Deep Representation-Based Feature Extraction and Recovering for Finger-Vein Verification

Finger-vein biometrics has been extensively investigated for personal verification. Despite recent advances in finger-vein verification, current solutions completely depend on domain knowledge and still lack the robustness to extract finger-vein features from raw images. This paper proposes a deep l...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on information forensics and security Ročník 12; číslo 8; s. 1816 - 1829
Hlavní autoři:	Qin, Huafeng, El-Yacoubi, Mounim A.
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	New York IEEE 01.08.2017 The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Institute of Electrical and Electronics Engineers
Témata:	Artificial neural networks Biometric recognition systems Computer Science Computer Vision and Pattern Recognition convolutional autoencoder convolutional neural network deep learning Feature extraction finger-vein verification Hand biometrics Image segmentation Iris recognition Machine learning Neural and Evolutionary Computing Neural networks representation learning Representations Signal and Image Processing Veins Representation learning Deep learning Hand biometrics Finger-vein verification Convolutional autoencoder Convolutional neural network
ISSN:	1556-6013, 1556-6021
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	Finger-vein biometrics has been extensively investigated for personal verification. Despite recent advances in finger-vein verification, current solutions completely depend on domain knowledge and still lack the robustness to extract finger-vein features from raw images. This paper proposes a deep learning model to extract and recover vein features using limited a priori knowledge. First, based on a combination of the known state-of-the-art handcrafted finger-vein image segmentation techniques, we automatically identify two regions: a clear region with high separability between finger-vein patterns and background, and an ambiguous region with low separability between them. The first is associated with pixels on which all the above-mentioned segmentation techniques assign the same segmentation label (either foreground or background), while the second corresponds to all the remaining pixels. This scheme is used to automatically discard the ambiguous region and to label the pixels of the clear region as foreground or background. A training data set is constructed based on the patches centered on the labeled pixels. Second, a convolutional neural network (CNN) is trained on the resulting data set to predict the probability of each pixel of being foreground (i.e., vein pixel), given a patch centered on it. The CNN learns what a finger-vein pattern is by learning the difference between vein patterns and background ones. The pixels in any region of a test image can then be classified effectively. Third, we propose another new and original contribution by developing and investigating a fully convolutional network to recover missing finger-vein patterns in the segmented image. The experimental results on two public finger-vein databases show a significant improvement in terms of finger-vein verification accuracy.
AbstractList	Finger-vein biometrics has been extensively investigated for personal verification. Despite recent advances in finger-vein verification, current solutions completely depend on domain knowledge and still lack the robustness to extract finger-vein features from raw images. This paper proposes a deep learning model to extract and recover vein features using limited a priori knowledge. First, based on a combination of the known state-of-the-art handcrafted finger-vein image segmentation techniques, we automatically identify two regions: a clear region with high separability between finger-vein patterns and background, and an ambiguous region with low separability between them. The first is associated with pixels on which all the above-mentioned segmentation techniques assign the same segmentation label (either foreground or background), while the second corresponds to all the remaining pixels. This scheme is used to automatically discard the ambiguous region and to label the pixels of the clear region as foreground or background. A training data set is constructed based on the patches centered on the labeled pixels. Second, a convolutional neural network (CNN) is trained on the resulting data set to predict the probability of each pixel of being foreground (i.e., vein pixel), given a patch centered on it. The CNN learns what a finger-vein pattern is by learning the difference between vein patterns and background ones. The pixels in any region of a test image can then be classified effectively. Third, we propose another new and original contribution by developing and investigating a fully convolutional network to recover missing finger-vein patterns in the segmented image. The experimental results on two public finger-vein databases show a significant improvement in terms of finger-vein verification accuracy Finger-vein biometrics has been extensively investigated for personal verification. Despite recent advances in finger-vein verification, current solutions completely depend on domain knowledge and still lack the robustness to extract finger-vein features from raw images. This paper proposes a deep learning model to extract and recover vein features using limited a priori knowledge. First, based on a combination of the known state-of-the-art handcrafted finger-vein image segmentation techniques, we automatically identify two regions: a clear region with high separability between finger-vein patterns and background, and an ambiguous region with low separability between them. The first is associated with pixels on which all the above-mentioned segmentation techniques assign the same segmentation label (either foreground or background), while the second corresponds to all the remaining pixels. This scheme is used to automatically discard the ambiguous region and to label the pixels of the clear region as foreground or background. A training data set is constructed based on the patches centered on the labeled pixels. Second, a convolutional neural network (CNN) is trained on the resulting data set to predict the probability of each pixel of being foreground (i.e., vein pixel), given a patch centered on it. The CNN learns what a finger-vein pattern is by learning the difference between vein patterns and background ones. The pixels in any region of a test image can then be classified effectively. Third, we propose another new and original contribution by developing and investigating a fully convolutional network to recover missing finger-vein patterns in the segmented image. The experimental results on two public finger-vein databases show a significant improvement in terms of finger-vein verification accuracy.
