Glaucoma Detection Using Ensemble Techniques with InceptionV3, VGG16 and ResNet50

Glaucoma, a prevalent optic neuropathy, poses a significant threat to vision and requires accurate and timely detection for effective management. Traditional diagnostic approaches face limitations, prompting the integration of advanced technologies such as deep learning models. Employing advanced deep learning models-GoogLeNet(Inception V3), VGG16, and ResNet50-we achieve individual accuracies of 99%, 99%, and 98% respectively on Combined Datasets, Acrima, Drishti-GS1, HRF, ORIGA-LIGHT, and Rim-One. The study further explores the synergy of these models through soft voting ensemble techniques, resulting in a remarkable combined accuracy of 99%.