Clustering and Ranking of Image Search Results

Abstract

In a typical content-based image retrieval (CBIR) system, query result is a set of images sorted by feature similarities with respect to the query. We introduce a new approach to CBIR result representation. We propose that CBIR system should retrieve image clusters, which elements should be sorted by the most meaningful feature similarities. Actually, this paper does not present a full approach but rather work in progress.

1 Figure or Table

Cite this paper

@inproceedings{Sivogolovko2009ClusteringAR, title={Clustering and Ranking of Image Search Results}, author={Elena Sivogolovko}, year={2009} }