ICIAP 2007 - Invited speakers

We are glad to present the ICIAP 2007 invited speakers:

(click on the talk title to see detailed information)
Iris Recognition Using Genetic Algorithm and Support Vector Machine
Prabir Bhattacharya
Concordia Univ., Canada
Area
Theory
From Image Analysis to Content Extraction: Are We There Yet?
Tsuhan Chen

--> Download the Presentation <--
Area
Multimedia
Looking for Patterns in Video
Rama Chellappa (IAPR sponsored)
Minta Martin Professor of Engineering
Department of Electrical and Computer Engineering and UMIACS
University of Maryland, College Park, MD.
Area
Human-Centred Applications
Surveillance on Graphs
Stan Sclaroff
Professor and Chair
Department of Computer Science
Boston University, Boston, MA USA

--> Download the Presentation <--
Area
Surveillance and Security
Web-scale multimedia data management: challenges and remedies
Edward Y. Chang
Univ. of California
Santa Barbara, Google China
Workshop
VMDL'07

Detailed information


Iris Recognition Using Genetic Algorithm and Support Vector Machine

Prabir Bhattacharya
Concordia University, Montreal, Quebec, Canada

Abstract
Iris recognition has been regarded as one of the most reliable biometric technologies in recent years. We propose an iris recognition technique based on the zigzag collarette area localization and asymmetrical support vector machine. The zigzag collarette area is one of the most important parts of the iris complex pattern since it is usually insensitive to the pupil dilation and less affected by the eyelids and the eyelashes. The collarette region captures only the most significant areas of the iris complex pattern and provides better recognition accuracy than the approach where the entire iris region is considered. The feature sequence extracted from the iris images using the log-Gabor filters is applied to train the support vector machine (SVM) as an iris pattern classifier. We use the multi-objective genetic algorithm (MOGA) to optimize the features and to increase the overall recognition accuracy based on the matching performance of the SVM. The proposed technique is computationally effective with recognition rates of 97.70 % and 95.60% on the ICE (Iris Challenge Evaluation, created by the University of Notre Dame) and the WVU (West Virginia University) iris data sets respectively.

Speaker Biography
Prabir Bhattacharya is a Professor at the Concordia University, Montreal, Canada where he holds a Canada Research Chair, Tier 1. He was earlier a Professor at the University of Nebraska-Lincoln, Department of Computer Science and Engineering, USA where he served during 1986-99. During 1999-2004, he worked as a Principal Scientist at the Panasonic Information Technologies Laboratory in Princeton, New Jersey, USA. He received his Ph.D. from the University of Oxford, UK. He is a Fellow of the IEEE, and the IAPR. He is the Associate Editor-in-Chief of the IEEE Transactions on Systems, Man and Cybernetics, Part B (Cybernetics). Also, he is an associate editor of three other technical journals. He holds 4 US Patents, and has co-authored about 200 publications including 90 journal papers.


From Image Analysis to Content Extraction: Are We There Yet?

Tsuhan Chen

Abstract
Based on the bag-of-words representation, topic models have recently become a popular approach to object discovery, i.e., extracting the "object of interest" from a set of images in a completely unsupervised manner. In this talk, we will outline this approach, and extend it from still images to motion videos. We will propose a novel spatial-temporal framework that extends topic models for both appearance modeling and motion modeling. The spatial and temporal models are integrated so that motion ambiguities can be resolved by appearance, and appearance ambiguities can be resolved by motion. This framework finds application in video retrieval (e.g., for YouTube or Google Video) and video surveillance.

