Person-Specific Face Antispoofing With Subject Domain Adaptation
Face antispoofing is important to practical face recognition systems. In previous works, a generic antispoofing classifier is trained to detect spoofing attacks on all subjects. However, due to the individual differences among subjects, the generic classifier cannot generalize well to all subjects....
Saved in:
| Published in | IEEE transactions on information forensics and security Vol. 10; no. 4; pp. 797 - 809 |
|---|---|
| Main Authors | , , , |
| Format | Journal Article |
| Language | English |
| Published |
IEEE
01.04.2015
|
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | Face antispoofing is important to practical face recognition systems. In previous works, a generic antispoofing classifier is trained to detect spoofing attacks on all subjects. However, due to the individual differences among subjects, the generic classifier cannot generalize well to all subjects. In this paper, we propose a person-specific face antispoofing approach. It recognizes spoofing attacks using a classifier specifically trained for each subject, which dismisses the interferences among subjects. Moreover, considering the scarce or void fake samples for training, we propose a subject domain adaptation method to synthesize virtual features, which makes it tractable to train well-performed individual face antispoofing classifiers. The extensive experiments on two challenging data sets: 1) CASIA and 2) REPLAY-ATTACK demonstrate the prospect of the proposed approach. |
|---|---|
| AbstractList | Face antispoofing is important to practical face recognition systems. In previous works, a generic antispoofing classifier is trained to detect spoofing attacks on all subjects. However, due to the individual differences among subjects, the generic classifier cannot generalize well to all subjects. In this paper, we propose a person-specific face antispoofing approach. It recognizes spoofing attacks using a classifier specifically trained for each subject, which dismisses the interferences among subjects. Moreover, considering the scarce or void fake samples for training, we propose a subject domain adaptation method to synthesize virtual features, which makes it tractable to train well-performed individual face antispoofing classifiers. The extensive experiments on two challenging data sets: 1) CASIA and 2) REPLAY-ATTACK demonstrate the prospect of the proposed approach. |
| Author | Li, Stan Z. Dong Yi Zhen Lei Jianwei Yang |
| Author_xml | – sequence: 1 surname: Jianwei Yang fullname: Jianwei Yang email: yjwterry@163.com organization: Nat. Lab. of Pattern Recognition, Inst. of Autom., Beijing, China – sequence: 2 surname: Zhen Lei fullname: Zhen Lei email: zlei@cbsr.ia.ac.cn organization: Nat. Lab. of Pattern Recognition, Inst. of Autom., Beijing, China – sequence: 3 surname: Dong Yi fullname: Dong Yi email: dyi@cbsr.ia.ac.cn organization: Nat. Lab. of Pattern Recognition, Inst. of Autom., Beijing, China – sequence: 4 givenname: Stan Z. surname: Li fullname: Li, Stan Z. email: stan.zq.li@gmail.com organization: Nat. Lab. of Pattern Recognition, Inst. of Autom., Beijing, China |
