Published Paper Details:

Glaucoma is a chronic eye disease that is the second leading cause of blindness all over the world, and a great number of people have been experiencing it. Glaucoma is a group of diseases that cause damage to the optic nerves,which leads to irreversible partial or fullvision loss. Early detection of glaucoma is critical and highly beneficial in preventing further deterioration. Glaucoma can occur at any age and shows no early signs or symptoms, which makes it hard to detect. The final stage leads to complete blindness, and a cure has not been found as of now. So, the only way is to slow down the effects by detecting them at an early stage. And another major drawback is the limited number of glaucoma specialists in our country, which makes it even more difficult to diagnose. Due to these reasons, the project focuses on developing an Android application that takes the fund us image as an input and then predicts whether it is glaucomatous or non- glaucomatous. This system is developed using the CNN algorithm in deep learning, which includes dataset collection, sequential model development,training,testing,model conversion,and application UIdevelopment.The accuracy of this model is found to be around 97%, and there are fewer false positives compared to the previous models. This project can be extended so that it can be used on multiple operating systems and be accessible through a web version. In the future, the fund us image can be extracted from the general eye image itself.