Exact Detection of Optic Disc in Retinal Images Using Segmentation Based On Level Set Method and Morphological Operations

Abstract

In this thesis we tried to localize the most important region of eye – optic disc using an approach based on level set method of segmentation. The optic disc is the region on the retina at which optic nerve axons enter and leave the eye. Changes in optic disc shape and area may indicate disease processes, particularly glaucoma, and accurate identification of the disk boundary may be used to quantify changes. The proposed algorithm consists of two steps – in first step, preprocessing of image is done using morphology operations and in second step, boundary of optic disc is detected using level set method. These pre-processing operations minimize erroneous boundary detection of optic disc due to blood vessels crossing it. Preprocessing techniques based on morphological operations of dilation, erosion and reconstruction are developed. After pre-processing, the optic disk boundary was determined using level set method.