An eye infection is a condition affecting the eyes that can be caused by a bacterium, virus, or fungus. Numerous eye infections exist, such as glaucoma, cellulitis, keratitis, and conjunctivitis. A few of the symptoms may be itching, discharge, altered eyesight and others. Antibiotics are not effective in treating viral infections. Antibiotics treat infections caused by bacteria exclusively. A class of eye infection known as glaucoma can result in blindness and visual loss by harming the optic nerve, a nerve located at the back of the eye. You might not notice the symptoms at first because they can appear so slowly. A thorough dilated eye exam is the only way to determine if you have glaucoma . Efforts have been done to automate the procedures for the recognition and classification of glaucoma. In this paper, we have proposed a transfer learning model by reviewing pre-trained models and the model is able to provide a better accuracy. Our model is classifying the datasets into positive and negative cases during testing and validation. We utilize different prêt rained models, that are ResNet50 (90%), EffiecintNet (78%) and CNN(79%) evaluate how well they perform when trained using various optimizers. Our results show differences in accuracy and provide important information about the possibility of these models for the detection of glaucoma. An important first step towards improving the precision and dependability of glaucoma detection models in clinical settings is represented by this work.
Keywords
Glaucoma, Transfer learning, ResNet50, EffientNet, CNN.
