Panel: content-based image indexing and retrieval with mobile agents

Abstract

At present, the de-facto platform for providing contents in the Internet is the World Wide Web. A technology, which is now emerging on the Web, is content based retrieval (CBR). A content based query matches examples or prototypes to known instances of a certain media type based on a measure of similarity. For efficiency, similarity measures are frequently computed on sets of discriminant features (so-called feature vectors) being extracted a priori from the stored media. J.R. Smith and S.-F. Chang (1997; 1997) developed a CBR system for the World Wide Web. S. Scarloff et al. (1997) developed a content based image query system including a gatherer collecting images from the Web. M. Beigi et al. (1998) already applied the principle of meta-searching to a number of available image search engines. We propose an alternative architecture and model for commercial distributed indexation and searching of images that combines CBR, mobile agent technology (K. Rothermel and F. Hohl, 1998), and digital watermarking (see for instance R. Anderson, (1996)).