Morphological process based segmentation for the detection of exudates from the retinal images of diabetic patients

Diabetic Retinopathy is an ocular systemic disease caused by complication of diabetes. It is a major cause of blindness in both middle and advanced age group. Earlier recognition of diabetic retinopathy shields understanding from visual impairment. The heading side effect of this difficulty seeing is the exudates. Exudates are the melted watery grasping solutes, proteins, cells, or cell garbage spilled from the harmed veins into near by tissues or on tissue surfaces in the retina. The spillage of these proteins or lipids causes vision misfortune to the patients. Distinguishing the exudates ahead of time can protect the diabetic patients from difficulty seeing. Ophthalmologists use widening system to identify the exudates. But it causes the irritation to the patients' eyes. This paper focuses on an automated method which detects the diabetic retinopathy through identifying exudates by Morphological process in colour fundus retinal images and then segregates the severity of the lesions. The severity level of the disease was achieved by Cascade Neural Network (CNN) classifier.