Retinal Vessel Segmentation employing Neural Network and Feature Extraction

Diabetic retinopathy, Glaucoma, Hypertension are the most common sight threatening eye diseases due to the changes in the blood vessel structure. The retinal blood vessel segmentation helps to identify the successive stages of a these diseases and thus helps to treat them at early stages. Blood vessel segmentation by making use of multilayer perceptron neural network is one such technique used for the segmentation of retinal blood vessels. As it provides the ability to identify and classify the image pixels as vessels or non vessels automatically, but it fails to achieve high accuracies. It is unable to segment the vessels of varying width and small size. Thus this research work provides the blood vessel segmentation with neural network, which gives more efficient results on fundus images.