Automated diagnosis of eye diseases using machine and deep learning models has become increasingly popular. Glaucoma, cataracts, diabetic retinopathy, Myopia, and age-related macular degeneration are common eye diseases that can cause severe damage. It is crucial to detect eye diseases early to prevent any potentially serious consequences. Early detection of eye disease is vital for effective treatment. Doing in-depth reading to identify any potential signs of eye disease is highly recommended. This paper will review all machine learning models built to detect and classify eye diseases in addition to helping grasp all limitations and challenges in this field. Recognizing eye diseases is a difficult task that typically requires several years of medical experience. This research is to be conducted to serve as a starting point for finding the most versatile solution. This research aims to review eye disease classification using deep learning models, including VGG16, ResNet, and Inception. The general classification model consists of these steps: The first step is to collect the globally obtainable datasets for the eye disease and pre-process them to ensure the generalization of experiments. The goal is to train the model to recognize disease symptoms instead of tweaking the outcomes for a specific dataset section. With the successful deployment of deep learning techniques for image classification and object recognition, research is now directed towards deep learning techniques instead of traditional handcrafted methods. One possible solution for the eye diseases classification challenge is to use a pre-trained deep CNN model for representation and feature extraction. This solution can be followed by classifier methods, such as support vector machines (SVM), multilayer perceptron (MLP), etc. It has been detected that CNN-based methods learned on large-scale marked datasets can be used for eye disease classification tasks with limited training datasets.
