Retinal Blood Vessel Segmentation Using Extreme Learning Machine

Extreme learning machine (ELM) is an effective machine learning technique that widely used in image processing. In this paper, a new supervised method for segmenting blood vessels in retinal images is proposed based on the ELM classifier. The proposed algorithm first constructs a 7-D feature vector...

Full description

Saved in:
Bibliographic Details
Published in:Journal of advanced computational intelligence and intelligent informatics 2017-11, Vol.21 (7), p.1280-1290
Main Authors: Guo, Fan, Xiang, Da, Zou, Beiji, Zhu, Chengzhang, Wang, Shengnan
Format: Article
Language:English
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c414t-614fa4d39bfc04db37fe5a46243bc7d96aa50e47982274e4263f16c7ef9d3c3a3
cites cdi_FETCH-LOGICAL-c414t-614fa4d39bfc04db37fe5a46243bc7d96aa50e47982274e4263f16c7ef9d3c3a3
container_end_page 1290
container_issue 7
container_start_page 1280
container_title Journal of advanced computational intelligence and intelligent informatics
container_volume 21
creator Guo, Fan
Xiang, Da
Zou, Beiji
Zhu, Chengzhang
Wang, Shengnan
description Extreme learning machine (ELM) is an effective machine learning technique that widely used in image processing. In this paper, a new supervised method for segmenting blood vessels in retinal images is proposed based on the ELM classifier. The proposed algorithm first constructs a 7-D feature vector using multi-scale Gabor filter, Hessian matrix and bottom-hat transformation. Then, an ELM classifier is trained on gold standard examples of vessel segmentation images to classify previous unseen images. The algorithm was tested on the publicly available DRIVE database – a digital image database for vessel extraction. Experimental results on both real-captured images and public database images demonstrate that our method shows comparative performance against other methods, which make the proposed algorithm a suitable tool for automated retinal image analysis.
doi_str_mv 10.20965/jaciii.2017.p1280
format article
fullrecord <record><control><sourceid>crossref</sourceid><recordid>TN_cdi_crossref_primary_10_20965_jaciii_2017_p1280</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>10_20965_jaciii_2017_p1280</sourcerecordid><originalsourceid>FETCH-LOGICAL-c414t-614fa4d39bfc04db37fe5a46243bc7d96aa50e47982274e4263f16c7ef9d3c3a3</originalsourceid><addsrcrecordid>eNotkMtOwzAURC0EElXpD7DyD6T4cWMnO6AqFCkICShby3Gui6s8KjsL-HvSltWcmcUsDiG3nC0FK1V-t7cuhDAVrpcHLgp2QWa8KGRWMA6XE0uQGeOSXZNFSnvGJhaKAZ-R-3ccQ29b-tgOQ0O_MCVs6QfuOuxHO4ahp9sU-h1d_4wRO6QV2tgfh1frvkOPN-TK2zbh4j_nZPu0_lxtsurt-WX1UGUOOIyZ4uAtNLKsvWPQ1FJ7zC0oAbJ2uimVtTlD0GUhhAYEoaTnymn0ZSOdtHJOxPnXxSGliN4cYuhs_DWcmZMGc9ZgjhrMSYP8A89FUhM</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Retinal Blood Vessel Segmentation Using Extreme Learning Machine</title><source>DOAJ Directory of Open Access Journals</source><creator>Guo, Fan ; Xiang, Da ; Zou, Beiji ; Zhu, Chengzhang ; Wang, Shengnan</creator><creatorcontrib>Guo, Fan ; Xiang, Da ; Zou, Beiji ; Zhu, Chengzhang ; Wang, Shengnan ; School of Information Science and Engineering, Central South University Changsha, Hunan 410083, China</creatorcontrib><description>Extreme learning machine (ELM) is an effective machine learning technique that widely used in image processing. In this paper, a new supervised method for segmenting blood vessels in retinal images is proposed based on the ELM classifier. The proposed algorithm first constructs a 7-D feature vector using multi-scale Gabor filter, Hessian matrix and bottom-hat transformation. Then, an ELM classifier is trained on gold standard examples of vessel segmentation images to classify previous unseen images. The algorithm was tested on the publicly available DRIVE database – a digital image database for vessel extraction. Experimental results on both real-captured images and public database images demonstrate that our method shows comparative performance against other methods, which make the proposed algorithm a suitable tool for automated retinal image analysis.</description><identifier>ISSN: 1343-0130</identifier><identifier>EISSN: 1883-8014</identifier><identifier>DOI: 10.20965/jaciii.2017.p1280</identifier><language>eng</language><ispartof>Journal of advanced computational intelligence and intelligent informatics, 2017-11, Vol.21 (7), p.1280-1290</ispartof><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c414t-614fa4d39bfc04db37fe5a46243bc7d96aa50e47982274e4263f16c7ef9d3c3a3</citedby><cites>FETCH-LOGICAL-c414t-614fa4d39bfc04db37fe5a46243bc7d96aa50e47982274e4263f16c7ef9d3c3a3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,776,780,860,27901,27902</link.rule.ids></links><search><creatorcontrib>Guo, Fan</creatorcontrib><creatorcontrib>Xiang, Da</creatorcontrib><creatorcontrib>Zou, Beiji</creatorcontrib><creatorcontrib>Zhu, Chengzhang</creatorcontrib><creatorcontrib>Wang, Shengnan</creatorcontrib><creatorcontrib>School of Information Science and Engineering, Central South University Changsha, Hunan 410083, China</creatorcontrib><title>Retinal Blood Vessel Segmentation Using Extreme Learning Machine</title><title>Journal of advanced computational intelligence and intelligent informatics</title><description>Extreme learning machine (ELM) is an effective machine learning technique that widely used in image processing. In this paper, a new supervised method for segmenting blood vessels in retinal images is proposed based on the ELM classifier. The proposed algorithm first constructs a 7-D feature vector using multi-scale Gabor filter, Hessian matrix and bottom-hat transformation. Then, an ELM classifier is trained on gold standard examples of vessel segmentation images to classify previous unseen images. The algorithm was tested on the publicly available DRIVE database – a digital image database for vessel extraction. Experimental results on both real-captured images and public database images demonstrate that our method shows comparative performance against other methods, which make the proposed algorithm a suitable tool for automated retinal image analysis.