System and method of optimized bit extraction for scalable video coding}}, year = {2010} }
@unpublished{Mark2012, abstract = {A scalable video compression system (100) having an encoder (120), bit extractor (140), and decoder (160) for efficiently encoding and decoding a scalable embedded bitstream (130) at different video resolution, framerate, and video quality levels is provided. Bits can be extracted in order of refinement layer (136), followed by temporal level (132), followed by spatial layer (134), wherein each bit extracted provides an incremental improvement in video decoding quality. Bit extraction can be truncated at a position in the embedded bitstream corresponding to a maximum refinement layer, a maximum temporal level, and a maximum spatial layer. For a given refinement layer, bits are extracted from all spatial layers in a lower temporal level prior to extracting bits from spatial layers in a higher temporal level for prioritizing coding gain to increase video decoding quality, and prior to moving to a next refinement layer.}, annote = {US Patent 8,170,094 EU patent EP2084907B1}, author = {Trandel, Mark R. and Katsaggelos, Aggelos. K. and Babacan, Sevket D. and Hsiang, Shih-Ta and Ishtiaq, Faisal}, title = {{Method and system for scalable bitstream extraction}}, url = {https://patents.google.com/patent/US8170094B2/en?oq=US+Patent+8%2C170%2C094 https://patents.google.com/patent/EP2084907B1/en?q=(%22Method+And+System+For+Scalable+Bitstream+Extraction%22)&oq=%22Method+And+System+For+Scalable+Bitstream+Extraction%22}, year = {2007} }
@unpublished{Faisal2006, annote = {US Patent 6,996,172}, author = {Ishtiaq, Faisal and Katsaggelos, Aggelos K}, title = {{Method and structure for scalability type selection in digital video}}, url = {https://patents.google.com/patent/US6996172B2/en?inventor=Katsaggelos&num=100&oq=Katsaggelos&sort=old}, year = {2006} }
@unpublished{Zhu2005db, abstract = {Procede et appareil pour reduire un contenu visuel Verfahren und vorrichtung zur verringerung von visuellem inhalt}, annote = {EU Patent EP1576539A3}, author = {Zhu, Li and Bhavan, Gandhi and Aggelos, K Katsaggelos}, title = {{Method and apparatus for reduction of visual content EP1576539A3}}, url = {https://patents.google.com/patent/EP1576539A3/en?inventor=Katsaggelos&num=100&oq=Katsaggelos&sort=old}, year = {2005} }
@unpublished{Zhu2005d, annote = {US Patent 6,963,378}, author = {Zhu, Li and Bhavan, Gandhi and Aggelos, K Katsaggelos}, title = {{Method and apparatus for reduction of visual content}}, url = {https://patents.google.com/patent/US6963378B2/en?inventor=Katsaggelos&num=100&oq=Katsaggelos&sort=old}, year = {2005} }
@unpublished{Zhu2005e, annote = {US Patent App. 10/990,583}, author = {Zhu, Li and Bhavan, Gandhi and Aggelos, Katsaggelos}, title = {{Method and apparatus for characterizing a video segment and determining if a first video segment matches a second video segment}}, url = {https://patents.google.com/patent/US20050125821A1/en?inventor=Katsaggelos&num=100&oq=Katsaggelos&sort=old}, year = {2005} }
@unpublished{Damon2005, annote = {US Patent US20050057670A1}, author = {Damon, Tull and Aggelos, Katsaggelos}, title = {{Method and device for extracting and utilizing additional scene and image formation data for digital image and video processing}}, url = {https://patents.google.com/patent/US20050057670A1/en?inventor=Katsaggelos&num=100&oq=Katsaggelos&sort=old}, year = {2005} }
@unpublished{Mark1998, annote = {US Patent 5,764,921}, author = {Mark, R Banham and James, C Brailean and Stephen, N Levine and Aggelos, K Katsaggelos and Guido, M Schuster}, title = {{Method, device and microprocessor for selectively compressing video frames of a motion compensated prediction-based video codec}}, url = {https://patents.google.com/patent/US5764921A/en?oq=US+Patent+5%2C764%2C921}, year = {1998} }
