Abstract

Retinal images are widely used for diagnostic purposes by ophthalmologists. Therefore, these images are suitable for digital image analysis for their visual enhancement and pathological risk or damage detection. In this paper, the optic disc segmentation and optic cup segmentation processes are used to detect and segment the blood vessels from the retinal image for indicate the normal and retinal disease diagnosis. The proposed system consists of following further steps for analysis of fundus images. At first the preprocessing of retinal image to enhance by using the Contrast Limited Adaptive Histogram Equalization CLAHE, before enhancement of the Retinal Image, which is filtered and removed unwanted noises from images using Median Filtering Method and after enhancement of the images, the Optic Disc segmentation is done by using Improved Markov random field (IMRF) and Optic Cup blood vessel segmentation using Artificial Neural Network (ANN) classifier. The proposed retinal image analysis system performance is analyzed by using publicly available retinal image dataset.

Paper Details