Contend Base Image Retrieval using Color Feature of Central Region and Optimized Comparing Bin


The KIPS Transactions:PartB , Vol. 11, No. 5, pp. 581-586, Aug. 2004
10.3745/KIPSTB.2004.11.5.581,   PDF Download:

Abstract

In this paper, we proposed a content-based image retrieval using a color feature for central region and its optimized comparing bin method. Human's visual characteristic is influenced by existent of central object. So we supposed that object is centrally located in image and then we extract color feature at central region. When the background of image is simple, the retrieval result can be bad affected by major color of background. Our method overcome this drawback as a result of the human visual characteristic. After we transform image into HSV color space, we extract color feature from the quantized image with 16 level. The experimental results showed that the method using the eight high rank bin is better than using the 16 bin The case which extracts the feature with image's central region was superior compare with the case which extracts the feature with the whole image about 5%.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
E. J. Ryu, Y. J. Song, W. B. Park, J. H. Ahn, "Contend Base Image Retrieval using Color Feature of Central Region and Optimized Comparing Bin," The KIPS Transactions:PartB , vol. 11, no. 5, pp. 581-586, 2004. DOI: 10.3745/KIPSTB.2004.11.5.581.

[ACM Style]
Eun Ju Ryu, Young Jun Song, Won Bae Park, and Jae Hyeong Ahn. 2004. Contend Base Image Retrieval using Color Feature of Central Region and Optimized Comparing Bin. The KIPS Transactions:PartB , 11, 5, (2004), 581-586. DOI: 10.3745/KIPSTB.2004.11.5.581.