An automated eye disease recognition system from visual content of facial images using machine learning techniques

Abstract

Many eye diseases like cataracts, trachoma, or corneal ulcer can cause vision problems. Progression of theseeye diseases can only be prevented if they are recognized accurately at the early stage. Visually observable symptomsdiffer a lot among these eye diseases. However, a wide variety of symptoms is necessary to be analyzed for the accuratedetection of eye diseases. In this paper, we propose a novel approach to provide an automated eye disease recognitionsystem using visually observable symptoms applying digital image processing techniques and machine learning techniquessuch as deep convolution neural network (DCNN) and support vector machine (SVM). We apply the principal componentanalysis and t-distributed stochastic neighbor embedding methods for better feature selection. The proposed systemautomatically divides the facial components from the frontal facial image and extracts the eye part. The proposedmethod analyzes and classifies seven eye diseases including cataracts, trachoma, conjunctivitis, corneal ulcer, ectropion,periorbital cellulitis, and Bitot’s spot of vitamin A deficiency. From the experimental results, we see that the DCNNmodel outperforms SVM models. We also compare our method with some other existing methods. Our method showsimproved accuracy compared to other methods. The average accuracy rate of our DCNN model is 98.79% with sensitivityof 97% and specificity of 99%.