Author	Huafeng Qin El-Yacoubi, Mounim A.
Author_xml	– sequence: 1 givenname: Huafeng orcidid: 0000-0003-4911-0393 surname: Qin fullname: Qin, Huafeng – sequence: 2 givenname: Mounim A. surname: El-Yacoubi fullname: El-Yacoubi, Mounim A.
BackLink	https://hal.science/hal-01587285$$DView record in HAL
BookMark	eNp9kE1Lw0AQhhepYP34AeIl4MlD6k6yXzlqNSoUBD-Kt2W7mehKTeImFf33bkztwYOnGWaedxieXTKq6goJOQQ6AaDZ6cNNfj9JKMhJIlQmE7ZFxsC5iAVNYLTpId0hu237SiljINSYPF0gNtEdNh5brDrTubqKz02LRZSj6VYeo8vPzhvbLyJTFYG19Qd6Vz1HZe2jPDTo4zm6KpqHcensz5F9sl2aZYsH67pHHvPLh-l1PLu9upmezWKbStrFrFScQlayEguessxmhUHGlBRUJnzBU5OVqABBLZRAMDYFwzOqFqkxQgib7pGT4e6LWerGuzfjv3RtnL4-m-l-RoErmSj-AYE9HtjG1-8rbDv9Wq98Fd7TEKTRhEEiAyUHyvq6bT2W2rpBTPDglhqo7pXrXrnuleu18pCEP8nfh_7LHA0Zh4gbXqqMBgnpN4UyjZE
CODEN	ITIFA6
CitedBy_id	crossref_primary_10_1109_ACCESS_2022_3226888 crossref_primary_10_1007_s10916_018_1104_5 crossref_primary_10_1007_s11633_022_1341_4 crossref_primary_10_1016_j_neucom_2018_02_042 crossref_primary_10_1016_j_neucom_2018_10_042 crossref_primary_10_1049_iet_bmt_2018_5130 crossref_primary_10_1109_ACCESS_2020_2990966 crossref_primary_10_1109_TCSVT_2023_3334825 crossref_primary_10_1109_TETCI_2024_3398022 crossref_primary_10_4018_IJEIS_2019010106 crossref_primary_10_1016_j_future_2019_07_003 crossref_primary_10_1109_TIM_2022_3200087 crossref_primary_10_1109_ACCESS_2019_2960411 crossref_primary_10_1109_TCSVT_2022_3227385 crossref_primary_10_3389_fnbot_2022_1065099 crossref_primary_10_1016_j_engappai_2025_110586 crossref_primary_10_1109_TIFS_2019_2924553 crossref_primary_10_1007_s00521_025_11363_7 crossref_primary_10_1016_j_patcog_2024_111064 crossref_primary_10_1007_s10489_021_02619_5 crossref_primary_10_1145_3329784 crossref_primary_10_3390_info10040145 crossref_primary_10_3390_s18072296 crossref_primary_10_1109_TIFS_2023_3258252 crossref_primary_10_1109_LSP_2018_2857207 crossref_primary_10_1109_ACCESS_2020_2984711 crossref_primary_10_1109_ACCESS_2019_2950698 crossref_primary_10_1109_TIFS_2023_3340915 crossref_primary_10_1109_TIFS_2018_2866330 crossref_primary_10_1109_JSEN_2022_3177472 crossref_primary_10_1109_TIFS_2024_3468898 crossref_primary_10_1109_TIM_2024_3400355 crossref_primary_10_1002_tee_23490 crossref_primary_10_1007_s00521_021_06630_2 crossref_primary_10_3390_s21144635 crossref_primary_10_1109_TIFS_2023_3238546 crossref_primary_10_3390_sym14122686 crossref_primary_10_1109_ACCESS_2019_2901335 crossref_primary_10_1016_j_patcog_2023_109643 crossref_primary_10_1109_TCSVT_2024_3404865 crossref_primary_10_1007_s00542_017_3701_5 crossref_primary_10_1016_j_ijleo_2022_169717 crossref_primary_10_1109_TIFS_2023_3243782 crossref_primary_10_1109_TIM_2022_3154834 crossref_primary_10_1109_TIM_2019_2921135 crossref_primary_10_1016_j_patcog_2024_111208 crossref_primary_10_1109_ACCESS_2020_2979902 crossref_primary_10_1109_TIM_2021_3109978 