Glaucoma Eye Disease Detection using Ml

Matha Kavya, Vadisela Jaya Sri, Rayavarapu Thannmye, Tenka Dinesh, Dr.M.Chandra Sekhar
Department of Information Technology, Maharaj Vijayaram Gajapathi Raj College, Vizianagram,Andhra Pradesh, India

Abstract— Glaucoma is a chronic eye disease that leads to irreversible blindness due to progressive damage to the optic nerve. It is one of  the leading causes of vision loss worldwide,particularly among the aging population. Earlydetection is crucial, but it remains challenging  because the disease develops gradually without noticeable symptoms in its initial stages.Traditional diagnostic methods rely on clinical examination and specialized equipment such as fundus imaging and optical coherence tomography, which are expensive and requireskilled ophthalmologists. This makes large-scale screening difficult, especially in rural and resource-limited areas.Recent advancements in deep learning and computer vision have significantly improved automated glaucoma detection using retinal fundus images. Variousapproaches, including Convolutional Neural Networks, multi-task learning models, and hybrid techniques, have demonstrated high accuracy in medical image analysis.In this project, a glaucoma detection system is developed using the YOLO (You Only Look Once) object detection algorithm. The system identifies importantregions such as the optic disc and analyzes them to detect signs of glaucoma. A fundus image dataset is used for training and testing the model, ensuring accurate classification of normal and glaucomatous eyes.The YOLO-based approachoffers advantages such as real-time detection, high accuracy, and computational efficiency, making it suitable for large-scale screening applications. The proposed system aims to assist ophthalmologists in early diagnosis and improve accessibility to glaucoma screening, thereby reducing the risk of vision loss.