Sclera-Net: Accurate Sclera Segmentation in Various Sensor Images Based on Residual Encoder and Decoder Network

Sclera segmentation is revealed to be of noteworthy importance for ocular biometrics. The paramount step for biometric recognition methods is the segmentation of the area of interest, i.e., the sclera in our case. The sclera segmentation process plays a pivotal part in retaining the accuracy of the...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE access Jg. 7; S. 98208 - 98227
Hauptverfasser:	Naqvi, Rizwan Ali, Loh, Woong-Kee
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Piscataway IEEE 2019 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:	Algorithms Artificial neural networks Biomedical imaging Biometrics Coders Complexity Convolution convolutional neural network Datasets Decoding Deep learning encoder-decoder network Image segmentation Iris Iris recognition Machine learning Recognition residual connections Sclera recognition sclera segmentation semantic segmentation Vessels
ISSN:	2169-3536, 2169-3536
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Abstract	Sclera segmentation is revealed to be of noteworthy importance for ocular biometrics. The paramount step for biometric recognition methods is the segmentation of the area of interest, i.e., the sclera in our case. The sclera segmentation process plays a pivotal part in retaining the accuracy of the sclera-based recognition schemes by restraining the errors. However, accurate sclera segmentation in the images from various sensors in a real environment is quite challenging due to the saturated and/or defocused vessel patterns and the vessel structure, which has complex nonlinear deformations due to the multilayered sclera. With the development of deep learning algorithms, studies that are based on the sclera segmentation using convolutional neural networks (CNNs) have achieved promising results for sclera recognition. However, previous CNN-based methods are based on the repeated subsampling stages of convolution strides, or spatial pooling leads to losing much of the finer image structure that significantly decreases overall performance in tasks, such as semantic segmentation. In this paper, we present Sclera-Net , a residual encoder and decoder network that exploits identity and non-identity mapping residual skip connections to take benefit of the high-frequency information from the prior layers of both encoder and decoder networks to determine the accurate sclera region as well as other ocular regions. In this way, the finer image structure that was being lost due to repeated subsampling during convolution and pooling can be reutilized using residual skip connections to enhance overall performance. Furthermore, the proposed Sclera-Net does not enhance the performance on the cost of increasing depth, complexity, or the number of parameters. We performed comprehensive experiments and obtained optimum performance not only on sclera datasets but also on the iris datasets. In particular, we achieved an equal error rate and mean F1-score of 0.0093 and 96.2421, respectively, on the challenging SBVPI database, which is the best-reported result to date.
AbstractList	Sclera segmentation is revealed to be of noteworthy importance for ocular biometrics. The paramount step for biometric recognition methods is the segmentation of the area of interest, i.e., the sclera in our case. The sclera segmentation process plays a pivotal part in retaining the accuracy of the sclera-based recognition schemes by restraining the errors. However, accurate sclera segmentation in the images from various sensors in a real environment is quite challenging due to the saturated and/or defocused vessel patterns and the vessel structure, which has complex nonlinear deformations due to the multilayered sclera. With the development of deep learning algorithms, studies that are based on the sclera segmentation using convolutional neural networks (CNNs) have achieved promising results for sclera recognition. However, previous CNN-based methods are based on the repeated subsampling stages of convolution strides, or spatial pooling leads to losing much of the finer image structure that significantly decreases overall performance in tasks, such as semantic segmentation. In this paper, we present Sclera-Net, a residual encoder and decoder network that exploits identity and non-identity mapping residual skip connections to take benefit of the high-frequency information from the prior layers of both encoder and decoder networks to determine the accurate sclera region as well as other ocular regions. In this way, the finer image structure that was being lost due to repeated subsampling during convolution and pooling can be reutilized using residual skip connections to enhance overall performance. Furthermore, the proposed Sclera-Net does not enhance the performance on the cost of increasing depth, complexity, or the number of parameters. We performed comprehensive experiments and obtained optimum performance not only on sclera datasets but also on the iris datasets. In particular, we achieved an equal error rate and mean F1-score of 0.0093 and 96.2421, respectively, on the challenging SBVPI database, which is the best-reported result to date.
