Glaucoma is a degenerative eye disease that can lead to blindness when it damages the optic nerve. It’s likely that because there are no early symptoms, a person won’t notice a decrease in vision until it gets worse. Therefore, early detection and regular, adequate eye exams are crucial to minimizing vision loss. One of the methods used to increase the speed of diagnosis of diseases and facilitate early diagnosis is the application of artificial intelligence in medical fields. Researchers are more interested in creating deep learning algorithms that can quickly and accurately identify glaucoma damage in diagnostic tests when compared to manual methods. In this study, we used eye scan pictures to provide a deep learning-based method for classifying glaucoma. Using transfer learning, we evaluated the performance of pre-trained Convolutional Neural Networks such as ResNet, InceptionV3, VGG-16, and Xception on a publicly available dataset. As a result of the study, the highest accuracy score of 0.94 was obtained using InceptionResNetV2, and DenseNet169 models. Based on the findings, it can be concluded that deep learning techniques can be used in glaucoma classification, the models used can detect medical images, customization increases this ability, making these models a valuable tool for medical image analysis.