A Novel Image Segmentation Approach Based on Improved Level Set Evolution Algorithm

Image segmentation is a fundamental topic in image processing. And the method of level set based on curve evolving theory is widely applied in image segmentation. In this paper, we propose a novel region-based active contour model which bases on the region- scalable fitting (RSF) term and the new signed pressure force (SPF) term. The RSF term is responsible for attracting the contour toward object boundaries and is dominant near object boundaries, while the SPF term which utilizes structure tensor information can improve the robustness to initialization of the contours. The model can handle weak edge and provide desirable segmentation results in the presence of intensity inhomogeneity, and offers high efficiency and rapid convergence. Given these advantages, the proposed method can get good performance and experiments show promising segmentation results on both synthetic and real images.