Eye Glaucoma Detection Using Machine Learning

Information Science & Engineering

ABSTRACT Glaucoma is a chronic eye disease leading to irreversible blindness by damaging the optic nerve of the eye. It is caused due to elevated intraocular pressure inside the eye. Detecting glaucoma is the most challenging process in the case of open-angle glaucoma (OAG) due to the lack of initial symptoms. In this paper, we propose an image processing technique to analyze and categorize the fundus image of the eye as a glaucomatous or healthy image based on the cup-to-disc ratio (CDR) value and feature extracted through Deep learning. The assessment of CDR is the foundation to detect glaucoma, the CDR value will increase from 0.6 – 0.9 when affected by this disease. Image processing techniques are used to extract the optic cup and optic disc region in the fundus image, and further by calculating the CDR value glaucomatous images are categorized. Overfitting is avoided by adopting a data augmentation technique. . The system is trained and the results demonstrate that the technique had a good accuracy in classifying the fundus images as healthy or glaucoma.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.