Effective Detection of Diabetic Retinopathy From Human Retinal Fundus Images Using Modified FCM and IWPSO

Diabetic Retinopathy is an eye disease caused in patients with diabetic which leads to blindness. So, detection of Diabetic retinopathy at early stage prevents loss of vision. In this paper, we proposed an effective segmentation method that combines modified Fuzzy C Means (FCM) clustering with spatial features and Inertia Weight Particle Swarm optimization (IWPSO) for detection of Diabetic Retinopathy. The input human retinal fundus images are filtered by a median filter to reduce speckle noise and then contrast enhancement is done by Adaptive Histogram Equalization. Then segmented by various methods like Chaotic Particle Swarm optimization (CPSO), Inertia Weight Particle Swarm optimization (IWPSO) and our proposed method. The performance of these methods is analyzed using the metrics Accuracy, True Positive Rate (Sensitivity), True Negative Rate (Specificity), False Positive Rate and False Negative Rate. A comparative analysis has been made for the above said segmentation algorithms and the results proved that our proposed method achieved the best than the other methods.