Abstract
Glaucoma is a serious eye disease that affects a lot of people around the world. Deep learning architectures have been widely used in recent years for image recognition tasks. In this paper, we aim to detect human eye infections of Glaucoma disease by firstly using different machine learning (ML) classifiers such as Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Naive Bayes (NB), Multi-layer perceptron (MLP), Decision Tree (DT) and Random Forest (RF), and secondly a Deep Learning (DL) model such as Convolutional Neural Network (CNN) based on Resnet152 model. The evaluation of the proposed approach is performed on the Ocular Disease Intelligent Recognition dataset. The obtained results showed that the RF and MLP classifiers achieved the highest accuracy of 77% in comparison to the other ML classifiers. On the other hand, the deep learning model (CNN model: Resnet152) provides an even better accuracy of 84% for the same task and dataset. Furthermore, we observe our best performing model produce competitive results in comparison to some state-of-the-art approaches.