Corner detection algorithm based on entropy and uniqueness
Zhang Li · Journal of Computer Applications · 2009
Corner detection is a basic problem in image processing domain. Aiming at the application of corner detection to image registration, based on correlation coefficient, the uniqueness measure at a pixel was defined, and a corner detection algorithm based on entropy and uniqueness was presented. Firstly, Canny edge detector was used to detect the edge of the image, and then entropy and uniqueness of the circle windows centered at the edge pixels, were computed. The corners were detected by selecting edge pixels with high entropy and uniqueness. And the uniqueness of remaining edge pixels was modified repeatedly in order to acquire widely dispersed corners. Compared with Harris corner detection and Sift region detection, the algorithm was more efficient in detecting corners accurately, with precise location, good noise resistance and orientation independence, and was especially suitable for image registration due to the widely dispersed corners detected, except that the corners were not scale invariant.