Author	Loh, Woong-Kee Naqvi, Rizwan Ali
Author_xml	– sequence: 1 givenname: Rizwan Ali orcidid: 0000-0002-7473-8441 surname: Naqvi fullname: Naqvi, Rizwan Ali organization: Department of Software, Gachon University, Seongnam, South Korea – sequence: 2 givenname: Woong-Kee surname: Loh fullname: Loh, Woong-Kee email: wkloh2@gachon.ac.kr organization: Department of Software, Gachon University, Seongnam, South Korea
BookMark	eNp9UU1vEzEUtFCRKG1_QS-WOG-6Xtu7NrcQAkSqqESAq-U8P0cOiV3sXSH-fV22IMQBX_w0mpn3MS_JWUwRCblm7YKxVt8sV6v1drvoWqYXneat1PwZOe9YrxsueX_2V_2CXJVyaOtTFZLDOUlbOGK2zUccX9MlwJTtiHQG6Rb3J4yjHUOKNET61eaQplLxWFKmm5PdY6FvbEFHK-MTluAme6TrCMlhpjY6-hbnujb4kfK3S_Lc22PBq6f_gnx5t_68-tDc3r3frJa3DYhWjY1miiPXGqUQ2veyY9gqBV44QA0SmHdKCM_B9gjAONfKd04jt4zBznt-QTazr0v2YO5zONn80yQbzC8g5b2xeQx1T-MU20mpBs97JbgTmrtBiEFKkN2OAVSvV7PXfU7fJyyjOaQpxzq-6YSUUveyF5WlZxbkVEpGbyDMpxuzDUfDWvMYl5njMo9xmae4qpb_o_098f9V17MqIOIfhRp6rXvFHwBjmqKe
CODEN	IAECCG
CitedBy_id	crossref_primary_10_1109_ACCESS_2020_3010011 crossref_primary_10_3390_app11072978 crossref_primary_10_32604_cmc_2020_013249 crossref_primary_10_1109_TBCAS_2024_3411713 crossref_primary_10_1109_TIFS_2022_3216468 crossref_primary_10_1051_itmconf_20246503014 crossref_primary_10_1007_s10462_021_10028_w crossref_primary_10_3390_math8122192 crossref_primary_10_1007_s00521_023_08937_8 crossref_primary_10_1007_s10044_024_01301_z crossref_primary_10_1007_s11760_023_02891_7 crossref_primary_10_1016_j_displa_2022_102257 crossref_primary_10_1109_TIM_2022_3232162 crossref_primary_10_1109_JSTARS_2023_3348572
Cites_doi	10.1109/ACCESS.2019.2918205 10.1109/TSMCA.2011.2170416 10.1109/ICCV.2015.436 10.1109/ISDA.2013.6920711 10.1038/42842 10.1115/1.802566.paper74 10.1109/LGRS.2018.2864342 10.1109/BTAS.2015.7358746 10.1007/s004170100365 10.1109/LGRS.2018.2867242 10.1109/CAC.2017.8243510 10.1109/CVPR.2016.90 10.1109/ACPR.2013.168 10.1109/TPAMI.2009.66 10.1109/TPAMI.2016.2644615 10.1109/BTAS.2015.7358796 10.1109/CVPR.2017.632 10.1001/archopht.1955.00930020231010 10.1109/ICSMC.2012.6377912 10.1109/BTAS.2017.8272764 10.1109/TIP.2013.2260165 10.1145/1143844.1143874 10.3390/sym9110263 10.1109/CVPR.2017.549 10.1109/IJCNN.2007.4371435 10.1109/CIBIM.2014.7015436 10.1109/ICARCV.2010.5707959 10.1016/j.patrec.2011.11.006 10.1109/BTAS.2018.8698597 10.1109/ICB.2012.6199815 10.1016/j.patcog.2008.01.012 10.1016/j.patrec.2015.02.012 10.1016/j.compmedimag.2018.03.001 10.1109/ICNGIS.2016.7854051 10.1109/IVS.2018.8500504 10.1109/ACCESS.2018.2868801 10.1016/j.procs.2016.09.365 10.1109/ICB.2016.7550069 10.1109/ICB2018.2018.00053 10.1016/j.ophtha.2015.11.020 10.1109/TPAMI.2016.2572683 10.1117/12.849706 10.1007/978-1-4757-4036-3_2 10.1109/ACCESS.2018.2794463 10.3390/s18051501 10.1109/ICCV.2015.304 10.1109/ICB.2016.7550055 10.1016/j.patrec.2015.02.009 10.1109/ACCESS.2019.2906344 10.1109/ICB.2016.7550049 10.1109/TIFS.2013.2291314 10.1007/978-3-642-01793-3_97 10.1007/978-3-642-01793-3_125 10.1117/12.849731 10.1109/IWOBI.2018.8464133
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019
