A graph-based approach to corner matching using mutual information as a local similarity measure

Corner matching constitutes a fundamental vision problem that serves as a building block of several important applications. The common approach to dealing with this problem starts by ranking potential matches according to their affinity, which is assessed with the aid of window-based intensity similarity measures. Then, actual matches are established by optimizing global criteria involving all potential matches. This paper puts forward a novel approach for solving the corner matching problem that uses mutual information as a window similarity measure, combined with graph matching techniques for determining a matching of corners that is globally optimal. Experimental results illustrate the effectiveness of the approach.