A novel region-based image retrieval method using relevance feedback

Feng Jing, Bo Zhang, Fuzong Lin, Wei-Ying Ma, Hong-Jiang Zhang
2001 Proceedings of the 2001 ACM workshops on Multimedia multimedia information retrieval - MULTIMEDIA '01  
Content-based image retrieval using region segmentation has been an active research area in the past few years. Contrasting to traditional approaches, which compute only global features of images, the region-based methods extract features of the segmented regions and perform similarity comparisons at the granularity of region. In this paper, we propose a novel regionbased retrieval method, Self-Learned Region Importance (SLRI). In this method, image similarity measure is based on the region
more » ... rtance learned from users' feedback. The region importance that coincides with human perception can not only be used in a query session, but also be memorized and cumulated for future queries. Experimental results on a database of about 8,600 general-purposed images show the effectiveness of our method. Keywords Region-based image retrieval, feedback, region importance.
doi:10.1145/500942.500943 fatcat:e4y3b2mskjavbpw26bgoccufsi