DBID	97E ESBDL RIA RIE AAYXX CITATION 7SC 7SP 7SR 8BQ 8FD JG9 JQ2 L7M L~C L~D DOA
DOI	10.1109/ACCESS.2019.2930593
DatabaseName	IEEE Xplore (IEEE) IEEE Xplore Open Access Journals IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Engineered Materials Abstracts METADEX Technology Research Database Materials Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional DOAJ Directory of Open Access Journals
DatabaseTitle	CrossRef Materials Research Database Engineered Materials Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace METADEX Computer and Information Systems Abstracts Professional
DatabaseTitleList	Materials Research Database
Database_xml	– sequence: 1 dbid: DOA name: Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	2169-3536
EndPage	98227
ExternalDocumentID	oai_doaj_org_article_d81b5587f36843d493d744755c52b1cc 10_1109_ACCESS_2019_2930593 8769968
Genre	orig-research
GrantInformation_xml	– fundername: National Research Foundation of Korea funderid: 10.13039/501100003725 – fundername: National Research Foundation grantid: NRF-2018R1A2B6009188 funderid: 10.13039/501100001321
GroupedDBID	0R~ 4.4 5VS 6IK 97E AAJGR ABAZT ABVLG ACGFS ADBBV AGSQL ALMA_UNASSIGNED_HOLDINGS BCNDV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS EJD ESBDL GROUPED_DOAJ IPLJI JAVBF KQ8 M43 M~E O9- OCL OK1 RIA RIE RNS AAYXX CITATION 7SC 7SP 7SR 8BQ 8FD JG9 JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c408t-9183e399e5449f6521e088cf4dce9c5c1fd844f3ca6ecc13398f2d9e3a11cbff3
IEDL.DBID	DOA
ISICitedReferencesCount	21
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000480326700004&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	2169-3536
IngestDate	Fri Oct 03 12:41:31 EDT 2025 Sun Nov 30 05:02:06 EST 2025 Tue Nov 18 21:48:02 EST 2025 Sat Nov 29 03:57:48 EST 2025 Wed Aug 27 02:54:22 EDT 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Language	English
License	https://creativecommons.org/licenses/by/4.0/legalcode
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c408t-9183e399e5449f6521e088cf4dce9c5c1fd844f3ca6ecc13398f2d9e3a11cbff3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-7473-8441
OpenAccessLink	https://doaj.org/article/d81b5587f36843d493d744755c52b1cc
PQID	2455596564
PQPubID	4845423
PageCount	20
ParticipantIDs	doaj_primary_oai_doaj_org_article_d81b5587f36843d493d744755c52b1cc proquest_journals_2455596564 crossref_primary_10_1109_ACCESS_2019_2930593 ieee_primary_8769968 crossref_citationtrail_10_1109_ACCESS_2019_2930593
PublicationCentury	2000
PublicationDate	20190000 2019-00-00 20190101 2019-01-01
PublicationDateYYYYMMDD	2019-01-01
PublicationDate_xml	– year: 2019 text: 20190000
PublicationDecade	2010
PublicationPlace	Piscataway
PublicationPlace_xml	– name: Piscataway
PublicationTitle	IEEE access
PublicationTitleAbbrev	Access
PublicationYear	2019
