An Improved Fast Normalized Cross Correlation Algorithm

Abstract

Using logical criterion based on the characteristics of binary image, the normalized cross-correlation algorithm is improved. First, the binary of gray image is carried out. The target and the background are made a distinction between 0 and 1. Second, through the logic correlation matching, two images of the same location value equal to 1, otherwise 0. Finally, the correlation coefficient is calculated. The experimental results show that the improved normalized cross-correlation algorithm can speed up the matching, without affecting the accuracy of the matching.