Published Paper Details:

Diabetes occurs when the pancreas fails to secrete enough insulin, slowly affecting the retina of the human eye. As it progresses, the vision of a patient starts deteriorating, leading to diabetic retinopathy. In this regard, retinal images are collected from DRIVE dataset images which are analyzing the consequences, nature, and status of the effect of diabetes on the eye. The objectives of this work are to (i) detect blood vessel, (ii) identify hemorrhages and (iii) classify different stages of diabetic retinopathy into normal or abnormal. The basis of the classification of different stages of diabetic retinopathy is the detection and quantification of blood vessels and hemorrhages present in the retinal image. Retinal vascular is segmented utilizing the contrast between the blood vessels and surrounding background. Hemorrhage candidates were detected using density analysis and bounding box techniques. Finally, classification of the different stages of eye disease was done using Random Forests technique based on the GLCM and LBP features of the blood vessels and hemorrhages. The proposed methodology for detection and grading of Diabetic Retinopathy is divided into following stages such as preprocessing, Optic Disc Removal, Blood Vessel Segmentation and Removal, Features Extraction and classification.