Identification of diabetic retinopathy in eye images using transfer learning

Authors:

Abstract
Convolutional Neural Networks have been performing exceptionally well for the recognition of worldly objects and there are various trained models available which can give you the class of an object if an image of the object is fed as their input. But, we can also retrain an already trained model for anotherset of classes of our interest and we have retrained such a model to check the severity of Diabetic Retinopathy in eye images (data has been provided by eyePacs as color fundus images) on the scale of 0-5. A convolutional neural network classifier engineered from Inception V3 network (trained for ImageNet) for 5-class severity classification performed best with an accuracy of 48.2%.

This publication has 7 references indexed in Scilit: