Ling Guan
Princeton University
| Organizer: IEEE Toronto Section, Signal Processing Chapter |
| Title: On Image Retrieval and Video Parsing in the Compressed Domain |
| Speaker: Ling Guan Princeton University |
| Abstract: Image retrieval and video parsing are playing a key role in multimedia information processing and system design. In particular, it is one of the focul research fields in the proposed MPEG-7 Standard for multimedia communications. Since most of the current standards are based on compressed domain methods (eg. DCT in JPEG, MPEG-1 and 2, Wavelet/VQ in JPEG2000), compatibility of the retrieval/paring techniques with the standards becomes a urgent issue to address. This talk will present some of the work undertaken in the Signal & Multimedia Processing Lab at University of Sydney to address this issue. After a short introduction, I will describe a scheme on image categorization as a preprocessing step. Then the integration of human perception to achieve accurate performance is presented. The method is based on RBF function and relevance feedback for similarity ranking. Finally, an autonomous processing framework in the DCT domain for video parsing is presented. Experimental results will be presented throughout the presentation to illustrate the performance. Bio: Ling Guan received his Ph.D. Degree in Electrical Engineering from University of British Columbia, Canada in 1989. In 1989-92, he was a Research Engineer of Array Systems Computing Inc, Toronto, Canada in machine vision and signal processing. He started his academic career with the University of Sydney, Australia in October, 1992, where he is currently the director of the Signal and Multimedia Processing Lab. He was a visiting fellow at British Telecom in 1994 and a visiting professorial fellow at Tokyo Institute of Technology. He is currently a visiting professor at Princeton University. His research interests include multimedia signal processing, computational intelligence, machine learning, adaptive image and signal processing, image/ video coding and retrieval. He has published more than 120 technical articles in these fields, and is editing/authoring two books "Multimedia Image and Video Processing" and "Adaptive Image Processing: A Computational Intelligence Perspective". He is an associate editor of IS&T/SPIE Journal of Electronic Imaging and an associate editor of Journal of Real-Time Imaging. He has edited/is guest-editing a number of special issues for international journals, including Proceedings of the IEEE. He also serves on the editorial board of CRC Press' Book Series on Image Processing. He has involved in organizing many international conferences, including the program chair of IEEE Int. Conf. on Eng. of Complex Computer Systems (California, 1998), and the First IEEE Pacific-Rim Conference on Multimedia (Sydney, 2000). Dr. Guan is a Senior Member of IEEE. He is currently serving on IEEE Signal Processing Society Technical Committee on Multimedia Signal Processing, and Technical Committee on Neural Networks in Signal Processing. |
| Time and Location: Monday, March 27, 2000, 12:00 - 1:00 p.m. Galbraith Building, Room 220 University of Toronto |
The Institute of Electrical and Electronics Engineers,
Toronto Section
E-mail sec.toronto@ieee.org
Send comments to tor.sect@tor.ieee.org