Color Texture Analysis for 2-D Recognition: Algorithms
and Applications

Abstract

The problem of visual recognition by computers is multi-faceted but can be broadly divided into two categories: 2-D and 3-D recognition. In the area of 2-dimensional recognition, which incorporates fields such as Image Processing, Image Analysis, and Pattern Recognition, the main goal is to describe a given image using a set of features such as color, texture, shape, that represent the image effectively (and efficiently). The work presented here focuses on the use of color and texture. Computing color and texture features can be done either separately, i.e., color features, texture features, or jointly, i.e., color texture features. The importance of a joint color texture representation is emphasized as results have shown that it could describe unique aspects of an image not provided by separate representations.  Several algorithms are described covering both approaches, and results are presented from applications in areas such as automated surveillance, defect detection, image database retrieval, and video segmentation.

Dr. George Paschos received the Ph.D. degree in Computer Science from the University of Louisiana, Lafayette in 1996. He also received a M.S. degree in Computer Science from the California State University, Chico (1992), and a B.S. (5-year) degree in Computer Science and Engineering from the University of Patras, Greece (1989). He has worked as a teaching and research assistant at the University of Louisiana, Lafayette (1993-96), Research Fellow at the Centre for Vision Speech and Signal Processing, University of Surrey, UK (1996), and Visiting Assistant Professor at Michigan Technological University (1996-97). He is currently an Assistant Professor of Computer Science at Florida Memorial College. His main research interests are in image processing and analysis. He has published several articles in international conferences and journals. He is a member of IEEE and ACM.

For more information, contact Venu Dasigi.

This page is maintained by Venu Dasigi.