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref57 ref13 ref12 ref58 ref14 (ref59) 2019 ref11 ref10 (ref29) 2019 nair (ref53) 2010 ref17 rot (ref24) 2018 ref16 ref19 ref18 he (ref51) 2016 ref50 (ref56) 2018 ref46 ref45 ref48 ref47 ref42 ioffe (ref52) 2015 ref41 (ref25) 2019 ref44 ref43 ref49 (ref28) 2019 ref8 ref7 arsalan (ref67) 2017; 9 ref9 ref4 ref6 ref5 ref40 ref35 ref34 ref37 ref36 ref31 ref30 ref33 ref32 ref2 ref1 ref39 (ref54) 2018 ref38 ref68 ref26 ref69 ref64 ref20 ref63 ref66 ref22 ref65 ref21 simonyan (ref15) 2015 (ref23) 2019 toh (ref3) 2006 ref27 ref60 ref62 ref61 glorot (ref55) 2011
References_xml	– ident: ref62 doi: 10.1109/ACCESS.2019.2918205 – ident: ref8 doi: 10.1109/TSMCA.2011.2170416 – start-page: 448 year: 2015 ident: ref52 article-title: Batch normalization: Accelerating deep network training by reducing internal covariate shift publication-title: Proc ICML – ident: ref66 doi: 10.1109/ICCV.2015.436 – ident: ref39 doi: 10.1109/ISDA.2013.6920711 – ident: ref12 doi: 10.1038/42842 – ident: ref7 doi: 10.1115/1.802566.paper74 – ident: ref44 doi: 10.1109/LGRS.2018.2864342 – year: 2019 ident: ref59 publication-title: Optimization Stochastic Gradient Descent – ident: ref45 doi: 10.1109/BTAS.2015.7358746 – ident: ref11 doi: 10.1007/s004170100365 – ident: ref58 doi: 10.1109/LGRS.2018.2867242 – ident: ref57 doi: 10.1109/CAC.2017.8243510 – ident: ref16 doi: 10.1109/CVPR.2016.90 – ident: ref9 doi: 10.1109/ACPR.2013.168 – ident: ref27 doi: 10.1109/TPAMI.2009.66 – ident: ref21 doi: 10.1109/TPAMI.2016.2644615 – ident: ref17 doi: 10.1109/BTAS.2015.7358796 – ident: ref50 doi: 10.1109/CVPR.2017.632 – ident: ref10 doi: 10.1001/archopht.1955.00930020231010 – ident: ref36 doi: 10.1109/ICSMC.2012.6377912 – ident: ref19 doi: 10.1109/BTAS.2017.8272764 – year: 2019 ident: ref29 publication-title: Biometrics Ideal Test – ident: ref69 doi: 10.1109/TIP.2013.2260165 – ident: ref63 doi: 10.1145/1143844.1143874 – year: 2019 ident: ref25 publication-title: SBVPI Dataset – start-page: 1 year: 2015 ident: ref15 article-title: Very deep convolutional networks for large-scale image recognition publication-title: Proc ICLR – volume: 9 start-page: 1 year: 2017 ident: ref67 article-title: Deep learning-based iris segmentation for iris recognition in visible light environment publication-title: Symmetry doi: 10.3390/sym9110263 – ident: ref22 doi: 10.1109/CVPR.2017.549 – start-page: 807 year: 2010 ident: ref53 article-title: Rectified linear units improve restricted boltzmann machines publication-title: Proc ICML – ident: ref30 doi: 10.1109/IJCNN.2007.4371435 – ident: ref40 doi: 10.1109/CIBIM.2014.7015436 – start-page: 630 year: 2016 ident: ref51 article-title: Identity mappings in deep residual networks publication-title: Proc ECCV – ident: ref35 doi: 10.1109/ICARCV.2010.5707959 – ident: ref38 doi: 10.1016/j.patrec.2011.11.006 – ident: ref47 doi: 10.1109/BTAS.2018.8698597 – start-page: 546 year: 2006 ident: ref3 article-title: Identity verification through palm vein and crease texture publication-title: Proc IEEE ICB – year: 2018 ident: ref24 article-title: Deep learning methods for biometric recognition based on eye information – start-page: 315 year: 2011 ident: ref55 article-title: Deep sparse rectifier neural networks publication-title: Proc AISTATS – ident: ref33 doi: 10.1109/ICB.2012.6199815 – ident: ref37 doi: 10.1016/j.patcog.2008.01.012 – ident: ref65 doi: 10.1016/j.patrec.2015.02.012 – ident: ref43 doi: 10.1016/j.compmedimag.2018.03.001 – year: 2019 ident: ref23 publication-title: Sclera-Net CNN Model (Sclera-Net) With Algorithm – ident: ref41 doi: 10.1109/ICNGIS.2016.7854051 – ident: ref48 doi: 10.1109/IVS.2018.8500504 – ident: ref61 doi: 10.1109/ACCESS.2018.2868801 – ident: ref4 doi: 10.1016/j.procs.2016.09.365 – ident: ref18 doi: 10.1109/ICB.2016.7550069 – ident: ref20 doi: 10.1109/ICB2018.2018.00053 – ident: ref14 doi: 10.1016/j.ophtha.2015.11.020 – ident: ref49 doi: 10.1109/TPAMI.2016.2572683 – ident: ref32 doi: 10.1117/12.849706 – ident: ref1 doi: 10.1007/978-1-4757-4036-3_2 – ident: ref5 doi: 10.1109/ACCESS.2018.2794463 – ident: ref68 doi: 10.3390/s18051501 – ident: ref60 doi: 10.1109/ICCV.2015.304 – ident: ref64 doi: 10.1109/ICB.2016.7550055 – ident: ref26 doi: 10.1016/j.patrec.2015.02.009 – ident: ref6 doi: 10.1109/ACCESS.2019.2906344 – year: 2018 ident: ref54 publication-title: Convolutional neural network – ident: ref42 doi: 10.1109/ICB.2016.7550049 – ident: ref34 doi: 10.1109/TIFS.2013.2291314 – ident: ref2 doi: 10.1007/978-3-642-01793-3_97 – year: 2019 ident: ref28 publication-title: NICE I-Noisy Iris Challenge Evaluation Part I – ident: ref31 doi: 10.1007/978-3-642-01793-3_125 – year: 2018 ident: ref56 publication-title: Matlab – ident: ref13 doi: 10.1117/12.849731 – ident: ref46 doi: 10.1109/IWOBI.2018.8464133
SSID	ssj0000816957
Score	2.291005
Snippet	Sclera segmentation is revealed to be of noteworthy importance for ocular biometrics. The paramount step for biometric recognition methods is the segmentation...
SourceID	doaj proquest crossref ieee
SourceType	Open Website Aggregation Database Enrichment Source Index Database Publisher
StartPage	98208
SubjectTerms	Algorithms Artificial neural networks Biomedical imaging Biometrics Coders Complexity Convolution convolutional neural network Datasets Decoding Deep learning encoder-decoder network Image segmentation Iris Iris recognition Machine learning Recognition residual connections Sclera recognition sclera segmentation semantic segmentation Vessels
SummonAdditionalLinks	– databaseName: IEEE Electronic Library (IEL) dbid: RIE link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwEB61FQc4lEdBLBTkA8emTWI7trltl1YgoRWiUPVmxS9UiSYo2e3vZ-y4EQiExM1ybMvJZ8_D8XwD8KZkzLemkYWh1MQUZrQw3JiiEaUwgdWOpzPdy49ivZZXV-rTDhzNsTDe-3T5zB_HYvqX73q7jUdlJ7hz0TyXu7ArRDPFas3nKTGBhOIiEwtVpTpZrlb4DvH2ljpGpRZz1_2mfBJHf06q8ockTurl_OH_TewR7Gczkiwn3B_Dju-ewINfyAUPoL_AJ0NbrP3mLVlau42kEGSqJBf-202OOurIdUcu0WXutyPWd2M_kA83KGZGcooqzhFs8dmPKWiLnHUxBn4gbefIOz-V19NN8qfw9fzsy-p9kdMrFJaVcoNiTlKP9onnjKnQoB73KHJsYM56ZbmtgpOMBWrbBnFGX1bJUDvlaVtV1oRAn8Fe13f-ORDRRpqXimNjjvgK5YKRZYujc2qlcQuo7767tpl7PKbA-K6TD1IqPYGlI1g6g7WAo7nTj4l649_NTyOgc9PIm50qECmdt6F2aKVzLkWgjWTUMUWdiJSH3PLaVNYu4CCiOw-SgV3A4d3y0HmPj7pmHN0xtIfZi7_3egn34wSnA5tD2NsMW_8K7tnbzfU4vE7L9ydTH-2S priority: 102 providerName: IEEE
