Topic-sensitive interactive image object retrieval with noise-proof relevance feedback

One current direction to enhance the search accuracy in visual object retrieval is to reformulate the original query through (pseudo-)relevance feedback, which augments a query with visual terms from the image documents most highly ranked by an initial search or identified by user. However, query and feedback images usually contain multiple objects or aspects, and as a consequence the original query´s focus may drift because of the newly added terms and noises. The results of using an augmented query are thus often inferior to that of using only the original one. In this paper we propose the topic-sensitive image retrieval with noise-proof relevance feedback to address the query drift problem in visual object retrieval. The proposed method removes irrelevant noises and topics from both query and feedback images to prevent query drift. A discriminative learning strategy is then employed to re-rank and improve the initial search result. Experiments on a real world data set demonstrate the effectiveness of our approach and show that the proposed approach can better learn user intention.