Published Paper Details:

The project is intended to create a cost-effective and easy-to-use eye disease detection and classification system for children and adults in economically underprivileged regions. The system proposed is either a mobile or a Desktop Application. The system takes as input a photo of an unadorned human eye. The picture of the eyes can be taken through a basic mobile camera or laptop camera without too much worry about light or lighting. The system can identify eye diseases such as cataracts, glaucoma, and other diseases where intervention by doctors for disease prediction is needed. The proposed method utilizes an algorithm that makes use of the VGG-19 Convolutional Neural Network (CNN) model with normalization techniques to categorize fundus images into five distinct classes: Cataract, Diabetic, Glaucoma, Normal, and Other. The primary objective is to provide an accessible technology for early detection and intervention of eye disorders in underserved communities. By employing a robust deep-learning model, we intend to enhance visual health outcomes and overall well-being among children and adults in these regions. The user-friendly interface and affordability of the system play pivotal roles in facilitating its seamless deployment and effective use, addressing the healthcare access disparity prevalent in these communities.