crossref_primary_10_3390_e21111033 crossref_primary_10_1016_j_inffus_2021_10_004 crossref_primary_10_1007_s10772_021_09807_1 crossref_primary_10_1109_ACCESS_2020_2996646 crossref_primary_10_1007_s11704_021_0475_9 crossref_primary_10_1109_TIFS_2021_3118894 crossref_primary_10_1109_ACCESS_2020_2964788 crossref_primary_10_1016_j_knosys_2021_107159 crossref_primary_10_1049_iet_bmt_2018_5245 crossref_primary_10_1002_cpe_5697 crossref_primary_10_1016_j_measen_2022_100583 crossref_primary_10_3390_sym17030420 crossref_primary_10_1016_j_ins_2019_05_045 crossref_primary_10_3390_s25072279 crossref_primary_10_1109_ACCESS_2020_2967771 crossref_primary_10_3390_s21010132 crossref_primary_10_1016_j_infrared_2023_104728 crossref_primary_10_1109_TIFS_2022_3172218 crossref_primary_10_3390_sym11091167 crossref_primary_10_1007_s00138_018_0959_2 crossref_primary_10_1109_JSEN_2022_3149286 crossref_primary_10_1109_TIM_2020_3001410 crossref_primary_10_1049_bme2_12009 crossref_primary_10_1109_ACCESS_2023_3253203 crossref_primary_10_1109_TIM_2020_2995485 crossref_primary_10_1016_j_eswa_2021_116288 crossref_primary_10_1016_j_jksuci_2020_04_002 crossref_primary_10_1109_TII_2019_2900665 crossref_primary_10_1109_ACCESS_2021_3128273 crossref_primary_10_1109_ACCESS_2020_3009220 crossref_primary_10_1109_TIFS_2019_2917156 crossref_primary_10_1109_ACCESS_2019_2918503 crossref_primary_10_1109_TIFS_2021_3122073 crossref_primary_10_1109_JSEN_2021_3130951 crossref_primary_10_1016_j_patcog_2022_109199 crossref_primary_10_1007_s11760_024_03471_z crossref_primary_10_1109_ACCESS_2024_3382197 crossref_primary_10_1109_TIM_2022_3173276 crossref_primary_10_1016_j_inffus_2024_102716 crossref_primary_10_3390_app9081687 crossref_primary_10_1109_ACCESS_2019_2901017 crossref_primary_10_1109_TIM_2023_3301062 crossref_primary_10_1016_j_infrared_2022_104483 crossref_primary_10_1109_ACCESS_2021_3084037 crossref_primary_10_1109_ACCESS_2020_2970735 crossref_primary_10_1109_TIFS_2017_2756598 crossref_primary_10_1049_2024_3236602 crossref_primary_10_1016_j_imavis_2020_103987 crossref_primary_10_1016_j_neucom_2018_06_085 crossref_primary_10_1109_TIM_2023_3348905 crossref_primary_10_1088_1757_899X_806_1_012043 crossref_primary_10_1109_TIM_2021_3139707 crossref_primary_10_3390_electronics11203300 crossref_primary_10_3390_electronics13030501 crossref_primary_10_1109_TIM_2021_3062164 crossref_primary_10_3390_info9090213 crossref_primary_10_1109_TIFS_2018_2850320 crossref_primary_10_1109_TIFS_2019_2902819 crossref_primary_10_3390_s21051885 crossref_primary_10_3390_s22062234 crossref_primary_10_1109_TIFS_2019_2928507 crossref_primary_10_3390_math10213948 crossref_primary_10_1016_j_eswa_2021_114584 crossref_primary_10_1007_s00371_024_03286_6 crossref_primary_10_1109_TCSVT_2018_2875147 crossref_primary_10_1109_TIFS_2025_3562690 