ICIAR 2006 - Plenary Talks

Plenary Talks

Ling Guan
Professor, Canada Research Chair in Multimedia
Electrical and Computer Engineering
Ryerson University, Canada
http://www.ee.ryerson.ca/people/Guan.html
Title: Self-Organizing Trees and Forests: A Powerful Tool in Pattern Clustering and Recognition

Abstract »

As the fruit of the Information Age comes to bare, the question of how such information, especially visual information, might be effectively harvested, archived and analyzed, remains a monumental challenge facing today�s research community. The processing of such information, however, is often fraught with the need for conceptual interpretation: a relatively simple task for humans, yet arduous for computers. In attempting to handle oppressive volumes of visual information becoming readily accessible within consumer and industrial sectors, some level of automation remains a highly desired goal.

To achieve such a goal requires computational systems that exhibit some degree of intelligence in terms of being able to formulate their own models of the data in question with little or no user intervention � a process popularly referred to as Pattern Clustering or Unsupervised Pattern Classification. One powerful tool in pattern clustering is the computational technologies based on principles of Self-Organization.

In this talk, we explore a new family of computing architectures that have a basis in self organization, yet are somewhat free from many of the constraints typical of other well known self-organizing architectures. Within this family, the basic processing unit is known as the Self-Organizing Tree Map (SOTM), and the most sophisticated is the Self-Organizing Forest (SOF) which consists of numerous conceptually linked trees. We will look at how this model has evolved since its inception in 1995, how it has inspired new models, and how it is being applied to complex pattern clustering problems in image filtering, image/video retrieval and 3-D image analysis.

Bio »

Ling Guan received his Bachelor Degree in Electronic Engineering from Tianjin University, China in 1982, Masters Degree in Systems Design Engineering at University of Waterloo, Canada in 1985, and Ph.D. Degree in Electrical Engineering from University of British Columbia, Canada in 1989. From 1993 to 2000, he was on the Faculty of Engineering at the University of Sydney, Australia. Since May 2001, he has been a professor in Electrical and Computer Engineering at Ryerson University, Canada. In November 2001, He was appointed to the position of Tier I Canada Research Chair in Multimedia. He is the recipient of numerous awards, including a Senior Fellowship from Australian Academy of Science/Japan Society for the Promotion of Science in 2002, and IEEE Transactions on Circuits and Systems for Video Technology Best Paper Award in 2005. He held visiting positions at British Telecom (1994), Tokyo Institute of Technology (1999), Princeton University (2000) and Microsoft Research Asia (2002). Dr. Guan has authored/co-authored more than 200 scientific articles and three books in multimedia processing and communications, computer vision, machine learning, and adaptive image/signal processing. He has served as associate editor/guest editor of numerous international journals, including Proceedings of the IEEE. Currently he is on the editorial boards of IEEE Signal Processing Magazine, IEEE Computational Intelligence Magazine, IEEE Transactions on Circuits and Systems for Video Technology and IEEE Transactions on Neural Networks. He was the Founding General Chair of IEEE Pacific-Rim Conference on Multimedia, and currently serves as the General Chair of 2006 IEEE International Conference on Multimedia and Expo to be held in Toronto, Canada.
B. John Oommen
Professor, Fellow of the IEEE, Fellow of the IAPR
School of Computer Science
Carleton University, Canada
http://www.scs.carleton.ca/~oommen/
Title: On Using Prototype Reduction Schemes to Optimize Dissimilarity-Based Classification

Abstract »

The aim of this talk is to present a strategy by which a new philosophy for pattern classification, namely that pertaining to Dissimilarity-Based Classifiers (DBCs), can be efficiently implemented. This methodology, proposed by Duin and his co-authors, is a way of defining classifiers between the classes, and is not based on the feature measurements of the individual patterns, but rather on a suitable dissimilarity measure between them. The advantage of this methodology is that since it does not operate on the class-conditional distributions, the accuracy can exceed the Bayes� bound and actually attempt to attain the zero-error bound. The problem with this strategy is, however, the need to compute, store and process the inter-pattern dissimilarities for all the training samples, and thus, the accuracy of the classifier designed in the dissimilarity space is dependent on the methods used to achieve this.

