MetaSEEk - A Content-Based Meta Search Engine for Images
This project deals with the retrieval of visual content from large distributed on-line repositories such as image search engines. The wealth of visual content on the Web is rapidly growing. The extension of current visual retrieval techniques to a large-scale distributed environment such as the Web has encountered important technical barriers concerning heterogeneity, complexity and bandwidth on the Internet. We have developed a prototype content-based metasearch engine for images, MetaSEEk, to investigate the issues involved with efficiently querying large, distributed online image search engines for locating images of interest on the Web. The most recent version of MetaSEEk exploits user feedback in previous searches for recommending target search engines and integrating the results from different search engines in future queries.
This research is currently part of the IMKA project, which aims at developing intelligent multimedia knowledge applications.
Faculty: Prof. Shih-Fu Chang
B. Benitez, M. Beige and S.-F. Chang, Using
Relevance Feedback in Content-Based Image Metasearch, IEEE Internet
Computing, Vol. 2, No. 4, pp. 59-69, Jul/Aug 1998.
Beigi, A. B. Benitez, and S.-F. Chang, MetaSEEk:
A Content-Based Meta-Search Engine for Images, Proceedings of the
SPIE 1998 Conference on Storage and Retrieval for Image and Video Databases
VI (IST/SPIE-1998), Vol. 3312, San Jose, CA, Jan 28-30, 1998.
J. R. Smith, M. Beigi and A. B. Benitez, Visual
Information Retrieval from Large Distributed On-line Repositories,
Communications of the ACM, Vol. 40, No. 12, pp. 63-71, Dec 1997.
For problems or questions
regarding this web site contact The