Detection of Microaneurysms in Color Retinal Images Using Multi-orientation Sum of Matched Filter

DOI

10.2991/icmt-13.2013.164How to use a DOI?

Keywords

Microaneurysms detection · Color retinal image · Matched filter

Abstract

This paper presents a new method to detect retinal microaneurysms, which are the first sign of diabetic retinopathy (DR). The methods of automatic microaneurysm detection can be generally classified into two groups: filtering based methods and supervised methods. The detection accuracy of the filtering based methods is affected by the background noises and the small vessels. The supervised methods generally have better accuracy by feature sets extraction and training. But the computational cost of feature sets extraction is very high, which makes the supervised methods not suitable for large population screening. And the accuracy of supervised methods will affected by training samples. This paper presents a new method to detect retinal microaneurysms using Multi-orientation Sum of Matched Filter (MSMF), which can well suppress the affection of background noises and the small vessels. Experimental results show that our method is fast and effective in microaneurysm detection.

Copyright

© 2013, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Li Qin
AU  - Lu Ruixiang
AU  - Miao Shaoguang
AU  - You Jane
PY  - 2013/11
DA  - 2013/11
TI  - Detection of Microaneurysms in Color Retinal Images Using Multi-orientation Sum of Matched Filter
BT  - Proceedings of 3rd International Conference on Multimedia Technology(ICMT-13)
PB  - Atlantis Press
SP  - 1334
EP  - 1341
SN  - 1951-6851
UR  - https://doi.org/10.2991/icmt-13.2013.164
DO  - 10.2991/icmt-13.2013.164
ID  - Qin2013/11
ER  -