crossref_primary_10_4018_IJCVIP_2019100102 crossref_primary_10_1109_ACCESS_2019_2927230 crossref_primary_10_1109_TIFS_2018_2871778 crossref_primary_10_3390_math11143190 crossref_primary_10_1109_TCSVT_2022_3224203 crossref_primary_10_1007_s10489_018_1353_5 crossref_primary_10_18267_j_aip_131 crossref_primary_10_1109_TIM_2023_3261909 crossref_primary_10_1016_j_asoc_2021_107344 crossref_primary_10_1080_02533839_2021_1919561 crossref_primary_10_1016_j_adhoc_2021_102607
Cites_doi	10.1109/TIP.2009.2023153 10.1109/TIP.2011.2171697 10.1109/CVPR.2014.220 10.1162/neco.2009.10-08-881 10.1117/1.3572129 10.1093/ietisy/e90-d.8.1185 10.1109/34.587996 10.1109/TCSVT.2003.818350 10.1109/TIFS.2011.2158423 10.1109/42.34715 10.1109/TASLP.2014.2339736 10.1016/j.dsp.2014.12.003 10.1016/j.patrec.2011.04.021 10.1016/j.optlaseng.2011.03.004 10.3390/s131114339 10.1109/TIFS.2015.2398817 10.1016/j.eswa.2013.11.033 10.1016/j.ins.2013.10.009 10.1007/s00138-004-0149-2 10.3390/s131115048 10.1109/CVPR.1991.139758 10.1002/ima.20193 10.1109/ICPR.2006.848 10.1162/NECO_a_00052 10.1109/ICPR.2010.316 10.1016/j.ins.2013.10.010 10.1109/VLSIC.2006.1705285 10.1007/s12539-009-0046-5 10.1016/j.neunet.2012.02.023 10.1179/1743131X12Y.0000000013 10.1109/CVPR.2015.7298907 10.1016/j.neuroimage.2014.12.061 10.1016/j.neucom.2014.05.069
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2017 Distributed under a Creative Commons Attribution 4.0 International License
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2017 – notice: Distributed under a Creative Commons Attribution 4.0 International License
DBID	97E RIA RIE AAYXX CITATION 7SC 7SP 7TB 8FD FR3 JQ2 KR7 L7M L~C L~D 1XC VOOES
DOI	10.1109/TIFS.2017.2689724
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Mechanical & Transportation Engineering Abstracts Technology Research Database Engineering Research Database ProQuest Computer Science Collection Civil Engineering Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional Hyper Article en Ligne (HAL) Hyper Article en Ligne (HAL) (Open Access)
DatabaseTitle	CrossRef Civil Engineering Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Mechanical & Transportation Engineering Abstracts Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Engineering Research Database Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional
DatabaseTitleList	Civil Engineering Abstracts
Database_xml	– sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Computer Science
EISSN	1556-6021
EndPage	1829
ExternalDocumentID	oai:HAL:hal-01587285v1 10_1109_TIFS_2017_2689724 7890487
Genre	orig-research
