Optic disc detection by multi-scale gaussian filtering with scale production and a vessels' directional matched filter

Authors:
Bob Zhang;Fakhri Karray
Affiliations:
Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, ON, Canada;Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, ON, Canada
Venue:
ICMB'10 Proceedings of the Second international conference on Medical Biometrics
Year:
2010

Citing 3
Cited 1

Segmentation of Color Fundus Images of the Human Retina: Detection of the Optic Disc and the Vascular Tree Using Morphological Techniques

ISMDA '01 Proceedings of the Second International Symposium on Medical Data Analysis
Comparison of Colour Spaces for Optic Disc Localisation in Retinal Images

ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 1 - Volume 1
A Model-Based Approach for Automated Feature Extraction in Fundus Images

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2

Detecting optic disc on asians by multiscale gaussian filtering

Journal of Biomedical Imaging - Special issue on Advances in Computer-Aided Detection and Diagnosis

Quantified Score

Hi-index	0.00

Visualization

Abstract

The optic disc (OD) is an important anatomical feature in retinal images, and its detection is vital for developing automated screening programs. In this paper we propose a method to automatically detect the OD in fundus images using two steps: OD vessel candidate detection and OD vessel candidate matching. The first step is achieved with multi-scale Gaussian filtering, scale production, and double thresholding to initially extract the vessels' directional map. The map is then thinned before another threshold is applied to remove pixels with low intensities. This result forms the OD vessel candidates. In the second step, a Vessels' Directional Matched Filter (VDMF) of various dimensions is applied to the candidates to be matched, and the pixel with the smallest difference designated the OD center. We tested the proposed method on a subset of a new database consisting of 139 images from a diabetic retinopathy (DR) screening programme. The OD center was successfully detected with an accuracy of 96.4% (134/139).