In this talk, we suggest a novel strategy to enhance the computation for all families of DBCs. Rather than compute, store and process the DBC based on the entire data set, we advocate that the training set be first reduced into a smaller representative subset. Also, rather than determine this subset on the basis of random selection or clustering, we advocate the use of a Prototype Reduction Scheme (PRS), whose output yields the points to be utilized by the DBC. The rationale for this is as follows : Since a PRS has the capability of extracting points in the original feature space that satisfactorily represent the global distribution, we believe that the dissimilarities between these representative subsets of points can effectively represent the dissimilarities between the training samples themselves. Thus, by appropriately selecting a few prototypes, it is possible to achieve a better classification performance in both speed and accuracy. In this talk we propose an approach of utilizing PRSs to select prototype vectors from the given training data set, and of simultaneously employing the Mahalanobis distance as the dissimilarity-measurement criterion to increase the DBC�s classification accuracy. Our experimental results demonstrate that the proposed mechanism increases the classification accuracy when compared with the conventional approaches for samples involving real-life as well as artificial data sets.

Bio »

Dr. John Oommen was born in Coonoor, India on September 9, 1953. He obtained his B.Tech. degree from the Indian Institute of Technology, Madras, India in 1975. He obtained his M.E. from the Indian Institute of Science in Bangalore, India in 1977. He then went on for his M.S. and Ph. D. which he obtained from Purdue University, in West Lafayettte, Indiana in 1979 and 1982 respectively. He joined the School of Computer Science at Carleton University in Ottawa, Canada, in the 1981-82 academic year. He is still at Carleton and holds the rank of a Full Professor. His research interests include Automata Learning, Adaptive Data Structures, Statistical and Syntactic Pattern Recognition, Stochastic Algorithms and Partitioning Algorithms. He is the author of more than 240 refereed journal and conference publications. He is a Fellow of the IEEE, and a Fellow of the IAPR. Dr. Oommen is on the Editorial Board of the IEEE Transactions on Systems, Man and Cybernetics, and Pattern Recognition.

For details of some of the other work presented by Dr. Oommen concerning Chaotic Pattern Recognition please click here.
Mubarak Shah
Agere Chair Professor
Computer Vision Lab, Director
School of Computer Science
University of Central Florida, USA
http://www.cs.ucf.edu/~vision/
Title: Object Tracking

Abstract »

Object tracking is an important task within the area of computer vision. The proliferation of high powered computers and the increasing need for automated surveillance systems have generated a great deal of interest in object tracking algorithms. Tracking can be defined as the problem of estimating the trajectory of an object as the object moves around a scene. Simply stated, we want to know where the object is in the image at each instant in time. Numerous approaches for object tracking have been proposed. These primarily differ from each other based on the way they tackle the following questions: Which object representation is suitable for tracking? Which image features should be used? How should the motion, the appearance and the shape of the object be modeled? The answers to these questions depend on the context/environment in which the tracking is being performed, and the end use for which the tracking information is being sought.

Our Computer Vision group at University of Central Florida has been involved in research related to several aspects of object tracking. We have developed efficient algorithms for tracking in imagery acquired by a fixed camera, a moving camera, multiple fixed overlapping and non-overlapping cameras, and multiple overlapping moving cameras. In this talk I will present an overview of our work in this area.

Bio »

Dr. Mubarak Shah, Agere Chair professor of Computer Science, and the founding director of the Computer Vision Laboratory at University of Central Florida (UCF), is a researcher in computer vision. He is a co-author of two books Video Registration (2003) and Motion-Based Recognition (1997), both by Kluwer Academic Publishers. He has worked in several areas including activity and gesture recognition, violence detection, event ontology, object tracking (fixed camera, moving camera, multiple overlapping and non-overlapping cameras), video segmentation, story and scene segmentation, view morphing, ATR, wide-baseline matching, and video registration. . Dr. Shah is a fellow of IEEE, was an IEEE Distinguished Visitor speaker for 1997-2000, and is often invited to present seminars, tutorials and invited talks all over the world. He received the Harris Corporation Engineering Achievement Award in 1999, the TOKTEN awards from UNDP in 1995, 1997, and 2000; Teaching Incentive Program award in 1995 and 2003, Research Incentive Award in 2003, and IEEE Outstanding Engineering Educator Award in 1997. He is an editor of international book series on "Video Computing"; editor in chief of Machine Vision and Applications journal, and an associate editor Pattern Recognition journal. He was an associate editor of the IEEE Transactions on PAMI, and a guest editor of the special issue of International Journal of Computer Vision on Video Computing.