</description><issn>1343-0130</issn><issn>1883-8014</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2017</creationdate><recordtype>article</recordtype><recordid>eNotkMtOwzAURC0EElXpD7DyD6T4cWMnO6AqFCkICShby3Gui6s8KjsL-HvSltWcmcUsDiG3nC0FK1V-t7cuhDAVrpcHLgp2QWa8KGRWMA6XE0uQGeOSXZNFSnvGJhaKAZ-R-3ccQ29b-tgOQ0O_MCVs6QfuOuxHO4ahp9sU-h1d_4wRO6QV2tgfh1frvkOPN-TK2zbh4j_nZPu0_lxtsurt-WX1UGUOOIyZ4uAtNLKsvWPQ1FJ7zC0oAbJ2uimVtTlD0GUhhAYEoaTnymn0ZSOdtHJOxPnXxSGliN4cYuhs_DWcmZMGc9ZgjhrMSYP8A89FUhM</recordid><startdate>20171120</startdate><enddate>20171120</enddate><creator>Guo, Fan</creator><creator>Xiang, Da</creator><creator>Zou, Beiji</creator><creator>Zhu, Chengzhang</creator><creator>Wang, Shengnan</creator><scope>AAYXX</scope><scope>CITATION</scope></search><sort><creationdate>20171120</creationdate><title>Retinal Blood Vessel Segmentation Using Extreme Learning Machine</title><author>Guo, Fan ; Xiang, Da ; Zou, Beiji ; Zhu, Chengzhang ; Wang, Shengnan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c414t-614fa4d39bfc04db37fe5a46243bc7d96aa50e47982274e4263f16c7ef9d3c3a3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2017</creationdate><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Guo, Fan</creatorcontrib><creatorcontrib>Xiang, Da</creatorcontrib><creatorcontrib>Zou, Beiji</creatorcontrib><creatorcontrib>Zhu, Chengzhang</creatorcontrib><creatorcontrib>Wang, Shengnan</creatorcontrib><creatorcontrib>School of Information Science and Engineering, Central South University Changsha, Hunan 410083, China</creatorcontrib><collection>CrossRef</collection><jtitle>Journal of advanced computational intelligence and intelligent informatics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Guo, Fan</au><au>Xiang, Da</au><au>Zou, Beiji</au><au>Zhu, Chengzhang</au><au>Wang, Shengnan</au><aucorp>School of Information Science and Engineering, Central South University Changsha, Hunan 410083, China</aucorp><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Retinal Blood Vessel Segmentation Using Extreme Learning Machine</atitle><jtitle>Journal of advanced computational intelligence and intelligent informatics</jtitle><date>2017-11-20</date><risdate>2017</risdate><volume>21</volume><issue>7</issue><spage>1280</spage><epage>1290</epage><pages>1280-1290</pages><issn>1343-0130</issn><eissn>1883-8014</eissn><abstract>Extreme learning machine (ELM) is an effective machine learning technique that widely used in image processing. In this paper, a new supervised method for segmenting blood vessels in retinal images is proposed based on the ELM classifier. The proposed algorithm first constructs a 7-D feature vector using multi-scale Gabor filter, Hessian matrix and bottom-hat transformation. Then, an ELM classifier is trained on gold standard examples of vessel segmentation images to classify previous unseen images. The algorithm was tested on the publicly available DRIVE database – a digital image database for vessel extraction. Experimental results on both real-captured images and public database images demonstrate that our method shows comparative performance against other methods, which make the proposed algorithm a suitable tool for automated retinal image analysis.</abstract><doi>10.20965/jaciii.2017.p1280</doi><tpages>11</tpages><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 1343-0130
ispartof Journal of advanced computational intelligence and intelligent informatics, 2017-11, Vol.21 (7), p.1280-1290
issn 1343-0130
1883-8014
language eng
recordid cdi_crossref_primary_10_20965_jaciii_2017_p1280
source DOAJ Directory of Open Access Journals
title Retinal Blood Vessel Segmentation Using Extreme Learning Machine
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-31T04%3A53%3A43IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-crossref&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Retinal%20Blood%20Vessel%20Segmentation%20Using%20Extreme%20Learning%20Machine&rft.jtitle=Journal%20of%20advanced%20computational%20intelligence%20and%20intelligent%20informatics&rft.au=Guo,%20Fan&rft.aucorp=School%20of%20Information%20Science%20and%20Engineering,%20Central%20South%20University%20Changsha,%20Hunan%20410083,%20China&rft.date=2017-11-20&rft.volume=21&rft.issue=7&rft.spage=1280&rft.epage=1290&rft.pages=1280-1290&rft.issn=1343-0130&rft.eissn=1883-8014&rft_id=info:doi/10.20965/jaciii.2017.p1280&rft_dat=%3Ccrossref%3E10_20965_jaciii_2017_p1280%3C/crossref%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c414t-614fa4d39bfc04db37fe5a46243bc7d96aa50e47982274e4263f16c7ef9d3c3a3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true