A Survey on Automated Eye Disease Detection using Computer Vision Based Techniques

Abstract

Due to recent advancements in the field of Artificial Intelligence (AI), many recent techniques have been developed to objectively identify diseases using images or videos. Eye-related diseases are one of the commonly occurring diseases in the human body. Many diseases can manifest in the eye such as Diabetic Retinopathy (DR), glaucoma, dry eye, Age Related Macular Degeneration (ARMD), cataract, keratoconus and so on. These diseases can cause severe discomfort in patients eye leading to vision loss, blurred vision or photophobia, highly impacting the quality of life of patients. Various AI and image processing techniques have been developed to assist ophthalmologists to diagnose the disease precisely as well as reducing healthcare cost. This paper reviews techniques utilizing machine learning and deep learning to detect eye diseases namely ARMD, cataract, DR and glaucoma. It is observed that the accuracy of AI based techniques outperforms manual feature extraction and classification techniques in all four disease detection areas.