Sangwook Oh, Min Gyo Chung and Sanghoon Sull,
Relevance Feedback Reinforced with Semantics
Accumulation,
In Proceedings of the Third International Conference on Image
and Video Retrieval (CIVR 2004),
Dublin, Ireland, No. 3115 in Lecture Notes in Computer Science, pp. 448-454, Springer-Verlag, July 21-23 2004.Relevance feedback (RF) is a mechanism introduced earlier to exploit a users perceptual feedback in image retrieval. It refines a query by using the relevance information from the user to improve subsequent retrieval. However, the users feedback information is generally lost after a search session terminates. In this paper, we propose an enhanced version of RF, which is designed to accumulate human perceptual responses over time through relevance feedback and to dynamically combine the accumulated high-level relevance information with low-level features to further improve the retrieval effectiveness. Experimental results are presented to demonstrate the potential of the proposed method.