Automated Detection of Optic Disc and Exudates in Retinal Images

Siddalingaswamy, PC and Prabhu, G K (2009) Automated Detection of Optic Disc and Exudates in Retinal Images. In: 13th International Conference on Biomedical Engineering, 3-6 December 2008, Singapore.

[img] PDF
ICBME_02.pdf - Published Version
Restricted to Registered users only

Download (537kB) | Request a copy
Official URL: http://www.springerlink.com/content/h568355638pu72...

Abstract

Digital colour retinal images are used by the ophthalmologists for the detection of many eye related diseases such as Diabetic retinopathy. These images are generated in large number during the mass screening of the disease and may result in biased observation due to fatigue. Automated retinal image processing system could save workload of the ophthalmologists and also assist them to extract the normal and abnormal structures in retinal images and help in grading the severity of the disease. In this paper we present a method for automatic detection of optic disc followed by classification of hard exudates pixels in retinal image. Optic disc localization is achieved by iterative threshold method to identify initial set of candidate regions followed by connected component analysis to locate the actual optic disc. Exudates are detected using k means clustering algorithm. The algorithm is evaluated against a carefully selected database of 100 color retinal images at different stages of diabetic retinopathy. The methods achieve a sensitivity of 92% for the optic disc and 86% for the detection of exudates.

Item Type: Conference or Workshop Item (Paper)
Additional Information: Copyright © Springer
Uncontrolled Keywords: Diabetic retinopathy;Optic disc;Exudates;clustering
Subjects: Engineering > MIT Manipal > Biomedical
Engineering > MIT Manipal > Computer Science and Engineering
Depositing User: ePrints@MU Administrator
Date Deposited: 25 Apr 2011 09:39
Last Modified: 17 Jun 2011 04:04
URI: http://eprints.manipal.edu/id/eprint/1

Actions (login required)

View Item View Item