Glaucoma refers to the accumulated loss of retinal cells within the optic nerve or the gradual visual loss caused by optic neuropathy. It is an illness that affects vision in the eye and is considered an irreversible condition that leads to degradation of eyesight. There are often no early warning signs of glaucoma, making it difficult to notice changes in vision due to subtle effects. To date, a large number of Deep Learning (DL) models have been developed for the accurate diagnosis of glaucoma. This work proposes an architecture for deep learning-based glaucoma detection using Convolutional Neural Networks (CNNs). CNNs can distinguish between patterns associated with glaucoma and non-glaucoma conditions, providing a hierarchical structure for classification. Using the proposed method, the disease is detected based on the optic cup-to-disc ratio. The diagnosis is further enhanced by integrating an image data generator for data augmentation. The results demonstrate that the proposed model achieved 98% accuracy, outperforming many existing algorithms.