Human eye is very sensitive organ. Many important eye diseases as well as systemic diseases manifest themselves in the retina of the eye and retinal image analysis is very intricate task. Automated retinal image analysis for disease detection is very important for early diagnosis of eye diseases like diabetic retinopathy (DR).DR is a condition where the retina is damaged due to fluid leaking from the blood vessels into the retina in the diabetic patients. In extreme cases, the patient would lose his vision completely. Hence, early detection of diabetic retinopathy condition is very crucial to prevent blindness. This paper aims at developing an algorithm for early detection of DR condition and classification of retinal images. This paper includes extraction of abnormalities like Exudates from retinal images using K-means lustering and Top-Hat and Bottom-Hat operations, also classifying a retinal image as healthy or abnormal using K-NN classifier.