Detection of glaucoma from fundus image using pre-trained Densenet201 model

In recent years, the performance of deep learning algorithms for image recognition has improved tremendously. The inherent ability of a convolutional neural network has made the task of classifying glaucoma and normal fundus images more appropriately. Transferring the weights from the pre-trained model resulted in faster and easier training than training the network from scratch. In this paper, a dense convolutional neural network (Densenet201) has been utilized to extract the relevant features for classification. Training with 80% of the images and testing with 20% of the images has been performed. The performance metrics obtained by various classifiers such as softmax, support vector machine (SVM), knearest neighbor (KNN), and Naive Bayes (NB) have been compared. Experimental results have shown that the softmax classifier outperformed the other classifiers with 96.48% accuracy, 98.88% sensitivity, 92.1% specificity, 95.82% precision, and 97.28% F1-score, with DRISHTI-GS1 database. An increase in the classification accuracy of about 1% has been achieved with enhanced fundus images.