Efficient query refinement for image retrieval

This paper uses multiple image features, and presents in details a new relevance feedback technique that integrates the positive and negative examples provided by the user that is more performant than the standard relevance feedback approach.

Abstract

Although powerful image representations have been proposed for content-based image retrieval, most of the current systems are "rigid", i.e. they retrieve a fixed set of images as response to a given query and an image feature. In this paper, our goal is to introduce tools for making image retrieval systems more flexible. More precisely, we use multiple image features, and present in details a new relevance feedback technique that integrates the positive and negative examples provided by the user. Experimental results on various large databases show that the proposed technique is more performant than the standard relevance feedback approach.