Recognition of Diabetic Retinopathy Basedon Transfer Learning

Diabetic retinopathy (DR) is a kind of eyes disease caused by diabetes. With the development of science and technology, vision plays an increasingly important role in people's daily life. Therefore, how to automatically classify diabetic retinopathy images has significant value. The traditional manual classification method requires knowledge and time and it's difficult to obtain an objective and unified medical diagnosis. Therefore, this paper proposes a method for diabetic retinopathy recognition based on transfer learning. First, download data from Kaggle's official website, then perform data enhancement, include data amplification, flipping, folding, and contrast adjustment. Then, use pretrained model such asVGG19, InceptionV3, Resnet50 and so on. Each neural network has been trained by ImageNet dataset already. What we need to do is migrate the DR images to these models. Finally, the images are divided into 5 types by the serious degree of diabetic retinopathy. The experimental results shows that the classification accuracy of this method can reach at 0.60, which is better than the traditional direct training method and has better robustness and generalization.