Automated Detection of Anatomical Structures in Retinal Images

Siddalingaswamy, PC and Prabhu, G K (2007) Automated Detection of Anatomical Structures in Retinal Images. In: International Conference on Computational Intelligence and Multimedia Applications (ICCIMA 2007) , 13-15 December 2007, Sivakasi, Tamil Nadu, India.

[img] PDF
ICCIMA-07.pdf - Published Version
Restricted to Registered users only

Download (394kB) | Request a copy
Official URL:


An efficient detection of anatomical structures in retinal images is the fundamental step in an automated retinal image analysis system. This paper presents an algorithm for the localization and segmentation of optic disc and fovea. 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. The fovea is identified by finding the darkest region in the image following the priori geometric criteria based on anatomy of human eye. The algorithm is evaluated against a carefully selected database of 50 ocular fundus images. The system achieves a sensitivity of 92% for the optic disc and 94% for the fovea.

Item Type: Conference or Workshop Item (Paper)
Additional Information: Copyright © IEEE Computer Society Washington, DC, USA
Subjects: Engineering > MIT Manipal > Biomedical
Engineering > MIT Manipal > Computer Science and Engineering
Depositing User: MIT Library
Date Deposited: 25 Apr 2011 10:48
Last Modified: 17 Jun 2011 03:50

Actions (login required)

View Item View Item