An Empirical Investigation of the Scalability of a Multiple Viewpoint CBIR System

Abstract

Our work in content-based image retrieval (CBIR) relies on content-analysis of multiple representations of an image which we term multiple viewpoints or channels. The conceptual idea is to place each image in multiple feature spaces and then perform retrieval by querying each of these spaces and merging the several responses. We have shown that a simple realization of this strategy can be used to boost the retrieval effectiveness of conventional CBIR. In this work we evaluate our framework in a larger, more demanding test environment and find that while absolute retrieval effectiveness is reduced, substantial relative improvement can be consistently attained.