GrantInformation_xml	– fundername: Scientific Research Foundation of Chongqing Technology and Business University grantid: 1352019; 2013-56-04 funderid: 10.13039/501100004500 – fundername: Direction générale des Entreprises of the Ministère de l’économie, de l’industrie et du numérique grantid: ITEA3 IDEA4SWIFT 12028 – fundername: National Natural Science Foundation of China grantid: 61402063 funderid: 10.13039/501100001809 – fundername: Natural Science Foundation Project of Chongqing grantid: cstc2013kjrc-qnrc40013 funderid: 10.13039/501100005230
GroupedDBID	0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFS ACIWK AENEX AETIX AGQYO AGSQL AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD HZ~ IFIPE IPLJI JAVBF LAI M43 O9- OCL P2P PQQKQ RIA RIE RNS AAYXX CITATION 7SC 7SP 7TB 8FD FR3 JQ2 KR7 L7M L~C L~D RIG 1XC VOOES
ID	FETCH-LOGICAL-c370t-4f85019f4fed5349c9dae448760725b53a9fe81e18b86e1ac31a5908b3aa666c3
IEDL.DBID	RIE
ISICitedReferencesCount	173
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000401340500005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1556-6013
IngestDate	Sun Oct 19 01:12:28 EDT 2025 Mon Jun 30 07:20:54 EDT 2025 Sat Nov 29 03:49:37 EST 2025 Tue Nov 18 22:35:26 EST 2025 Tue Aug 26 16:43:23 EDT 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	8
Keywords	Representation learning Deep learning Hand biometrics Finger-vein verification Convolutional autoencoder Convolutional neural network
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html Distributed under a Creative Commons Attribution 4.0 International License: http://creativecommons.org/licenses/by/4.0
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c370t-4f85019f4fed5349c9dae448760725b53a9fe81e18b86e1ac31a5908b3aa666c3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0003-4911-0393 0000-0002-7383-0588
OpenAccessLink	https://hal.science/hal-01587285
PQID	1897024127
PQPubID	85506
PageCount	14
ParticipantIDs	crossref_citationtrail_10_1109_TIFS_2017_2689724 crossref_primary_10_1109_TIFS_2017_2689724 proquest_journals_1897024127 ieee_primary_7890487 hal_primary_oai_HAL_hal_01587285v1
PublicationCentury	2000
PublicationDate	2017-08-01
PublicationDateYYYYMMDD	2017-08-01
PublicationDate_xml	– month: 08 year: 2017 text: 2017-08-01 day: 01
PublicationDecade	2010
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on information forensics and security
PublicationTitleAbbrev	TIFS
PublicationYear	2017
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Institute of Electrical and Electronics Engineers
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE) – name: Institute of Electrical and Electronics Engineers
References	zeiler (ref38) 2014 ref35 ref13 ref12 ref15 ref36 ref14 ref31 ref30 ref10 cire (ref34) 2013 ref2 ref1 ref39 ref17 ref16 ref19 ref18 sun (ref32) 2015 ref24 ref23 ref26 ref25 ref20 ref41 ref22 ref21 wei (ref9) 2008 ref28 ref27 ref29 ref8 krizhevsky (ref7) 2012 he (ref37) 2015 ref4 han (ref11) 1997; 15 ref3 ciresan (ref33) 2012 ref6 ref5 ref40
