Determination of Glaucoma Disease with Gray Level Co-occurrence Matrix Features

Glaucoma is a disease that causes an abnormal increase in intraocular pressure and therefore permanent damage to the optic nerves. Early accurate diagnosis of disease, known as most "insidious" among eye diseases, important. In this study, glaucoma prediction application was performed from high-resolution fundus photographs taken open-source database. Correlation, energy, homogeneity, contrast entropy features were extracted segmented using gray-level co-occurrence matrix. Extracted divided into 66% test 33% training after taking their average values. A 3-fold cross-validation applied data feedback artificial neural network, classification regression trees algorithm k nearest neighbor trained data. Classification success also tested with As result, healthy individuals classified 86.7% accuracy algorithm, 87.8% decision trees, 96.7% network algorithm. According results obtained, it seen could be detected high matrix disease.