Diabetic retinopathy (DR) is one of the world’s most significant difficulties of diabetes identified with eye illness which happens when veins in the retina become swollen and releases liquid which at last prompts vision misfortune. Early discovery of DR can anticipate the harm to the retina and vision misfortune or atleast moderate its movement. There are various strategies used to distinguish DR in retinal fundus imageries which give inadmissible outcome for certain situations due to the morbidities of fundus images. In this paper, DR is analyzed by separating veins, optic plate and exudates from retinal fundus images by utilizing prediction ANN classifier and RG based segmentation approach. The performance of this segmentation approach is executed for different DR datasets and the outcomes demonstrates that the proposed segmentation approach produces 99% of accuracy in detection of DR which stands out from the various existing strategies.

糖尿病性视网膜病（DR）是世界上最严重的糖尿病之一，被眼部疾病所识别，这种疾病发生在视网膜静脉肿胀并释放出液体时，最终导致视力下降。DR的早期发现可以预期对视网膜的伤害，视力下降或至少减轻其运动。存在多种用于区分视网膜眼底图像中的DR的策略，由于眼底图像的发病率，在某些情况下DR不能给出可接受的结果。在本文中，DR是通过使用预测ANN分类器和基于RG的分割方法从视网膜眼底图像中分离静脉，视盘和渗出液来进行分析的。