References_xml	– ident: ref5 doi: 10.1109/TIP.2009.2023153 – ident: ref4 doi: 10.1109/TIP.2011.2171697 – start-page: 2843 year: 2012 ident: ref33 article-title: Deep neural networks segment neuronal membranes in electron microscopy images publication-title: Proc Adv Neural Inf Process Syst – start-page: 1097 year: 2012 ident: ref7 article-title: ImageNet classification with deep convolutional neural networks publication-title: Proc NIPS – ident: ref30 doi: 10.1109/CVPR.2014.220 – ident: ref35 doi: 10.1162/neco.2009.10-08-881 – ident: ref23 doi: 10.1117/1.3572129 – ident: ref17 doi: 10.1093/ietisy/e90-d.8.1185 – ident: ref2 doi: 10.1109/34.587996 – ident: ref3 doi: 10.1109/TCSVT.2003.818350 – ident: ref6 doi: 10.1109/TIFS.2011.2158423 – ident: ref26 doi: 10.1109/42.34715 – start-page: 1 year: 2008 ident: ref9 article-title: Counterfeit iris detection based on texture analysis publication-title: Proc ICPR – ident: ref28 doi: 10.1109/TASLP.2014.2339736 – ident: ref22 doi: 10.1016/j.dsp.2014.12.003 – ident: ref16 doi: 10.1016/j.patrec.2011.04.021 – ident: ref19 doi: 10.1016/j.optlaseng.2011.03.004 – ident: ref12 doi: 10.3390/s131114339 – year: 2015 ident: ref32 publication-title: DeepID3 Face Recognition with Very Deep Neural Networks – ident: ref10 doi: 10.1109/TIFS.2015.2398817 – ident: ref13 doi: 10.1016/j.eswa.2013.11.033 – ident: ref18 doi: 10.1016/j.ins.2013.10.009 – ident: ref20 doi: 10.1007/s00138-004-0149-2 – ident: ref24 doi: 10.3390/s131115048 – ident: ref1 doi: 10.1109/CVPR.1991.139758 – ident: ref39 doi: 10.1002/ima.20193 – ident: ref27 doi: 10.1109/ICPR.2006.848 – year: 2015 ident: ref37 publication-title: Deep residual learning for image recognition – volume: 15 start-page: 39 year: 1997 ident: ref11 article-title: Anatomical study and clinical application of superficial palmar digital veins in finger replantation publication-title: Chinese J Clin Anatomy – ident: ref29 doi: 10.1162/NECO_a_00052 – ident: ref15 doi: 10.1109/ICPR.2010.316 – ident: ref25 doi: 10.1016/j.ins.2013.10.010 – ident: ref14 doi: 10.1109/VLSIC.2006.1705285 – ident: ref41 doi: 10.1007/s12539-009-0046-5 – ident: ref8 doi: 10.1016/j.neunet.2012.02.023 – start-page: 818 year: 2014 ident: ref38 article-title: Visualizing and understanding convolutional networks publication-title: Vision Computer – ident: ref21 doi: 10.1179/1743131X12Y.0000000013 – ident: ref31 doi: 10.1109/CVPR.2015.7298907 – ident: ref36 doi: 10.1016/j.neuroimage.2014.12.061 – start-page: 411 year: 2013 ident: ref34 article-title: Mitosis detection in breast cancer histology images with deep neural networks publication-title: Medical Image Computing and Computer-Assisted Intervention-MICCAI – ident: ref40 doi: 10.1016/j.neucom.2014.05.069
SSID	ssj0044168
Score	2.5847344
Snippet	Finger-vein biometrics has been extensively investigated for personal verification. Despite recent advances in finger-vein verification, current solutions...
