Optic Disc Extraction Using Segmentation Technique

This paper reports on the design and test of an image processing algorithm for the segmentation of the optic disk (OD) in fundus images. This work describes the methods to detect main features of fundus images such as optic disk and optic cup in a retinal image, optic disk (OD) appears as a roughly round region which is brighter than its surrounding. The location of any abnormality in a retinal image relative to OD is useful for later analysis and classification of pathologies. Optic cup is found using their high greylevel variation and their contours are determined by means of morphological techniques. The blood vessels are highlighted using bottom hat transform and morphological dilation after edge detection. All the enhanced features are then combined in the fundus image for the detection of abnormalities in the eye. In this project, we do Segmentation into a piecewise constant structure which requires one more step using optic disc Extraction algorithm (ODE). Since convergence is guaranteed, the technique does not require the intervention of the user to stop the filtering at the desired image quality. This scheme has been tested on a number of retinal images in which the optical disc has been successfully segmented.