A New Method for Edge Feature Detection and Matching

Image feature detection and matching is a fundamental task in image processing and machine vision. In this paper we present novel methods for feature detection and matching. We have used edge points and their accumulated curvature information for feature detection. The detected features are then matched using a new method called “fuzzy-edge based feature matching”. To increase the speed of matching algorithms, a new multi-resolution based method and edge pyramids are proposed. Experimental results have shown that the algorithms are fast and reliable and can be used in the environments with noise and illumination change. The proposed algorithms can be used in various machine vision applications such as target tracking, image registration and stereovision. Keywords– Feature detection, edge matching, multi-resolution based edge matching, edge pyramid