Share Email Print

Proceedings Paper

Evaluation on color spaces and distance measures for color histogram-based image retrieval
Author(s): Xin Zhao; Youbin Chen
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

In this paper, the performance of color histogram features in different color spaces and different distance measures are evaluated experimentally in an image retrieval system. Color histogram is an important technique for color image retrieval. The former researches have not given the conclusion which color space and distance measure is most suitable for image retrieval. In our system, color histograms are extracted from each image in different color spaces, and then used with distance measures to determine similarity. We tested numerous popular color spaces and distance measures and found the result providing the most accurate and perceptually relevant retrievals. The experiment is carried out on the bench marked Wang's dataset, comprising Correl images. For research on color image retrieval using color histogram feature, the findings of this paper may offer the guidelines in selecting color spaces and distance measures.

Paper Details

Date Published: 1 October 2011
PDF: 5 pages
Proc. SPIE 8285, International Conference on Graphic and Image Processing (ICGIP 2011), 82853F (1 October 2011); doi: 10.1117/12.914398
Show Author Affiliations
Xin Zhao, Tsinghua Univ. (China)
Youbin Chen, Tsinghua Univ. (China)

Published in SPIE Proceedings Vol. 8285:
International Conference on Graphic and Image Processing (ICGIP 2011)
Yi Xie; Yanjun Zheng, Editor(s)

© SPIE. Terms of Use
Back to Top