The improvement of GAC model for image segmentation

Abstract

An Adaptive image segmentation algorithm based on geometric active contour (GAC) model was presented in this paper in order to solve the problem that tradition GAC model can not segment adaptively. By combining the regional information to construct energy functional description area information. We propose an improved adaptive image segmentation algorithm, This algorithm combines the advantages of GAC model and C-V model effectively, Regional energy functional could determine the evolution speed to replace the constant evolution speed in traditional GAC model. Experimental results showed that the proposed algorithm is feasible, and reaches an obvious effect in terms of boundary leaking.