Glaucoma has become a critical problem in the healthcare industry in recent years. Although it is not life-threatening at all times, it is possible for glaucoma to cause permanent blindness. Glaucoma rarely leads to blindness. But once the vision is lost, it is irreversible. Hence, it is essential to diagnose the condition in its early stages in order to minimize the patient’s risk factors. The major goal is to conduct a comparative examination of the accuracy of deep learning models in glaucoma detection. Deep learning is a subcategory of machine learning, which is essentially a neural network with three or more layers. Deep learning models are extensively used in the field of medicine to make diagnoses and prognoses. This work employs the Resnet50, which has an accuracy of 90% when trained and tested with fundus images. ResNet50 outperformed the CNN algorithm. Therefore, the proposed system is believed to provide an effective model that detects glaucoma.