Illumination invariant Analysis of Color Texture

Assistant Prof. Donald Adjeroh

Lane Dept of Computer Science and Elec. Engineering, West Virginia Uni.

Thu Dec 15 11:00:00 NZDT 2005 in Room 031, MSCS

Abstract

Color and texture are two well-studied cues used by both man and machine in object recognition and scene understanding. When the basic problem is analysis of object surfaces, there has been a long standing debate on whether color and texture should be processed separately or jointly. The basic objective in this talk is to contribute to this debate. We will describe a recently proposed illumination minvariance model - a transformation scheme for illumination invariance. We then present results of the application of the model in color texture analysis, face recognition, and general image enhancement.

This work is a joint effort with Uma Kandawamy (WVU), and Allan Hanbury (Vienna University of Technology, Austria).

Biography

Don Adjeroh received the BEng degree (First Class Honors) in electronics and computer engineering in 1990. He received the PhD degree in computer science from the Chinese University of Hong Kong in 1997. He is currently an Assistant Professor with the Lane Department of Computer Science and Electrical Engineering, West Virginia University (WVU), Morgantown, USA. Before joining WVU in November 2000, he was a Lecturer at the Department of Computer Science, University of Canterbury, New Zealand. His general research interests are in image and video processing, multimedia data compression, distributed multimedia systems, computational aspects of vision, and bioinformatics. He received the US DoE CAREER Award in 2002. Don Adjeroh is a member of the IEEE and the IEEE Computer Society.