期刊名称：International Journal on Computer Science and Engineering
印刷版ISSN：2229-5631
电子版ISSN：0975-3397
出版年度：2012
卷号：4
期号：01
页码：40-44
出版社：Engg Journals Publications
摘要：CBIR is the application of computer vision techniques to the image retrieval problem, that is, the problem of searching for digital images in large databases. An experimental comparison of a number of different color descriptors for evaluation of CBIR approaches for differently sized images is presented in this paper. Color descriptors are considered for retrieval. The primary goal is to determine which approach is most efficient in representing the similarity of color images which are not same in size, though their aspect ratio is same. In this paper, we present the comparison of different color descriptors. For the purpose we have used Global Color Histogram (GCH), Local Color Histogram (LCH) and Color average. Publicly available image database is used and the retrieval performance of the features is analyzed in detail. The work is concluded by stating which method performs well.
关键词：Image Retrieval; Image Size; Color Histogram; Correlation
