Automatic Exudates Detection from Non-dilated Diabetic Retinopathy Retinal Image Using Fuzzy C-means Clustering

Exudates are the primary signs of diabetic retinopathy which are mainly cause of blindness. It could be prevented with an early screening process. Pupil dilation is required in the normal screening process but this affects patients’ vision. Automatic computerized screening should facilitate screening process, reduce inspection time and increase accuracy. In this paper we proposed an automatic method to detect exudates from low-contrast digital images of retinopathy patients with non-dilated pupils using a Fuzzy C-Means (FCM) clustering technique. Intensity, standard deviation on intensity, hue and a number of edge pixels, were selected as main features to supply to FCM method. The number of cluster optimization was based on sensitivity and specificity which were calculated by comparison of the detected results and hand-drawn groundtruths from expert ophthalmologists. From the result, it is found that the proposed method detected exudates successfully with high accuracy of 92.18 % and 91.52 % for sensitivity and specificity respectively.