Share Email Print
cover

Proceedings Paper

Correlation retrieval method for content-based image retrieval system embedded with DSP
Author(s): Dingyuan Xia; Manli Zhou; Zhengquan Xiang
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Aimed at the limitations existed in content-based image retrieval systems for optimization model, generalization design and retrieval efficiency, in this paper, first, based on the representative method for accumulative histogram on color and co-occurrence matrix on texture, according to the interactive relevance feedback principle between man and computer, a new description method for combined features of image is given. Then, referring to the universal system design norm provided in the MPEG-7, an optimization model of image features correlation retrieval is presented, and a content-based image features correlation retrieval system embedded with DSP is masterly constructed. In this system, the advantages of digital signal processor (DSP) in image signal processing are full utilized, and the parallel processing flows for correlation description of image features and fast retrieval, extraction and index of image features, as well as management and renewal of image data are availably performed, which brings forward a new idea for appropriative image retrieval in large image database (such as remote sensing images in GIS) and universal image retrieval in Web database (such as different images on Internet). The rationality of the new scheme is validated by experimental results.

Paper Details

Date Published: 31 July 2002
PDF: 7 pages
Proc. SPIE 4875, Second International Conference on Image and Graphics, (31 July 2002); doi: 10.1117/12.477112
Show Author Affiliations
Dingyuan Xia, Huazhong Univ. of Science and Technology and Guilin Institute of Electronic Technology (China)
Manli Zhou, Huazhong Univ. of Science and Technology (China)
Zhengquan Xiang, Guilin Institute of Electronic Technology (China)


Published in SPIE Proceedings Vol. 4875:
Second International Conference on Image and Graphics
Wei Sui, Editor(s)

© SPIE. Terms of Use
Back to Top