An efficient approach for detecting exudates in diabetic retinopathy images.

The blood vessels are responsible for supplying the blood throughout the entire region of the retina. The retinal blood vessels are damaged due to the ageing of the people and other factors such as blood pressure. Exudates lesions are formed in retinal image due to the damage in retinal blood vessels. Ignoring these lesion symptoms leads to the loss of vision, as these symptoms are not exposed easily and requires diagnosis at an earlier stage. In this paper, the hard and soft exudates are detected and segmented using mathematical morphological operations. The proposed algorithm for soft and hard exudates detection is applied over the retinal images of MESSIDOR dataset. The sensitivity of 96.1% and specificity of 94.6% are achieved for soft exudates detection. The sensitivity of 98.71% and specificity of 99.56% are achieved for hard exudates detection.