Computerized Exudate Detection in Fundus Images Using Statistical Feature based Fuzzy C-mean Clustering

Diabetic retinopathy(DR) is considered as the root cause of vision loss for diabetic patients .One of the greatest concern and immediate challenges to the current health care is the severe progression of diabetes. Diabetic retinopathy is an eye disease and appearance of hard exudates is one of its earliest signs. The accuracy of the automated disease identification techniques should be high .Besides being accurate; the techniques need to possess a quick convergence rate enabling them to be suitable for real-time applications. In order to lessen the cost of these screenings, modern image processing techniques are used to voluntarily detect the existence of abnormalities in the retinal images acquired during the screenings. Hard and Soft exudates (Cotton wool spots) are a major indicator of diabetic retinopathy that can possibly be quantified automatically. Automatic computerized screening should facilitate screening process, reduce inspection time and increase accuracy. In this paper an automated method to detect exudates from low-contrast digital images of retinopathy patients with non-dilated pupils using feature based Fuzzy C-Means (FCM) clustering technique with a combination of morphology techniques and pre-processing to improve the robustness of blood vessel and optic disk detection. Pre-processing involve colour, normalization ,contrast enhancement and brightness preserving dynamic fuzzy histogram equalization whereas addressable features are converted colour spaces, intensity, standard deviation, edge strength, size, colour, texture and entropy. The detection accuracy is calculated with comparison to expert ophthalmologists’ hand-drawn ground-truths and the results are comparatively analysed.