	Plenary Talks Ling Guan Professor, Canada Research Chair in Multimedia Electrical and Computer Engineering Ryerson University, Canada http://www.ee.ryerson.ca/people/Guan.html Title: Self-Organizing Trees and Forests: A Powerful Tool in Pattern Clustering and Recognition Abstract » As the fruit of the Information Age comes to bare, the question of how such information, especially visual information, might be effectively harvested, archived and analyzed, remains a monumental challenge facing today�s research community. The processing of such information, however, is often fraught with the need for conceptual interpretation: a relatively simple task for humans, yet arduous for computers. In attempting to handle oppressive volumes of visual information becoming readily accessible within consumer and industrial sectors, some level of automation remains a highly desired goal. To achieve such a goal requires computational systems that exhibit some degree of intelligence in terms of being able to formulate their own models of the data in question with little or no user intervention � a process popularly referred to as Pattern Clustering or Unsupervised Pattern Classification. One powerful tool in pattern clustering is the computational technologies based on principles of Self-Organization. In this talk, we explore a new family of computing architectures that have a basis in self organization, yet are somewhat free from many of the constraints typical of other well known self-organizing architectures. Within this family, the basic processing unit is known as the Self-Organizing Tree Map (SOTM), and the most sophisticated is the Self-Organizing Forest (SOF) which consists of numerous conceptually linked trees. We will look at how this model has evolved since its inception in 1995, how it has inspired new models, and how it is being applied to complex pattern clustering problems in image filtering, image/video retrieval and 3-D image analysis. Bio » Ling Guan received his Bachelor Degree in Electronic Engineering from Tianjin University, China in 1982, Masters Degree in Systems Design Engineering at University of Waterloo, Canada in 1985, and Ph.D. Degree in Electrical Engineering from University of British Columbia, Canada in 1989. From 1993 to 2000, he was on the Faculty of Engineering at the University of Sydney, Australia. Since May 2001, he has been a professor in Electrical and Computer Engineering at Ryerson University, Canada. In November 2001, He was appointed to the position of Tier I Canada Research Chair in Multimedia. He is the recipient of numerous awards, including a Senior Fellowship from Australian Academy of Science/Japan Society for the Promotion of Science in 2002, and IEEE Transactions on Circuits and Systems for Video Technology Best Paper Award in 2005. He held visiting positions at British Telecom (1994), Tokyo Institute of Technology (1999), Princeton University (2000) and Microsoft Research Asia (2002). Dr. Guan has authored/co-authored more than 200 scientific articles and three books in multimedia processing and communications, computer vision, machine learning, and adaptive image/signal processing. He has served as associate editor/guest editor of numerous international journals, including Proceedings of the IEEE. Currently he is on the editorial boards of IEEE Signal Processing Magazine, IEEE Computational Intelligence Magazine, IEEE Transactions on Circuits and Systems for Video Technology and IEEE Transactions on Neural Networks. He was the Founding General Chair of IEEE Pacific-Rim Conference on Multimedia, and currently serves as the General Chair of 2006 IEEE International Conference on Multimedia and Expo to be held in Toronto, Canada. B. John Oommen Professor, Fellow of the IEEE, Fellow of the IAPR School of Computer Science Carleton University, Canada http://www.scs.carleton.ca/~oommen/ Title: On Using Prototype Reduction Schemes to Optimize Dissimilarity-Based Classification Abstract » The aim of this talk is to present a strategy by which a new philosophy for pattern classification, namely that pertaining to Dissimilarity-Based Classifiers (DBCs), can be efficiently implemented. This methodology, proposed by Duin and his co-authors, is a way of defining classifiers between the classes, and is not based on the feature measurements of the individual patterns, but rather on a suitable dissimilarity measure between them. The advantage of this methodology is that since it does not operate on the class-conditional distributions, the accuracy can exceed the Bayes� bound and actually attempt to attain the zero-error bound. The problem with this strategy is, however, the need to compute, store and process the inter-pattern dissimilarities for all the training samples, and thus, the accuracy of the classifier designed in the dissimilarity space is dependent on the methods used to achieve this. In this talk, we suggest a novel strategy to enhance the computation for all families of DBCs. Rather than compute, store and process the DBC based on the entire data set, we advocate that the training set be first reduced into a smaller representative subset. Also, rather than determine this subset on the basis of random selection or clustering, we advocate the use of a