Image segmentation based on adaptive threshold edge detection and mean shift

Abstract

A novel image segmentation algorithm based on the adaptive edge detection and an improved mean shift is proposed. According to the Ostu method, an adaptive threshold algorithm is applied to improve Canny operator in edge detection. The edge detection method has better performance and strong adaptability. Then the resulting edge information is incorporated into the main two steps of image segmentation based on mean shift. Since the discontinuity and homogeneity information are combined flexibly, the proposed algorithm takes the best of local and global image information. Experimental results reveal that the proposed algorithm is stronger adaptive and achieves better segmentation performance compared with several typical kinds of methods.