Segmentation of Color Fundus Images of the Human Retina: Detection of the Optic Disc and the Vascular Tree Using Morphological Techniques

This paper presents new algorithms based on mathematical morphology for the detection of the optic disc and the vascular tree in noisy low contrast color fundus photographs. Both features - vessels and optic disc - deliver landmarks for image registration and are indispensable to the understanding of retinal fundus images. For the detection of the optic disc, we first find the position approximately. Then we find the exact contours by means of the watershed transformation. The algorithm for vessel detection consists in contrast enhancement, application of the morphological top-hat-transform and a post-filtering step in order to distinguish the vessels from other blood containing features.