Review on restoration of vision in glaucoma through image processing using machine learning techniques

Abstract

Glaucoma is the silent vision thief. Early detection of glaucoma is almost impossible and there is currently no solution for glaucoma in its later stages. This study focused on a variety of automated glaucoma detection techniques. An extensive literature review was performed on preprocessing, feature extraction, feature selection, machine learning (ML) methods, and the dataset used for testing and training. Automated glaucoma prediction is essential, but unfortunately, only a small amount of work has been done in this area and only a minimal level of accuracy has been achieved. However, automatic glaucoma detection has advanced to the point where most machine learning techniques can accurately detect 85% of glaucoma patients. Optical coherence tomography (OCT) can be used to predict the outcome of surgery-induced glaucoma.