SourceID	hal proquest crossref ieee
SourceType	Open Access Repository Aggregation Database Enrichment Source Index Database Publisher
StartPage	1816
SubjectTerms	Artificial neural networks Biometric recognition systems Computer Science Computer Vision and Pattern Recognition convolutional autoencoder convolutional neural network deep learning Feature extraction finger-vein verification Hand biometrics Image segmentation Iris recognition Machine learning Neural and Evolutionary Computing Neural networks representation learning Representations Signal and Image Processing Veins
Title	Deep Representation-Based Feature Extraction and Recovering for Finger-Vein Verification
URI	https://ieeexplore.ieee.org/document/7890487 https://www.proquest.com/docview/1897024127 https://hal.science/hal-01587285
Volume	12
WOSCitedRecordID	wos000401340500005&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: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1556-6021 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0044168 issn: 1556-6013 databaseCode: RIE dateStart: 20060101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3faxQxEB56xQd9sNoqnlYJ4pOYdrPZbJLHqj0qlCJay70t2WSWFmRbrndH__xmstlDUQTflpBkw36bzDeT-QHwTlCKdtN6XiiveVXLjjsdNNeq9MT_W5fSNV2c6rMzM5_br1vwYRMLg4jJ-QwP6DHd5YdrvyJT2SEFbUaCPYGJ1vUQqzWeulGqD2FvStU8vkTmG0xR2MPzL7Pv5MSlD8raWF1Wv8mgySV5QKbSKn-cx0nIzHb-b3lP4HEmk-xoQP8pbGG_CztjoQaW9-0uPPol6-AezD8j3rBvyQU2Rx71_GOUZoERIVwtkB3fLRdDxANzfWCko67TaBY5LpuNpsCrnl3E5i7b_Z7Bj9nx-acTngsscC91seRVZ1SkeF3VYVCyst4Gh1Ff03WhS9Uq6WyHRmAE09QonJfCUY30VjoX1R4vn8N2f93jC2BR8emqoNrWd3EiJZzAgJUKwrXWVFZOoRg_eeNz9nEqgvGzSVpIYRtCqSGUmozSFN5vhtwMqTf-1fltxHHTj5JmnxydNtQWCY_RpVFrMYU9Qm3TKwM2hf0R9ibv4NtGxGkjfxGlfvn3Ua_gIS1gcAbch-3lYoWv4YFfL69uF2_Sz3kP6Bnf-A
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PaxQxFH60VdAeWm0rXa0axJOYdjJJJsmxrV22uC6ia9lbyCQZLMi0bHcX_3yTTGaxKIK3ISSZMN8k73sv7wfAWxJTtMva4oJbgVlFG2yEE1jw0kb-X5uUrulqLCYTOZupzxvwfh0L471Pzmf-OD6mu3x3Y5fRVHYSgzYDwd6EB5yxsuiitfpzN8j1LvCN8wqH19B8h0kKdTK9HH6NblziuKykEiW7J4U2v0cfyFRc5Y8TOYmZ4e7_LfAJ7GQ6iU47_J_Chm_3YLcv1YDyzt2D7d_yDu7D7IP3t-hLcoLNsUctPgvyzKFICZdzjy5-LuZdzAMyrUNRS12l0SiwXDTsjYHXLboKzU22_B3At-HF9HyEc4kFbKkoFpg1kgeS17DGO06ZssoZHzQ2URWi5DWnRjVeEh_glJUnxlJiYpX0mhoTFB9Ln8FWe9P6Q0BB9WmY43VtmzARJ4Z45xl3xNRKMkUHUPSfXNucfzyWwfihkx5SKB1R0hElnVEawLv1kNsu-ca_Or8JOK77xbTZo9Oxjm2B8khRSr4iA9iPqK17ZcAGcNTDrvMevtMkTBsYDCnF87-Peg2PRtNPYz2-nHx8AY_jYjrXwCPYWsyX_iU8tKvF9d38VfpRfwG0TuM_
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=Deep+Representation-Based+Feature+Extraction+and+Recovering+for+Finger-Vein+Verification&rft.jtitle=IEEE+transactions+on+information+forensics+and+security&rft.au=Huafeng+Qin&rft.au=El-Yacoubi%2C+Mounim+A.&rft.date=2017-08-01&rft.pub=IEEE&rft.issn=1556-6013&rft.volume=12&rft.issue=8&rft.spage=1816&rft.epage=1829&rft_id=info:doi/10.1109%2FTIFS.2017.2689724&rft.externalDocID=7890487
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1556-6013&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1556-6013&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1556-6013&client=summon