In this paper, we present an approach to improve microaneurysm detection in digital color fundus images. Instead of following the standard process which considers preprocessing, candidate extraction and classification, we propose a novel approach that combines several preprocessing methods and candidate extractors before the classification step. We ensure high flexibility by using a modular model and a simulated annealing-based search algorithm to find the optimal combination. Our experimental results show that the proposed method outperforms the current state-of-the-art individual microaneurysm candidate extractors.
Description
Improving microaneurysm detection using an optimally selected subset of candidate extractors and preprocessing methods - ScienceDirect
%0 Journal Article
%1 ANTAL2012264
%A Antal, Bálint
%A Hajdu, András
%D 2012
%J Pattern Recognition
%K retinopathy
%N 1
%P 264 - 270
%R https://doi.org/10.1016/j.patcog.2011.06.010
%T Improving microaneurysm detection using an optimally selected subset of candidate extractors and preprocessing methods
%U http://www.sciencedirect.com/science/article/pii/S0031320311002780
%V 45
%X In this paper, we present an approach to improve microaneurysm detection in digital color fundus images. Instead of following the standard process which considers preprocessing, candidate extraction and classification, we propose a novel approach that combines several preprocessing methods and candidate extractors before the classification step. We ensure high flexibility by using a modular model and a simulated annealing-based search algorithm to find the optimal combination. Our experimental results show that the proposed method outperforms the current state-of-the-art individual microaneurysm candidate extractors.
@article{ANTAL2012264,
abstract = {In this paper, we present an approach to improve microaneurysm detection in digital color fundus images. Instead of following the standard process which considers preprocessing, candidate extraction and classification, we propose a novel approach that combines several preprocessing methods and candidate extractors before the classification step. We ensure high flexibility by using a modular model and a simulated annealing-based search algorithm to find the optimal combination. Our experimental results show that the proposed method outperforms the current state-of-the-art individual microaneurysm candidate extractors.},
added-at = {2019-11-11T10:33:26.000+0100},
author = {Antal, Bálint and Hajdu, András},
biburl = {https://www.bibsonomy.org/bibtex/21260df898c6139edd3d86ab27fe9098a/gnoyel},
description = {Improving microaneurysm detection using an optimally selected subset of candidate extractors and preprocessing methods - ScienceDirect},
doi = {https://doi.org/10.1016/j.patcog.2011.06.010},
interhash = {f4cd45ddd37f773c355a5298191e159e},
intrahash = {1260df898c6139edd3d86ab27fe9098a},
issn = {0031-3203},
journal = {Pattern Recognition},
keywords = {retinopathy},
number = 1,
pages = {264 - 270},
timestamp = {2019-11-11T10:33:26.000+0100},
title = {Improving microaneurysm detection using an optimally selected subset of candidate extractors and preprocessing methods},
url = {http://www.sciencedirect.com/science/article/pii/S0031320311002780},
volume = 45,
year = 2012
}