COLOR MATCHING FOR IMAGE RETRIEVAL

Color is an important attribute for image matching and retrieval. We p resent two new color matching methods, the ''Reference Color Table Met hod'' and a ''Distance Method'', for image retrieval. Both these metho ds and an existing method ''Histogram Intersection'' were implemented and tested for a database size of 170 color images. To compare the eff icacy of each method, a figure of merit, called ''Efficiency of Retrie val'', is defined. The results show that both the new methods perform. better than the existing method, and that the Reference Color Table M ethod gives the best results.