Detection of Glaucoma using Deep Learning

Abstract

Glaucoma is an incurable disease that impairs vision and livability. We used a convolutional neural network to construct a deep learning framework for the identification of spontaneous eye problem in this study. In-depth instructional strategies, like as convolutional neural networks, might evaluate visual sequences in which glaucoma as well as non-glaucoma characteristics may be segregated for testing objectives. The suggested Deep Learning architecture comprise of six study layers: four conv layers and two completely functional levels. Discontinuation and augmentation methods are utilized to increase the accuracy of glaucoma diagnosis. ORIGA and SCES details have been thoroughly tested.