Title	Sclera-Net: Accurate Sclera Segmentation in Various Sensor Images Based on Residual Encoder and Decoder Network
URI	https://ieeexplore.ieee.org/document/8769968 https://www.proquest.com/docview/2455596564 https://doaj.org/article/d81b5587f36843d493d744755c52b1cc
Volume	7
WOSCitedRecordID	wos000480326700004&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVAON databaseName: Directory of Open Access Journals customDbUrl: eissn: 2169-3536 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000816957 issn: 2169-3536 databaseCode: DOA dateStart: 20130101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2169-3536 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000816957 issn: 2169-3536 databaseCode: M~E dateStart: 20130101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LT9wwELYq1EM5IFqoWEpXPvTYQBLbsd3b7nZRK7WrCijiZsUvhATZKlk49rd3_GC1VaVy4RJFzuThmck8LM83CH0oKXWtbkShCdGhhRkpNNO6aHjJtae1ZXFN9_IbXyzE1ZX8sdHqK-wJS_DAiXEnFuIqxgT3pBGUWCqJ5QGkjhlW68qYYH1LLjeSqWiDRdVIxjPMUFXKk8lsBjMKe7nkMbi40MnuL1cUEftzi5V_7HJ0Nqe7aCdHiXiSvu41euG6N2h7AztwDy3P4UrfFgu3-oQnxtwHzAecBvG5u77LRUUdvunwJWTEkOLDeDcse_z1DqzIgKfgwSwGijM3xJosPO9CiXuP287izy6dL9JG8X3083R-MftS5O4JhaGlWIEVE8RB-OEYpdI34KYdWBTjqTVOGmYqbwWlnpi2ATFCqiqFr610pK0qo70nb9FWt-zcAcK8DSguFQNiBuLj0notyhaezogR2o5Q_chIZTK0eOhwcatiilFKlbivAvdV5v4IfVzf9Csha_yffBoktCYNsNhxAJRFZWVRTynLCO0F-a4fAq4A8j0xQkeP8lb5Fx5UTRlkWxDu0sPnePU79CpMJ63eHKGtVX_v3qOX5mF1M_TjqL1w_P57Po41iH8A_HXxhw
linkProvider	Directory of Open Access Journals
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwEB6VggQcyqMglhbwgWPTJrGd2Ny2S6tWLBGiperNil-oEk1QssvvZ5y4USsQErfIGVuOP3tm7Hi-AXifMuZqXYhEU6pDCjOaaK51UpRpqT3LLR_OdC-WZVWJy0v5ZQP2plgY59xw-czth8fhX75tzToclR3gykX3XNyD-5yxPB2jtaYTlZBCQvIyUgtlqTyYLxb4FeH-ltxHsxay190xPwNLf0yr8ocuHgzM8ZP_69pT2IqOJJmPyD-DDdc8h8e36AW3oT3DN12dVG71gcyNWQdaCDIWkjP3_TrGHTXkqiEXuGlu1z2WN33bkdNrVDQ9OUQjZwlKfHX9ELZFjpoQBd-RurHkoxufq_Eu-Qv4dnx0vjhJYoKFxLBUrFDRCerQQ3E4nNIXaMkdKh3jmTVOGm4ybwVjnpq6QKRxNyuFz610tM4yo72nL2GzaRv3CkhZB6KXjKMwR4RLab0WaY2tc2qEtjPIb8Zdmcg-HpJg_FDDLiSVagRLBbBUBGsGe1OlnyP5xr_FDwOgk2hgzh4KECkVF6Ky6KdzLkpPC8GoZZLaMpAecsNznRkzg-2A7tRIBHYGuzfTQ8VV3quccdyQoUfMXv-91jt4eHL-eamWp9WnHXgUOjse3-zC5qpbuzfwwPxaXfXd22Eq_wbQBvDZ
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Sclera-Net%3A+Accurate+Sclera+Segmentation+in+Various+Sensor+Images+Based+on+Residual+Encoder+and+Decoder+Network&rft.jtitle=IEEE+access&rft.au=Naqvi%2C+Rizwan+Ali&rft.au=Loh%2C+Woong-Kee&rft.date=2019&rft.issn=2169-3536&rft.eissn=2169-3536&rft.volume=7&rft.spage=98208&rft.epage=98227&rft_id=info:doi/10.1109%2FACCESS.2019.2930593&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_ACCESS_2019_2930593
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2169-3536&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2169-3536&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2169-3536&client=summon