Feature description using local neighborhoods

Abstract

Feature description and matching is an essential part of many computer vision applications. Numerous feature description algorithms have been developed to achieve reliable performance in image matching, e.g. SIFT, SURF, ORB, and BRISK. However, their descriptors usually fail when the images have undergone large viewpoint changes or shape deformation. To remedy the problem, we propose a novel feature description and similarity measure based on local neighborhoods. The proposed descriptor and similarity is useful for a wide range of matching methods including nearest neighbor matching methods and popular graph matching algorithms. Experimental results show that the proposed method detects reliable matches for image matching, and performs robustly to viewpoint changes and shape deformation.