Convolutional Neural Network Modeling for Eye Disease Recognition

The eye is an important sensing organ of the human body, as it reacts to light and allows vision humans. Many Bangladeshi people become nearsighted when comes awareness loss due disease. Bangladeshis are more concerned about losing their money than getting or blind, a combination poverty illiteracy. With this view, paper proposes osteopathic expert system that can deal with image recognize Here, we have focused on three most common diseases in Bangladesh, namely cataract, chalazion, squint. We modeled six convolutional neural networks (CNN’s), VGG16, VGG19, MobileNet, Xception, InceptionV3, DenseNet121 diseases. reached best configuration each these CNN models after adequate investigation. After performing satisfactory experimentation, found MobileNet model gives performance based accuracy, precision, recall, F1-score. At last, compared our findings recently reported relevant works show efficacy.