Improved multiscale matched filter for retina vessel segmentation using PSO algorithm

The concept of matched filter is widely used in the area of retina vessel segmentation. Multiscale matched filters have superior performance over single scale filters. The proposed approach makes use of the improved noise suppression features of multiscale filters. A major performance issue here is...

Full description

Bibliographic Details
Main Authors: K.S. Sreejini, V.K. Govindan
Format: Article
Language:English
Published: Elsevier 2015-11-01
Series:Egyptian Informatics Journal
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S111086651500033X
_version_ 1818621004117704704
author K.S. Sreejini
V.K. Govindan
author_facet K.S. Sreejini
V.K. Govindan
author_sort K.S. Sreejini
collection DOAJ
description The concept of matched filter is widely used in the area of retina vessel segmentation. Multiscale matched filters have superior performance over single scale filters. The proposed approach makes use of the improved noise suppression features of multiscale filters. A major performance issue here is the determination of the right parameter values of the filter. The approach employs particle swarm optimization for finding the optimal filter parameters of the multiscale Gaussian matched filter for achieving improved accuracy of retina vessel segmentation. The proposed approach is tested on DRIVE and STARE retina database and obtained better results when compared to other available retina vessel segmentation algorithms.
first_indexed 2024-12-16T18:02:22Z
format Article
id doaj.art-5cf606a1d0a54d3ea7739d343c5d4b46
institution Directory Open Access Journal
issn 1110-8665
language English
last_indexed 2024-12-16T18:02:22Z
publishDate 2015-11-01
publisher Elsevier
record_format Article
series Egyptian Informatics Journal
spelling doaj.art-5cf606a1d0a54d3ea7739d343c5d4b462022-12-21T22:22:01ZengElsevierEgyptian Informatics Journal1110-86652015-11-0116325326010.1016/j.eij.2015.06.004Improved multiscale matched filter for retina vessel segmentation using PSO algorithmK.S. SreejiniV.K. GovindanThe concept of matched filter is widely used in the area of retina vessel segmentation. Multiscale matched filters have superior performance over single scale filters. The proposed approach makes use of the improved noise suppression features of multiscale filters. A major performance issue here is the determination of the right parameter values of the filter. The approach employs particle swarm optimization for finding the optimal filter parameters of the multiscale Gaussian matched filter for achieving improved accuracy of retina vessel segmentation. The proposed approach is tested on DRIVE and STARE retina database and obtained better results when compared to other available retina vessel segmentation algorithms.http://www.sciencedirect.com/science/article/pii/S111086651500033XMultiscale matched filterOptimizationRetina vesselsPSO
spellingShingle K.S. Sreejini
V.K. Govindan
Improved multiscale matched filter for retina vessel segmentation using PSO algorithm
Egyptian Informatics Journal
Multiscale matched filter
Optimization
Retina vessels
PSO
title Improved multiscale matched filter for retina vessel segmentation using PSO algorithm
title_full Improved multiscale matched filter for retina vessel segmentation using PSO algorithm
title_fullStr Improved multiscale matched filter for retina vessel segmentation using PSO algorithm
title_full_unstemmed Improved multiscale matched filter for retina vessel segmentation using PSO algorithm
title_short Improved multiscale matched filter for retina vessel segmentation using PSO algorithm
title_sort improved multiscale matched filter for retina vessel segmentation using pso algorithm
topic Multiscale matched filter
Optimization
Retina vessels
PSO
url http://www.sciencedirect.com/science/article/pii/S111086651500033X
work_keys_str_mv AT kssreejini improvedmultiscalematchedfilterforretinavesselsegmentationusingpsoalgorithm
AT vkgovindan improvedmultiscalematchedfilterforretinavesselsegmentationusingpsoalgorithm