Spotting Of Glaucoma Using A Minimal Approach With Ternary Level Convolutional Neural Network

Abstract

Glaucoma is an eye disease that leads to vision loss by causing damage to the optic nerve. A novel method namely Tripartite Tier Convolutional Neural Network Scheme (TT_CNN Scheme) was proposed for detection of glaucoma. The proposed model contains three layers namely left tier, middle tier and right tier. This model is designed in such a way that shows improved result. Multiple .classifiers are used for classifying the fundus images as normal or glaucomatous images. Random Forest Classifier shows improved results than other classifiers. This TT_CNN Scheme has been analysed using MIAG RIMONE (Release2) database and MIAG RIMONE (Release3) database and obtained result is compared with the results of LP_LDS method. The performance metrics illustrates enhanced results for TT_CNN Scheme than LP_LDS method