A Robust Computer Aided System For Retinal Screening
Author(s):
ANJU K ABRAHAM, SANGEETA T.R
Keywords:
CDR, RDR, GLCM, Color moments, Color histograms, SVM Classifier
Abstract
Diabetic retinopathy (DR) and Diabetic Maculopathy (DM) are nowadays two of the most frequent causes of blindness and vision loss. In addition, these diseases will experience a high growth in the future due to diabetes incidence increase and ageing population in the current society. Computer aided diagnosis system is very much used for medical image screening. There are some limitations to find the fundus diseases from fundus images. This proposed work investigates discrimination capabilities in the texture, color and histogram of fundus images to differentiate between pathological and healthy images. For this purpose, Gray level co-occurrence matrix taken as a texture descriptor, in addition the color and histogram features to increase the feature strength. Initially the optical cup to disk ratio and rim to disc ratio is find out to analyze the glaucoma disease with expert results. Then the DR and DM analyzed with the help of extracted features. Then SVM classifier acting as a classifier to find the diseases. The proposed procedure obtaining promising results. Thus the proposed system well suitable for fundus image screening, compared to other conventional computer aided system methods
Article Details
Unique Paper ID: 146372

Publication Volume & Issue: Volume 4, Issue 12

Page(s): 365 - 370
Article Preview & Download


Share This Article

Join our RMS



Conference Alert

NCSEM 2024

National Conference on Sustainable Engineering and Management - 2024

Last Date: 15th March 2024

Latest Publication

Call For Paper

Volume 10 Issue 10

Last Date for paper submitting for March Issue is 25 June 2024

About Us

IJIRT.org enables door in research by providing high quality research articles in open access market.

Send us any query related to your research on editor@ijirt.org

Social Media

Google Verified Reviews

Contact Details

Telephone:6351679790
Email: editor@ijirt.org
Website: ijirt.org

Policies

Important Links

Browse Rsearch papers