How to compare search engines in CBIR?

Abstract

At present a great deal of research is being done in different aspects of Content-Based Image Retrieval (CBIR) of which the search engine is one of the most important elements. In this paper we cover the state-of-the-art techniques in CBIR according to the aims of retrieval and matching techniques. The issue we address is the analysis of search engines reducing the `semantic gap'. The matching methods are compared in terms of their usefulness for different user's aims. Finally, we compare our search engine with Google's and the SIFT method.