| BookMark | eNp9kE1PwkAQhjcGEwH9AcZL_0BxZr-gNwmKkpBoAsZjM93u6hLYbbr14L8XAuHgwdO8l2fmnWfAeiEGy9gtwggRivv1Yr4acUA14hKEAH3B-qiUzjVw7J0ziis2SGkDICXqSZ89vNk2xZCvGmu88yabk7HZNHQ-NTE6Hz6zD999ZavvamNNlz3GHfmQTWtqOup8DNfs0tE22ZvTHLL3-dN69pIvX58Xs-kyN1yrLneGnLKiErJGLLgkVVcSpcICCJzTvJZIMHbVhGpdFVYZs39CkKG6KJwAMWR43GvamFJrXdm0fkftT4lQHhSUBwXlQUF5UrBnxn8Y44-tu5b89l_y7kh6a-350hgkcoHiFx3va3M |
| CODEN | ITIFA6 |
| CitedBy_id | crossref_primary_10_1007_s13042_025_02573_5 crossref_primary_10_1109_ACCESS_2020_2985453 crossref_primary_10_1109_TIFS_2022_3178240 crossref_primary_10_1049_iet_bmt_2017_0077 crossref_primary_10_1109_TCSVT_2019_2949868 crossref_primary_10_1109_TIFS_2021_3111766 crossref_primary_10_1016_j_patcog_2022_109148 crossref_primary_10_1117_1_JEI_26_4_043007 crossref_primary_10_55525_tjst_1142626 crossref_primary_10_1016_j_compeleceng_2021_107293 crossref_primary_10_1016_j_patcog_2021_107888 crossref_primary_10_1049_bme2_12041 crossref_primary_10_1109_TIFS_2022_3192999 crossref_primary_10_48175_IJARSCT_9732 crossref_primary_10_1109_TIFS_2020_2985530 crossref_primary_10_1016_j_imavis_2019_11_004 crossref_primary_10_1109_ACCESS_2017_2729161 crossref_primary_10_1016_j_jvcir_2019_102746 crossref_primary_10_1007_s00530_023_01070_5 crossref_primary_10_1109_TIFS_2021_3135748 crossref_primary_10_1016_j_eswa_2019_113002 crossref_primary_10_1109_ACCESS_2023_3292407 crossref_primary_10_1109_TIFS_2016_2555286 crossref_primary_10_1109_ACCESS_2021_3087917 crossref_primary_10_1186_s13635_022_00135_8 crossref_primary_10_3390_bdcc7010037 crossref_primary_10_1007_s11263_024_02178_5 crossref_primary_10_1016_j_patcog_2020_107696 crossref_primary_10_1109_TIFS_2020_3029879 crossref_primary_10_1007_s11042_023_14453_7 crossref_primary_10_1109_TBIOM_2022_3220406 crossref_primary_10_1109_TCSVT_2020_3046505 crossref_primary_10_1109_JSTSP_2020_3001719 crossref_primary_10_1109_TIFS_2018_2801312 crossref_primary_10_1016_j_inffus_2021_04_015 crossref_primary_10_1109_TCSVT_2021_3133620 crossref_primary_10_1109_TIFS_2023_3240841 crossref_primary_10_1371_journal_pone_0238058 crossref_primary_10_1002_cpe_4641 crossref_primary_10_1109_TBIOM_2023_3312128 crossref_primary_10_1109_TIFS_2020_3002390 crossref_primary_10_1109_TIFS_2023_3266138 crossref_primary_10_1007_s10044_020_00875_8 crossref_primary_10_3390_rs14205191 crossref_primary_10_1109_TIFS_2016_2578288 crossref_primary_10_1016_j_neucom_2020_12_095 crossref_primary_10_1109_ACCESS_2020_2969480 crossref_primary_10_1109_TIFS_2021_3125603 crossref_primary_10_1016_j_patcog_2018_08_019 crossref_primary_10_1109_TMM_2017_2750415 crossref_primary_10_1109_LSP_2016_2630740 crossref_primary_10_1109_TIFS_2015_2458700 |
