ABSTRACT
Detection of eye pathologies from the database of iris images is taken intodeliberation. The images of disease affected and normal eyes are taken from High Resolution Fundus (HRF) Image Data base and the influence of ocular diseases on iris is determined using areliable Artificial Neural Network (ANN) based recognition scheme. Nearly, 45 samples of iris are acquired using Canon CR-1 fundus camera with a field of view of 45° when subjected to routine ophthalmology visits and the samples of eye images include healthy eyes, eyes affected by glaucoma, cataract and diabetic retinopathy. These images are then subjected to various image processing techniques like pre-processing for de-noising and feature extraction using wavelet, followed by Feed Forward Neural Network (FFNN) trained with Back Propagation Algorithm (BPA) inference scheme to categorize the normal and diseased eyes. Finally the results for the proposed method is evaluated using performance measures like sensitivity, specificity, accuracy and time take for online diagnosis against the other methods developed various other researchers. It is inferred that the proposed method takes only 2 minutes with efficiency in the range of 98% to 99.9% respectively.
