Region-based relevance feedback in image retrieval

Relevance feedback and region-based representation of images are two effective ways to improve accuracy in content-based image retrieval. We propose a novel relevance feedback approach based on region representation. It can be considered as a special case of the query point movement method in region-based image retrieval. By assembling all the segmented regions of positive examples together and resizing the regions to emphasize the latest positive examples, we form a composite image as the optimal query. A region-based image similarity measure is used to calculate the distance between the optimal query and an image in the database. An incremental clustering technique is also considered to improve the retrieval efficiency. Experimental results show that the proposed approach is effective in improving the performance of content-based image retrieval systems.