| Cites_doi | 10.1109/TPAMI.2008.222 10.1109/IJCB.2011.6117509 10.1109/CVPRW.2013.22 10.1007/s11235-010-9313-3 10.1109/FG.2011.5771438 10.1016/0169-7439(87)80096-5 10.1109/CVBVS.2000.855246 10.1109/ICB.2013.6612968 10.1109/IJCB.2011.6117478 10.1109/ICB.2013.6612957 10.1109/CVPRW.2008.4563115 10.1109/IJCB.2011.6117510 10.5244/C.26.101 10.1109/FUZZY.2010.5584864 10.1109/ICCV.2007.4409068 10.1109/AUTOID.2005.20 10.1109/AFGR.2008.4813353 10.1109/ICCV.2003.1238414 10.1109/ICB.2013.6612955 10.1109/TIFS.2007.902037 10.1007/11752790_2 10.1109/ICB.2013.6612981 10.1109/ICB.2012.6199754 10.1109/ICCV.2013.398 10.1109/BTAS.2013.6712690 10.1109/CVPR.2010.5539975 10.1117/12.541955 10.1109/IJCB.2011.6117522 10.1049/iet-bmt.2012.0071 10.1109/ICIP.2011.6116484 10.1109/CVPR.1997.609330 10.1117/1.OE.52.11.113102 10.1109/ICB.2013.6613026 10.1109/CVPR.2013.454 10.1109/ICARCV.2012.6485156 10.1016/j.patrec.2013.02.002 |
| ContentType | Journal Article |
| DBID | 97E RIA RIE AAYXX CITATION |
| DOI | 10.1109/TIFS.2015.2403306 |
| DatabaseName | IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Computer Science |
| EISSN | 1556-6021 |
| EndPage | 809 |
| ExternalDocumentID | 10_1109_TIFS_2015_2403306 7041231 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: National Natural Science Foundation of China grantid: 61203267; 61375037; 61473291 funderid: 10.13039/501100001809 – fundername: National Science and Technology Support Program grantid: 2013BAK02B01 – fundername: AuthenMetric Research and Development Funds – fundername: Chinese Academy of Sciences, Beijing, China grantid: KGZD-EW-102-2 |
| 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 RIG |
| ID | FETCH-LOGICAL-c265t-fcaf5e3b34d11924a5db4145190a0ff62d41a07fb8ad6b9e5cc3063acad99f303 |
| IEDL.DBID | RIE |
| ISSN | 1556-6013 |
| IngestDate | Tue Jul 01 02:34:10 EDT 2025 Thu Apr 24 23:10:59 EDT 2025 Tue Aug 26 16:50:02 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 4 |
| Keywords | Face anti-spoofing subject domain adaptation person-specific |
| Language | English |
| License | https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c265t-fcaf5e3b34d11924a5db4145190a0ff62d41a07fb8ad6b9e5cc3063acad99f303 |
| PageCount | 13 |
| ParticipantIDs | crossref_primary_10_1109_TIFS_2015_2403306 ieee_primary_7041231 crossref_citationtrail_10_1109_TIFS_2015_2403306 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2015-April 2015-4-00 |
| PublicationDateYYYYMMDD | 2015-04-01 |
| PublicationDate_xml | – month: 04 year: 2015 text: 2015-April |
| PublicationDecade | 2010 |
| PublicationTitle | IEEE transactions on information forensics and security |
| PublicationTitleAbbrev | TIFS |
| PublicationYear | 2015 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| References | ref35 ref13 ref34 ref37 ref15 ref36 ref31 ref30 ref33 ref11 de freitas pereira (ref12) 2013 ref32 ref2 ref39 chingovska (ref10) 2012 ref16 ref19 tan (ref3) 2010 rosipal (ref42) 2006 erdogmus (ref24) 2013 tang (ref38) 2003 ref23 ref26 ref25 bao (ref18) 2009 ref20 ref41 ref44 ref21 ref43 chetty (ref17) 2005; 57 ref28 ref27 ref29 ref8 ref7 de marsico (ref22) 2012 ref9 ref4 ref6 ref5 ref40 määttä (ref1) 2011 sun (ref14) 2007 |