@unpublished{Taner1998, annote = {US Patent 5,764,307}, author = {Taner, Ozcelik and James, C Brailean and Aggelos, K Katsaggelos and Ozan, Erdogan and Cheung, Auyeung}, title = {{Method and apparatus for spatially adaptive filtering for video encoding}}, url = {https://patents.google.com/patent/US5764307A/en?q=(%22Method+and+apparatus+for+spatially+adaptive+filtering+for+video+encoding%22)&oq=%22Method+and+apparatus+for+spatially+adaptive+filtering+for+video+encoding%22}, year = {1998} }
@unpublished{James1998b, annote = {AU Patent AU682135C}, author = {James, C Brailean and Taner, Ozcelik and Aggelos, K Katsaggelos}, title = {{Method and system for estimating motion within a video sequence AU682135C}}, url = {https://patents.google.com/patent/AU682135C/en?inventor=Katsaggelos&num=100&oq=Katsaggelos&sort=old}, year = {1998} }
@unpublished{James1998, annote = {US Patent 5,717,463}, author = {James, C Brailean and Taner, Ozcelik and Aggelos, K Katsaggelos}, title = {{Method and system for estimating motion within a video sequence}}, url = {https://patents.google.com/patent/US5717463A/en?q=(%22Method+and+system+for+estimating+motion+within+a+video+sequence%22)&oq=%22Method+and+system+for+estimating+motion+within+a+video+sequence%22}, year = {1998} }
@unpublished{robers, annote = {WO1998053613A1}, author = {{Marshall A. Robers Mark R. Banham}, Aggelos K Katsaggelos}, title = {{Apparatus, method and computer readable medium for scalable coding of video information }}, url = {https://patents.google.com/patent/WO1998053613A1/en?inventor=Katsaggelos&num=100&oq=Katsaggelos&sort=old}, year = {1998} }
@unpublished{Guido1998a, annote = {US Patent 5,778,192}, author = {Guido, M Schuster and Aggelos, Katsaggelos and Mark, R Banham and James, C Brailean}, title = {{Method and device for optimal bit allocation between different sources of information in digital video compression}}, url = {https://patents.google.com/patent/US5778192A/en?q=(%22Method+and+device+for+optimal+bit+allocation+between+different+sources+of+information+in+digital+video+compression%22)&oq=%22Method+and+device+for+optimal+bit+allocation+between+different+sources+of+in}, year = {1998} }
@unpublished{banhamjames, annote = {EU Patent EP0800684A1}, author = {Banham, Mark R and Brailean, James C and Levine, Stephen N and O'connell, Kevin J and Katsaggelos, Aggelos K}, title = {{Method and device for encoding/decoding a displaced frame difference}}, url = {https://patents.google.com/patent/EP0800684A1/en?inventor=Katsaggelos&num=100&oq=Katsaggelos&sort=old}, year = {1997} }
@unpublished{Taner1997a, annote = {US Patent 5,612,745}, author = {Taner, Ozcelik and James, C Brailean and Aggelos, K Katsaggelos}, title = {{Method and apparatus for detecting occlusion}}, url = {https://patents.google.com/patent/US5612745A/en?oq=US+Patent+5%2C612%2C745}, year = {1997} }
@unpublished{Taner1997, annote = {US Patent 5,646,867}, author = {Taner, Ozcelik and James, C Brailean and Aggelos, K Katsaggelos and Stephen, N Levine}, title = {{Method and system for improved motion compensation}}, url = {https://patents.google.com/patent/US5646867A/en?oq=US+Patent+5%2C646%2C867}, year = {1997} }
@unpublished{Taner1996b, annote = {AU Patent AU681324C}, author = {Ozcelik, Taner and Brailean, James C and Katsaggelos, Aggelos K}, title = {{Method and apparatus for regenerating a dense motion vector field AU681324C}}, url = {https://patents.google.com/patent/AU681324C/en?inventor=Katsaggelos&num=100&oq=Katsaggelos&sort=old}, year = {1996} }
@unpublished{Taner1996, annote = {US Patent 5,574,663}, author = {Ozcelik, Taner and Brailean, James C and Katsaggelos, Aggelos K}, title = {{Method and apparatus for regenerating a dense motion vector field}}, url = {https://patents.google.com/patent/US5574663A/en?oq=US+Patent+5%2C574%2C663}, year = {1996} }