This paper presents a deep learning framework for the early detection of glaucoma in retinal fundus images. Glaucoma is a serious eye disease that can lead to permanent blindness if not detected early. The study uses publicly available datasets, including ORIGA, STARE, and REFUGE, to train and test a convolutional neural network (CNN) model. The model employs AlexNet, VGG16, ResNet50, and InceptionV3, with ResNet50 and InceptionV3 being combined to create a hybrid model. The hybrid model achieved high accuracy, with F1 scores of 97.4% for ORIGA, 99.1% for STARE, and 99.2% for REFUGE. The proposed framework provides a reliable diagnostic system for glaucoma, aiding ophthalmologists in early detection and diagnosis. The study highlights the effectiveness of deep learning in medical image processing, particularly in retinal fundus image analysis. The results demonstrate that the proposed methodology can significantly improve the accuracy and efficiency of glaucoma diagnosis. The study also discusses the challenges of using deep learning in medical imaging, including the need for large datasets and the importance of accurate segmentation and classification techniques. The authors conclude that the proposed framework has the potential to enhance the early detection of glaucoma and improve the overall efficiency of medical diagnosis.This paper presents a deep learning framework for the early detection of glaucoma in retinal fundus images. Glaucoma is a serious eye disease that can lead to permanent blindness if not detected early. The study uses publicly available datasets, including ORIGA, STARE, and REFUGE, to train and test a convolutional neural network (CNN) model. The model employs AlexNet, VGG16, ResNet50, and InceptionV3, with ResNet50 and InceptionV3 being combined to create a hybrid model. The hybrid model achieved high accuracy, with F1 scores of 97.4% for ORIGA, 99.1% for STARE, and 99.2% for REFUGE. The proposed framework provides a reliable diagnostic system for glaucoma, aiding ophthalmologists in early detection and diagnosis. The study highlights the effectiveness of deep learning in medical image processing, particularly in retinal fundus image analysis. The results demonstrate that the proposed methodology can significantly improve the accuracy and efficiency of glaucoma diagnosis. The study also discusses the challenges of using deep learning in medical imaging, including the need for large datasets and the importance of accurate segmentation and classification techniques. The authors conclude that the proposed framework has the potential to enhance the early detection of glaucoma and improve the overall efficiency of medical diagnosis.