| References_xml | – start-page: 233 year: 2009 ident: ref18 article-title: A liveness detection method for face recognition based on optical flow field publication-title: Proc Int Conf Image Anal Process – ident: ref39 doi: 10.1109/TPAMI.2008.222 – start-page: 252 year: 2007 ident: ref14 article-title: Blinking-based live face detection using conditional random fields publication-title: Proc ICB – ident: ref7 doi: 10.1109/IJCB.2011.6117509 – start-page: 1 year: 2012 ident: ref10 article-title: On the effectiveness of local binary patterns in face anti-spoofing publication-title: Proc Int Conf Biometrics Special Interest Group (BIOSIG) – ident: ref31 doi: 10.1109/CVPRW.2013.22 – ident: ref28 doi: 10.1007/s11235-010-9313-3 – ident: ref26 doi: 10.1109/FG.2011.5771438 – ident: ref43 doi: 10.1016/0169-7439(87)80096-5 – ident: ref25 doi: 10.1109/CVBVS.2000.855246 – start-page: 121 year: 2013 ident: ref12 article-title: LBP - TOP based countermeasure against face spoofing attacks publication-title: Computer Vision – ident: ref5 doi: 10.1109/ICB.2013.6612968 – ident: ref33 doi: 10.1109/IJCB.2011.6117478 – ident: ref23 doi: 10.1109/ICB.2013.6612957 – ident: ref21 doi: 10.1109/CVPRW.2008.4563115 – start-page: 1 year: 2011 ident: ref1 article-title: Face spoofing detection from single images using micro-texture analysis publication-title: Proc Int Joint Conf Biometrics (IJCB 2011) doi: 10.1109/IJCB.2011.6117510 – start-page: 1 year: 2013 ident: ref24 article-title: Spoofing 2D face recognition systems with 3D masks publication-title: Proc Int Conf Biometrics Special Interest Group (BIOSIG) – ident: ref34 doi: 10.5244/C.26.101 – ident: ref16 doi: 10.1109/FUZZY.2010.5584864 – ident: ref2 doi: 10.1109/ICCV.2007.4409068 – ident: ref19 doi: 10.1109/AUTOID.2005.20 – ident: ref32 doi: 10.1109/AFGR.2008.4813353 – start-page: 504 year: 2010 ident: ref3 article-title: Face liveness detection from a single image with sparse low rank bilinear discriminative model publication-title: Proc 11th ECCV – start-page: 687 year: 2003 ident: ref38 article-title: Face sketch synthesis and recognition publication-title: Proc 9th IEEE Int Conf Comput Vis doi: 10.1109/ICCV.2003.1238414 – ident: ref11 doi: 10.1109/ICB.2013.6612955 – ident: ref15 doi: 10.1109/TIFS.2007.902037 – start-page: 34 year: 2006 ident: ref42 article-title: Overview and recent advances in partial least squares publication-title: Subspace Latent Structure and Feature Selection doi: 10.1007/11752790_2 – ident: ref4 doi: 10.1109/ICB.2013.6612981 – ident: ref40 doi: 10.1109/ICB.2012.6199754 – ident: ref37 doi: 10.1109/ICCV.2013.398 – ident: ref13 doi: 10.1109/BTAS.2013.6712690 – volume: 57 start-page: 17 year: 2005 ident: ref17 article-title: Audio-visual multimodal fusion for biometric person authentication and liveness verification publication-title: Proc NICTA-HCSNet Multimodal User Interact Workshop (MMUI) – ident: ref35 doi: 10.1109/CVPR.2010.5539975 – ident: