Pareto-depth for Multiple-query Image Retrieval

Ko-Jen Hsiao, Jeff Calder Alfred O. Hero III

Most content-based image retrieval systems consider either one single query, or multiple queries that include the same object or represent the same semantic information. In this paper we consider the content-based image retrieval problem for multiple query images corresponding to different image semantics. We propose a novel multiple-query information retrieval algorithm that combines the Pareto front method (PFM) with efficient manifold ranking (EMR). We show that our proposed algorithm outperforms state of the art multiple-query retrieval algorithms on real-world image databases. We attribute this performance improvement to concavity properties of the Pareto fronts, and prove a theoretical result that characterizes the asymptotic concavity of the fronts. We also present a graphical user interface (GUI) that allows the user to explore the Pareto fronts and visualize the partially ordered relationships between the queries and the images in the database.

The Matlab code of GUI for Pareto retrieval method can be downloaded here.

Download

If you find any bugs or errors, you may report them to the first author of the paper. The email of Ko-Jen Hsiao is coolmark@umich.edu