Nonparametric approach to color based image retrieval

The rapid growth of image archives increases the need for efficient and fast tools that can retrieve and search through large amount of visual data. In this paper we propose an efficient method of extracting the image color content, which can serve as an image digital signature, allowing the efficient indexing and retrieval of large Internet-based multimedia databases. We applied the proposed method using the images from two Internet databases containing a collection of images of fine arts and a database of low resolution images, and show that the new method of image color representation is robust to image distorsions caused by resizing and compression and can be incorporated into existing web-based retrieval systems, that exploit the information on color content of digital images.