Neural Network Based Diagnosis of Glaucoma

Glaucoma is one of the major reasons for blindness. Untreated glaucoma can lead to permanent damage of the optic nerve and resultant visual field loss, which over time can progress to blindness. For this reason, early detection of glaucoma is essential for affected patients. This paper is focused on classifying glaucoma with image-based features from fundus photographs. So in this work, we have detected the glaucoma disease in the retinal optical images. The extent of the disease spread can be identified by extracting the features of the retina. Detection of the disease is done using Probabilistic Neural Network (PNN) classifier. The accuracy of the proposed system is 94.54 %.