Content-based search of video using color texture and motion

Y. Deng and B. S. Manjunath
Department of Electrical and Computer Engineering
University of California, Santa Barbara, CA 93106
E-mail: deng [at], manj [at]


We present an implementation of a system for content- based search and retrieval of video based on low-level vision features. Currently the system consists of three parts, automatic video partition, feature extraction, video search and retrieval. Three primary features, color, texture and motion are used for indexing. They are represented by color histogram, Gabor texture features, and motion histogram. Most of the processing is done directly in the MPEG compressed domain. Testing on sports and movie databases have shown good retrieval performance.
[PDF] [BibTex]
Y. Deng and B. S. Manjunath,
IEEE International Conference on Image Processing, vol. 2, pp. 534-537, Santa Barbara, California, Oct. 1997.
Node ID: 252 , DB ID: 47 , VRLID: 47 , Lab: VRL , Target: Proceedings
Subject: [Image Texture] « Look up more