Genetic Algorithm for Retinal Image Analysis

Diabetic Retinopathy is one of the leading causes of blindness. Hard exudates have been found to be one of the most prevalent earliest clinical signs of retinopathy. Thus, identification and classification of hard exudates from retinal images is clinically significant. For this purpose the images from the hospitals were taken as reference. In this work, Genetic Algorithm (GA) for best feature selection from retinal images is proposed. The features that improve the classification accuracy are selected by Genetic Algorithm and termed as optimized feature set. The others that degrade the performance are rejected at the end of specified generation (in this case 100 generations).