Abstract
Diabetic Retinopathy is one of the ophthalmic reasons for visual deficiency. The favored fixate of consideration is on the estimation of deviation in the breadth of the retinal veins and the new vessel development. To witness the progressions, segmentation has to be made primarily. A framework to improve the quality of the segmentation result over pathological retinal images is proposed. The proposed method uses adaptive histogram equalizer for preprocessing, pulse coupled neural Network model for automatic feature vector generation and extraction of the retinal blood vessels. The test result represents that the proposed method is enhanced than other retinal competitive methods. The evaluation of the proposed approach is executed over standard public DRIVE, STARE, REVIEW, HRF, and DRIONS fundus image datasets. The proposed technique improves the segmentation results in terms of sensitivity, specificity, and accuracy.