Diabetes mellitus in people causes damage to vessels in eyes, kidneys, heart and nervous systems and diabetic retinopathy (DR) is an important hurdle in diabetic people and it causes lesion formation in retina. Bright lesions (BLs) are initial clinical sign of DR. Early BLs detection can help avoiding vision loss. The severity can be recognized based on number of BLs in the color fundus image. Manually diagnosing a large amount of images is time consuming.  So a computerized DR grading and BLs detection system is proposed. For BLs detection, the optic disk (OD) and vessel structures are segmented and eliminated by thresholding techniques. Publicly available databases are used for DR severity testing. The support vector machine classifier (SVM) used to separate fundus images in various levels of DR based on feature set. The proposed system obtained the better results compared to the existing techniques in terms of statistical measures sensitivity, specificity and accuracy.

diabetic retinopathy, bright lesions, feature extraction, classification, segmentation, support vector machine classifier.