By Topic

Detection of Diabetic Retinopathy in Fundus Images using Vector Quantization Technique

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Satyarthi, D. ; Dept. of Electron. & Commun. Eng., Indian Inst. of Technol., Guwahati ; Raju, B.A.N. ; Dandapat, S.

Diabetic retinopathy is one of the major cause of blindness among the people. Many approaches are proposed by the authors to automate and detect the presence of diabetic retinopathy in fundus image. We propose a novel method of detection of the diabetic retinopathy using Gaussian intensity feature input to a VQ classifier. The underlying idea of using this technique in fundus imaging is that there are certain features which pertain only to diabetic retinopathy. These features are extracted in terms of diameter of the blood vessels expressed by sigma, and the height of the Gaussian profile across the cross-section, given by h. In this work, 30 images are taken as normal images and 25 pathological images are considered. A successful average diagnostic performance of 90% is achieved in this method

Published in:

India Conference, 2006 Annual IEEE

Date of Conference:

Sept. 2006