Improving retrieval performance by region constraints and relevance feedback

In this paper, region features and relevance feedback are used to improve the performance of CBIR. Unlike existing region-based approaches where either individual regions are used or only simple spatial layout is modeled, the proposed approach simultaneously models both region properties and their spatial relationships in a probabilistic framework. Furthermore, the retrieval performance is improved by an adaptive filter based relevance feedback. To illustrate the performance of the proposed approach, extensive experiments have been carried out on a large heterogeneous image collection with 17,000 images, which render promising results on a wide variety of queries. Supported by the National Natural Science Foundation of China under Grant No.69902004 and the National Key Project of China under Grant No.2001BA201A07. Wang Tao is a Ph.D. candidate in Department of Computer Science and Technology at Tsinghua University. He received the B.S. degree in the University of Science and Technology of China in 1996, the M.S. degree from Chinese Academy of Sciences in 1999. His current research interests are content-based image retrieval, pattern recognition, image processing and computer graphics. Yong Rui received his Ph.D. degree in electrical and computer engineering in 1999 from the University of Illinois at Urbana-Champaign. Since March 1999, he has been a researcher in Microsoft Research, Redmond. His research interests include multimedia systems, distance learning and distributed meetings, image/video/audio processing, computer vision and machine learning. He has published five book chapters, six journal papers, and over forty refereed conference papers in the above areas. Dr. Rui holds six U.S. pending patents and is a member of ACM and IEEE. Jia-Guang Sun is a professor in Department of Computer Science and Technology at Tsinghua University. He is also the Director of National CAD Engineering Center at Tsinghua University and an Academician of the Chinese Academy of Engineering. He received the B.S degree in Computer Science from Tsinghua University in 1972. During 1985 to 1986, he was a visiting scholar in UCLA. His current research interests are computer-aided geometric design, computer graphics and product data management.