Speaker Biography
Tsuhan Chen has been with the Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, Pennsylvania, since October 1997, where he is currently Professor and Associate Department Head. From August 1993 to October 1997, he worked at AT&T Bell Laboratories, Holmdel, New Jersey. He received the M.S. and Ph.D. degrees in electrical engineering from the California Institute of Technology, Pasadena, California, in 1990 and 1993, respectively. He received the B.S. degree in electrical engineering from the National Taiwan University in 1987. Tsuhan served as the Editor-in-Chief for IEEE Transactions on Multimedia in 2002-2004. He also served in the Editorial Board of IEEE Signal Processing Magazine and as Associate Editor for IEEE Trans. on Circuits and Systems for Video Technology, IEEE Trans. on Image Processing, IEEE Trans. on Signal Processing, and IEEE Trans. on Multimedia. He co-edited a book titled Multimedia Systems, Standards, and Networks. Tsuhan received the Charles Wilts Prize at the California Institute of Technology in 1993. He was a recipient of the National Science Foundation CAREER Award, from 2000 to 2003. He received the Benjamin Richard Teare Teaching Award at the Carnegie Mellon University in 2006. He is elected to the Board of Governors, IEEE Signal Processing Society, 2007-2009. He is a member of the Phi Tau Phi Scholastic Honor Society. He is Fellow of IEEE, and a Distinguished Lecturer of the Signal Processing Society.


Looking for Patterns in Video

Rama Chellappa
Minta Martin Professor of Engineering
Department of Electrical and Computer Engineering and UMIACS
University of Maryland, College Park, MD.

Abstract
With the ubiquitous presence of inexpensive video cameras, new challenges to video-based pattern recognition problems are emerging. Video-based pattern recognition problems have applications in homeland security, healthcare, video indexing and anomaly detection. The single most important feature that distinguishes video-based pattern recognition problems from still-image based recognition problems is the dynamical nature of patterns in videos. This creates new intellectual challenges and provides opportunities for novel approaches. In this talk, I will first discuss some of the general principles for designing robust video-based pattern recognition systems using statistical, structural and syntactic methods. We first present the design of statistical parametric classifiers for face and gait-based human recognition, recognition of bee dances, human activity recognition and vehicle class recognition across non-overlapping cameras. Characterization of class-conditional densities using pattern appearance, shape, motion and behavior are discussed. A method for compensating for the variations in the rate at which patterns evolve and the role of quasi-invariants in activity recognition are then discussed. A non-parametric method based on a novel "human gait DNA" signature is then described for recognizing human motion patterns. We then present two examples of pattern recognition in video using attribute grammars and stochastic Petri nets. Finally, we discuss some theoretical issues and practical problems that remain to be addressed in this area.

Speaker Biography
Prof. Chellappa received the M.S.E.E. and Ph.D. Degrees in Electrical Engineering from Purdue University, West Lafayette, IN, in 1978 and 1981 respectively. Since 1991, he has been a Professor of Electrical and Computer Engineering and an Affiliate Professor of Computer Science at University of Maryland (UMD), College Park. He is also affiliated with the Center for Automation Research (Director) and the Institute for Advanced Computer Studies (Permanent member). Recently, he was named a Minta Martin Professor of Engineering. Over the past 26 years, he has published numerous book chapters, peer-reviewed journal and conference papers. He has co-authored and edited many books in visual surveillance, biometrics, MRFs and image processing. His current research interests are in face and gait analysis, 3D modeling from video, surveillance and monitoring, hyper spectral processing, and computer vision. Prof. Chellappa served as the associate editor of many IEEE Transactions and as the Editor-in-Chief of IEEE Transactions on Pattern Analysis and Machine. Intelligence. He served as a member of the IEEE Signal Processing Society’s Board of Governors and as its Vice President of Awards and Membership. He has received several awards, including an NSF Presidential Young Investigator Award, two IBM Faculty Development Awards, an Excellence in Teaching Award, a Technical Achievement Award from the IEEE Signal Processing Society, two conference paper awards from ICPR 1992 and 2006, an the Outstanding Innovator Award. He was elected as a Distinguished Faculty Research Fellow and as a Distinguished Scholar-Teacher at UMD. He is a Fellow of IEEE and the International Association for Pattern Recognition. He has served as a General and Technical Program Chair/Co-Chair for several IEEE international and national conferences and workshops. He is a Golden Core Member of IEEE Computer Society.


