Hierarchical clustering relevance feedback for content-based image retrieval

In this paper we address the issue of relevance feedback in the context of content-based image retrieval. We propose a method that uses an hierarchical cluster representation of the relevant and non-relevant images in a query. The main advantage of this strategy is in performing on the initial set of the retrieved images (user feedback is provided only once for a small number of retrieved images) instead of performing additional queries as most approaches do. Experimental tests conducted on several standard image databases and using state-of-the-art content descriptors (e.g. MPEG-7, SURF) show that the proposed method provides a significant improvement in the retrieval performance, outperforming some other classic approaches.