ref8 doi: 10.1117/12.541955 – ident: ref29 doi: 10.1109/IJCB.2011.6117522 – ident: ref20 doi: 10.1049/iet-bmt.2012.0071 – ident: ref9 doi: 10.1109/ICIP.2011.6116484 – ident: ref41 doi: 10.1109/CVPR.1997.609330 – ident: ref27 doi: 10.1117/1.OE.52.11.113102 – ident: ref6 doi: 10.1109/ICB.2013.6613026 – ident: ref44 doi: 10.1109/CVPR.2013.454 – ident: ref30 doi: 10.1109/ICARCV.2012.6485156 – start-page: 73 year: 2012 ident: ref22 article-title: Moving face spoofing detection via 3D projective invariants publication-title: Proc 5th IAPR Int Conf Biometrics (ICB) – ident: ref36 doi: 10.1016/j.patrec.2013.02.002 |
| SSID | ssj0044168 |
| Score | 2.370122 |
| Snippet | Face antispoofing is important to practical face recognition systems. In previous works, a generic antispoofing classifier is trained to detect spoofing... |
| SourceID | crossref ieee |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 797 |
| SubjectTerms | Adaptation models Face Face anti-spoofing Face recognition Feature extraction person-specific Shape subject domain adaptation Training Vectors |
| Title | Person-Specific Face Antispoofing With Subject Domain Adaptation |
| URI | https://ieeexplore.ieee.org/document/7041231 |
| Volume | 10 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3dS8MwEA9zT_rgdFOcX-TBJ7G1XZI2fXOoZQoTwQ33VtJ8aFG7Id2Lf725fowhIr6UUhIId9fcXXL3-yF0RpQwRBPqUKLtQxnP4URwh0sdyogHocehwXn8EIym9H7GZi10seqF0VqXxWfahdfyLl_N5RKOyi5DAIeCpukNm7hVvVrNrmu9etX2xljg2CSD1DeYvhddTu7iJyjiYi6AzxEgN1rzQWukKqVPiTto3KymKiV5c5dF6sqvH0CN_13uDtqug0s8rKxhF7V03kWdhrgB1_9xF22toRD20NVjGXU7JRW9ySSOhdR4mBeZTXmt7eUv-DkrXrHdY-DQBt_MP0SW46ESi-oefw9N49vJ9cipiRUcOQhY4RgpDNMkJVT5kIAJplIKlL2RJzxjgoGivvBCk3KhgjTSTEorNSKkUFFkrNPbR-18nusDhJnxB5KExFcDTY3h3Ne-ShXnFJDlhN9HXiPqRNao40B-8Z6U2YcXJaCdBLST1Nrpo_PVlEUFufHX4B4IfjWwlvnh75-P0CZMripvjlG7-FzqExtUFOlpaU3f0DHHdw |
| linkProvider | IEEE |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LS8NAEB5ED-rBVxXrcw-exNRsN5tsbha11EeLYIu9hc0-tKipSHrx17uTpKWIiJcQwiYsM5OdnZ2Z7wM4YVpaZljgBcy4i7a-J5gUnlAmUrEII19gg3O3F3YGwe2QDxfgbNYLY4wpis9MA2-LXL4eqwkelZ1HCA6FTdNLzu9zWnZrTddd59fLxjfOQ8-FGazKYVI_Pu_ftB-xjIs3EH6OIb3RnBeao1UpvEp7HbrT-ZTFJK-NSZ421NcPqMb_TngD1qrtJWmV9rAJCybbgvUpdQOp_uQtWJ3DIazBxUOx7_YKMno7UqQtlSGtLB-5oNdZX_ZMnkb5C3GrDB7bkKvxuxxlpKXlR5nJ34ZB-7p_2fEqagVPNUOee1ZJyw1LWaAphmCS6zRA0t7Yl761YVMHVPqRTYXUYRobrpSTGpNK6ji2zu3twGI2zswuEG5pU7GIUd00gbVCUEN1qoUIEFtO0jr4U1EnqsIdR_qLt6SIP_w4Qe0kqJ2k0k4dTmevfJSgG38NrqHgZwMrme_9_vgYljv97n1yf9O724cV_FBZh3MAi_nnxBy6LUaeHhWW9Q1mzsrA |
| 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=Person-Specific+Face+Antispoofing+With+Subject+Domain+Adaptation&rft.jtitle=IEEE+transactions+on+information+forensics+and+security&rft.au=Jianwei+Yang&rft.au=Zhen+Lei&rft.au=Dong+Yi&rft.au=Li%2C+Stan+Z.&rft.date=2015-04-01&rft.pub=IEEE&rft.issn=1556-6013&rft.volume=10&rft.issue=4&rft.spage=797&rft.epage=809&rft_id=info:doi/10.1109%2FTIFS.2015.2403306&rft.externalDocID=7041231 |
| 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 |