An Efficiency Analysis for Detection of Exudates in Color Images using Clustering Algorithms

Abstract

This research work enhances the process of exudates detection using two algorithms. The objective of system is to increase the performance and reduces the time factor while extracting the features from the color images. The preprocessed color retinal images are segmented using K-Means Clustering technique. The segmented images establish a dataset of regions. To classify these segmented regions into Exudates and Non-Exudates, a set of features based on color and texture are extracted. The contrast adaptive histogram equalization is used for preprocessing stage and Fuzzy C-Means (FCM) and k-Means clustering algorithms are applied to segment the exudates in abnormal input images. A set of features such as the standard deviation, mean, energy, entropy and homogeneity of the segmented regions are extracted and fed as inputs into random forest (RF) classification to discriminate between the normal and pathological image. At finally, calculate the time factor and analyzing the performances of proposed approach.

Keywords: Eexudates detection, K-Means, fuzzy c-Means, variance, Entrophy.