Prototype Reduction Scheme (PRS), whose output yields the points to be utilized by the DBC. The rationale for this is as follows : Since a PRS has the capability of extracting points in the original feature space that satisfactorily represent the global distribution, we believe that the dissimilarities between these representative subsets of points can effectively represent the dissimilarities between the training samples themselves. Thus, by appropriately selecting a few prototypes, it is possible to achieve a better classification performance in both speed and accuracy. In this talk we propose an approach of utilizing PRSs to select prototype vectors from the given training data set, and of simultaneously employing the Mahalanobis distance as the dissimilarity-measurement criterion to increase the DBC�s classification accuracy. Our experimental results demonstrate that the proposed mechanism increases the classification accuracy when compared with the conventional approaches for samples involving real-life as well as artificial data sets. Bio » Dr. John Oommen was born in Coonoor, India on September 9, 1953. He obtained his B.Tech. degree from the Indian Institute of Technology, Madras, India in 1975. He obtained his M.E. from the Indian Institute of Science in Bangalore, India in 1977. He then went on for his M.S. and Ph. D. which he obtained from Purdue University, in West Lafayettte, Indiana in 1979 and 1982 respectively. He joined the School of Computer Science at Carleton University in Ottawa, Canada, in the 1981-82 academic year. He is still at Carleton and holds the rank of a Full Professor. His research interests include Automata Learning, Adaptive Data Structures, Statistical and Syntactic Pattern Recognition, Stochastic Algorithms and Partitioning Algorithms. He is the author of more than 240 refereed journal and conference publications. He is a Fellow of the IEEE, and a Fellow of the IAPR. Dr. Oommen is on the Editorial Board of the IEEE Transactions on Systems, Man and Cybernetics, and Pattern Recognition. For details of some of the other work presented by Dr. Oommen concerning Chaotic Pattern Recognition please click here. Mubarak Shah Agere Chair Professor Computer Vision Lab, Director School of Computer Science University of Central Florida, USA http://www.cs.ucf.edu/~vision/ Title: Object Tracking Abstract » Object tracking is an important task within the area of computer vision. The proliferation of high powered computers and the increasing need for automated surveillance systems have generated a great deal of interest in object tracking algorithms. Tracking can be defined as the problem of estimating the trajectory of an object as the object moves around a scene. Simply stated, we want to know where the object is in the image at each instant in time. Numerous approaches for object tracking have been proposed. These primarily differ from each other based on the way they tackle the following questions: Which object representation is suitable for tracking? Which image features should be used? How should the motion, the appearance and the shape of the object be modeled? The answers to these questions depend on the context/environment in which the tracking is being performed, and the end use for which the tracking information is being sought. Our Computer Vision group at University of Central Florida has been involved in research related to several aspects of object tracking. We have developed efficient algorithms for tracking in imagery acquired by a fixed camera, a moving camera, multiple fixed overlapping and non-overlapping cameras, and multiple overlapping moving cameras. In this talk I will present an overview of our work in this area. Bio » Dr. Mubarak Shah, Agere Chair professor of Computer Science, and the founding director of the Computer Vision Laboratory at University of Central Florida (UCF), is a researcher in computer vision. He is a co-author of two books Video Registration (2003) and Motion-Based Recognition (1997), both by Kluwer Academic Publishers. He has worked in several areas including activity and gesture recognition, violence detection, event ontology, object tracking (fixed camera, moving camera, multiple overlapping and non-overlapping cameras), video segmentation, story and scene segmentation, view morphing, ATR, wide-baseline matching, and video registration. . Dr. Shah is a fellow of IEEE, was an IEEE Distinguished Visitor speaker for 1997-2000, and is often invited to present seminars, tutorials and invited talks all over the world. He received the Harris Corporation Engineering Achievement Award in 1999, the TOKTEN awards from UNDP in 1995, 1997, and 2000; Teaching Incentive Program award in 1995 and 2003, Research Incentive Award in 2003, and IEEE Outstanding Engineering Educator Award in 1997. He is an editor of international book series on "Video Computing"; editor in chief of Machine Vision and Applications journal, and an associate editor Pattern Recognition journal. He was an associate editor of the IEEE Transactions on PAMI, and a guest editor of the special issue of International Journal of Computer Vision on Video Computing.
ICIAR - International Conference on Image Analysis and Recognition Send your comments to [email protected]