Seminar Announcement
This seminar is sponsored by the IEEE Upper Mon subsection

Abstract: The rapid growth of visual media based applications necessitates sophisticated compression and indexing techniques in order to store, transmit and retrieve audio-visual information. The recent MPEG 4 and JPEG 2000 standards address the need for content based coding and manipulation of visual media. The upcoming MPEG 7 standard proposes content descriptors, which succinctly describe the visual content for the purpose of efficient retrieval. This implies that there is an impending need for efficient and effective joint compression and indexing approaches. Several compressed domain indexing techniques have been presented in the recent literature. These are based on the extraction of features from the compression parameters to derive the indices. However, there is little work in the domain of exploring the use of these features to serve the purposes of both compression and indexing.
Due to the revolutionary knowledge that researchers gained in understanding the human brain in the last couple of decades, and because of the promising performance of designed models that characterizes the human visual system, designing and developing image coders that correlate well with the human perception has became very superior/promising. This is due to the fact that humans are the ends users of visual data. However, there is no work directed toward visual data characterization based on human perception for joint compression and classification purposes.

In this talk we try to introduce a joint compression and classification model for visual data that exploits the content of the image for both purposes simultaneously in the wavelet domain. We try to achieve this objective at the both the coefficient level (transform level) and the bit-stream level. Then we try to apply this system on some Face Recognition applications.

Speaker Bio: Gamal Fahmy received his Bsc from University of Assiut, Egypt, in 1996. He got his Master thesis, with a title "Wavelet Functions in Image Processing", from University of Assiut, Egypt, in 1998. In August 1999 he got admitted as a Ph.D student at the Electrical Engineering Department, Arizona State University (ASU). Since then he joined the Media Processing Group at the Visual Computing and Communication Laboratory at ASU as a research assistant. His research interests are in the area of Image Compression/Classification, Image Indexing/Retrieval, Feature Extraction, and Characterizing Visual Data based on Human Perception. In the summer of 2001, he was an intern at the Video Entertainment Group, SPS, Motorola Chandler AZ, where he worked on fast classification of visual data through embedded micro-controllers. His Ph.D thesis is about developing joint Compression and classification models based on Human Perception in the wavelet compressed domain.