Physicians who see a suspicious region in a image and want to look up previous examples of that image to compare, using visual similarities for gas and oil exploration, and site-specific crop management and yield prediction are some of the uses for a system that would find an electronically stored image according to what was in it rather than what was said about it. The 20 papers report success to date and some ideas being worked in on image retrieval, video retrieval, relevance feedback and indexing, and modeling for image and video libraries. The topics include using artificial queries to evaluate image retrieval, a factor graph framework for semantic indexing and retrieval in video, Bayesian relevance feedback, and a hidden Markov model approach to the structure of documentaries. There is no subject index. Annotation copyrighted by Book News, Inc., Portland, ORQuery images appear in the first column; matched images are shown to the right, with matching cost shown below. ... Leung, and Jan Puzicha for helpful discussions and Niclas Borlin of Umea University for his Matlab code for the assignment problem. References  S. Belongie et al. Color- and texture-based image segmentation using EM and its application to content-based image retrieval. ln Proc.
|Title||:||Proceedings, IEEE Workshop on Content-Based Access of Image and Video Libraries, Hilton Head Island, South Carolina, June 12, 2000|
|Publisher||:||IEEE - 2000|