A corner tracker snake approach to segment irregular object shape in video image

In this paper we propose a modified version of the classical explicit snake (active contour) approach for the segmentation of irregular object shape in video images. In the classical approach the external evolution force is computed using the gradient of the image or the region information. In our original proposed method the external force is computed using the region information with two windows around the contour point. This new approach improves the speed of convergence and also the quality of segmentation especially for irregular objects shape (objects with sharp corners, deep concave/convex shape). As the contour points are attracted to the discontinuity of form, the modified snake is called "corner tracker snake".