[Segmentation of retinal blood vessels based on centerline extraction].

ABSTRACT

The precise estimation of blood vessel centerline and width is a prerequisite condition for the quantitative and visualized diagnosis of blood vessel disease in fundus images. In this paper, a retinal blood vessel segmentation algorithm based on centerline extraction is proposed. According to the characteristics of the fundus image and retinal blood vessels, the image is convoluted with the masks of discrete Gaussian partial derivative kernels. The centerline is determined by differential geometric properties of the blood vessels and the width is also calculated. The precision of our method can reach sub-pixel level with a fast computation speed. The experiments on several kinds of fundus images showed that the method worked quickly and accurately.