A Rotation Invariance Image Matching Method Based on Harris Corner Detection

Abstract

This paper introduces a method for extracting the distinctive feature of rotation invariance from image that shows reliable matching between images of different angle. First, we use the method of Harris corner detection for finding the interest points from the two images to be matched, in which an extreme tactics is adopted for exactly determining the interest points. Follow by adopting a sub-block checking method for eliminating the cluster and reduce the number of interest points. Second, this paper describes an approach to depict the characteristics of interest points which are gained by rotating the area centered the interest point. By this means the rotation invariance of images can implement. Third, the marching method is introduced calculating the similar information among these points, for example the NPROD algorithm. Through a number of experimental images, we prove that this method is proved viable and robust.