A New Approach for Affine-Invariant Image Matching

Abstract

Affine-invariant matching is one of the challenging fields for image matching. Although several algorithms (ASIFT, Fair-SURF) have been proposed and achieved expressive performance, all these method need to simulate perspective changes and exhaust all possible match which is of high computation complexity (O(N2)). In this paper, we proposed a new method to introduce global descriptor to filter out much unnecessary coarse matches for the matching procedure. Specially, the computation complexity of matching procedure in our method reduces significantly to O(N). But, the experiment result shows that the proposed method can achieve comparable performance to ASIFT at much lower cost.