Surveillance on Graphs

Stan Sclaroff
Professor and Chair
Department of Computer Science
Boston University, Boston, MA USA

Abstract
Graphical models provide a convenient representation for a number of surveillance problems. In the first part of the talk, I will describe a solution to the problem of learning and predicting traffic patterns within a collection of video cameras that are distributed over a wide area. Given an unknown video camera layout containing active, e.g., pan-tilt-zoom, cameras and people moving around, the goal is to predict a subset of cameras, respective camera parameter settings, and time windows that will most likely lead to success of particular vision tasks when a camera observes an event of interest. We propose an adaptive probabilistic framework that learns temporal camera correlations over time as the cameras report observed events. No extrinsic, intrinsic or color calibration of cameras is required. In the second part of the talk, I will describe how graphical models can be used to simplify reasoning about occlusions of activities observed in monocular video streams. Layers of graphical models are instantiated in the image plane, such that these layers are consistent with the depth ordering of static and dynamic occluding objects in the observed scene. This framework is demonstrated in experiments with tracking human activities in parking lots, where there are many vehicles and people moving among vehicles, entering and exiting vehicles, etc. Given these graphical models, prediction and inference are achieved efficiently via Sequential Monte Carlo sampling across space and time. Other applications of graphical models in surveillance will be described as time allows.

Speaker Biography
Stan Sclaroff received his PhD from MIT in 1995. He is a Professor of Computer Science at Boston University, where he founded the Image and Video Computing research group. Prof. Sclaroff has coauthored numerous scholarly publications in the areas of tracking, video-based analysis of human motion and gesture, surveillance, deformable shape matching and recognition, as well as image/video database indexing, retrieval and data mining methods. He has served on the technical program committees of over 80 computer vision conferences and workshops. He received an ONR Young Investigator Award and an NSF Faculty Early Career Development Award in 1996. He has served as an Associate Editor for IEEE Transactions on Pattern Analysis, 2000-2004, and 2006-present. He is a Senior Member of the IEEE.


Web-scale multimedia data management: challenges and remedies

Edward Y. Chang
Google Research

Abstract
Text-based search engines have been flourishing. However, despite increasing needs of tools for organizing and searching imagery and video content, we have not seen a successful deployment of a Web-scale multimedia search engine. This talk analyzes main technical challenges of such a deployment, and presents remedies in three areas: feature extraction, similarity characterization, and scalability.

Speaker Biography
Professor Edward Chang received his M.S. in Computer Science and PhD in Electrical Engineering at Stanford University in 1994 and 1999, respectively. He joined the department of Electrical & Computer Engineering at University of California, Santa Barbara, in September 1999. He received his tenure in March 2003, and was promoted to full professor of Electrical Engineering in 2006. His recent research activities are in the areas of machine learning, data mining, high-dimensional data indexing, and their applications to image databases, video surveillance, and Web mining. Recent research contributions of his group include methods for learning image/video query concepts via active learning with kernel methods, formulating distance functions via dynamic associations and kernel alignment, managing and fusing distributed video-sensor data, categorizing and indexing high-dimensional image/video information, and speeding up Support Vector Machines via parallel matrix factorization and indexing. Professor Chang has served on several ACM, IEEE, and SIAM conference program committees. He co-founded the annual ACM Video Sensor Network Workshop and has co-chaired it since 2003. He co-chairs several conferences: Multimedia Modeling (2006), SPIE/IS&T Multimedia Information Retrieval (2006), ACM Multimedia (2006), IEEE Data Engineering (2007), and WWW 2007. He serves as an Associate Editor for IEEE Transactions on Knowledge and Data Engineering and ACM Multimedia Systems Journal. Professor Chang is a recipient of the IBM Faculty Partnership Award and the NSF Career Award. He is currently on leave from UC, heading Google Research at China.

» 
»