Download PDFOpen PDF in browser

Early Detection of Diabetic Retinopathy Using Deep Convolutional Neural Network

EasyChair Preprint 3604

6 pagesDate: June 14, 2020

Abstract

Diabetic Retinopathy is basically an eye oddity that is caused due to the long-term effects of a disease called diabetes. As this abnormality propagates it leads to blurry vision. The detection of DR using colored and detailed images requires skilled doctors in order to identify the presence of minute but critical features which makes it a challenging and tedious task.

In our research we have used digital images for diagnosing  DR. In this research we implemented a new technique in which the full image is divided into various regions and only the regions which are useful are taken into consideration for testing. CNN's approach turns out to be very useful in terms of pace and precision. An accuracy of approx. 93.3% is obtained from CNN in this problem.

Keyphrases: CNN, Classification, DR(Diabetic Retinopathy)

BibTeX entry
BibTeX does not have the right entry for preprints. This is a hack for producing the correct reference:
@booklet{EasyChair:3604,
  author    = {Aditya Mogha and K. Thirunavukkarasu},
  title     = {Early Detection of Diabetic Retinopathy Using Deep Convolutional Neural Network},
  howpublished = {EasyChair Preprint 3604},
  year      = {EasyChair, 2020}}
Download PDFOpen PDF in browser