Face Recognition Using Dense SIFT Feature Alignment
This paper addresses face recognition problem in a more challenging scenario where the training and test samples are both subject to the visual variations of poses, expressions and misalignments. We employ dense Scale-invariant feature transform（SIFT） feature matching as a generic transformation to...
Saved in:
| Published in | Chinese Journal of Electronics Vol. 25; no. 6; pp. 1034 - 1039 |
|---|---|
| Main Authors | , , , , , |
| Format | Journal Article |
| Language | English |
| Published |
Published by the IET on behalf of the CIE
01.11.2016
|
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | This paper addresses face recognition problem in a more challenging scenario where the training and test samples are both subject to the visual variations of poses, expressions and misalignments. We employ dense Scale-invariant feature transform（SIFT） feature matching as a generic transformation to roughly align training samples; and then identify input facial images via an improved sparse representation model based on the aligned training samples. Compared with previous methods, the extensive experimental results demonstrate the effectiveness of our method for the task of face recognition on three benchmark datasets. |
|---|---|
| AbstractList | This paper addresses face recognition problem in a more challenging scenario where the training and test samples are both subject to the visual variations of poses, expressions and misalignments. We employ dense Scale-invariant feature transform（SIFT） feature matching as a generic transformation to roughly align training samples; and then identify input facial images via an improved sparse representation model based on the aligned training samples. Compared with previous methods, the extensive experimental results demonstrate the effectiveness of our method for the task of face recognition on three benchmark datasets. This paper addresses face recognition problem in a more challenging scenario where the training and test samples are both subject to the visual variations of poses, expressions and misalignments. We employ dense Scale-invariant feature transform (SIFT) feature matching as a generic transformation to roughly align training samples; and then identify input facial images via an improved sparse representation model based on the aligned training samples. Compared with previous methods, the extensive experimental results demonstrate the effectiveness of our method for the task of face recognition on three benchmark datasets. |
| Author | Zhou, Quan Wang, Lei Wei, Xin Zheng, Baoyu Zhou, Yu Shafiq, ur Rehman |
| AuthorAffiliation | Key Lab of Ministry of Education for Broad Band Communication and Sensor Network Technology, Nanjing University of Posts and Telecommunications, Nanjing 210003, China Department of Applied Physics and Electronics, Umea University, Umea, Sweden School of Computer Science, Beijing University of Posts and Telecommunications, Beijing 100876, China |
| Author_xml | – sequence: 1 givenname: Quan surname: Zhou fullname: Zhou, Quan email: quan.zhou@njupt.edu.cn organization: Key Lab of Ministry of Education for Broad Band Communication and Sensor Network Technology, Nanjing University of Posts and Telecommunications, Nanjing 210003, China – sequence: 2 givenname: ur Rehman surname: Shafiq fullname: Shafiq, ur Rehman organization: Department of Applied Physics and Electronics, Umeå University, Umeå, Sweden – sequence: 3 givenname: Yu surname: Zhou fullname: Zhou, Yu organization: School of Computer Science, Beijing University of Posts and Telecommunications, Beijing 100876, China – sequence: 4 givenname: Xin surname: Wei fullname: Wei, Xin organization: Key Lab of Ministry of Education for Broad Band Communication and Sensor Network Technology, Nanjing University of Posts and Telecommunications, Nanjing 210003, China – sequence: 5 givenname: Lei surname: Wang fullname: Wang, Lei organization: Key Lab of Ministry of Education for Broad Band Communication and Sensor Network Technology, Nanjing University of Posts and Telecommunications, Nanjing 210003, China – sequence: 6 givenname: Baoyu surname: Zheng fullname: Zheng, Baoyu organization: Key Lab of Ministry of Education for Broad Band Communication and Sensor Network Technology, Nanjing University of Posts and Telecommunications, Nanjing 210003, China |
| BackLink | https://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-129909$$DView record from Swedish Publication Index |
| BookMark | eNqFkUlLBDEQhYMoOC5nr41X6bGy9XIcx2kXBMHtGtLpShuZSY-9IP57M4wLiMupSPG-epVXO2TTNx4JOaAwpiDyY_OEYwY0Ca8xAN0gIwapjKXM000yosBYLBLJt8l-17kSIElBUspGhBfaYHSDpqm9613jo_vO-To6Rd9hdHtR3EUF6n5oMZrMXe0X6Ps9smX1vMP997pL7ovZ3fQ8vro-u5hOrmIjaBYMU8uFQGqFrkyJ1OhEasbLCkvDrRVAhagYp5XOKkiAizTTFRoJxlayNJbvkng9t3vB5VCqZesWun1VjXbq1D1MVNPWalgMirI8hzzo5Vpv2qbrWrTKuF6vPtW32s0VBbUKS4Ww1CqsVSOEFbjjb9yH0-9EtiZe3Bxf_5Or6eWMnRQAnLOAHq1Rh716aobWhwj_MDr8QR3mKSpBZKCWlf0SmcfG18_hfJ8bhTsnaZILzt8AixijRg |
| CitedBy_id | crossref_primary_10_1007_s00500_019_03870_2 crossref_primary_10_1108_SR_06_2017_0115 crossref_primary_10_1049_iet_bmt_2017_0160 crossref_primary_10_1049_iet_cps_2018_5045 crossref_primary_10_1109_ACCESS_2020_2964298 |
| ContentType | Journal Article |
| Copyright | Chinese Institute of Electronics 2016 Chinese Institute of Electronics |
| Copyright_xml | – notice: Chinese Institute of Electronics – notice: 2016 Chinese Institute of Electronics |
| DBID | 2RA 92L CQIGP W92 ~WA AAYXX CITATION ADTPV AOWAS D93 |
| DOI | 10.1049/cje.2016.10.001 |
| DatabaseName | 维普_期刊 中文科技期刊数据库-CALIS站点 中文科技期刊数据库-7.0平台 中文科技期刊数据库-工程技术 中文科技期刊数据库- 镜像站点 CrossRef SwePub SwePub Articles SWEPUB Umeå universitet |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| DocumentTitleAlternate | Face Recognition Using Dense SIFT Feature Alignment |
| EISSN | 2075-5597 |
| EndPage | 1039 |
| ExternalDocumentID | oai_DiVA_org_umu_129909 10_1049_cje_2016_10_001 CJE2BF00332 670676943 |
| Genre | article |
| GrantInformation_xml | – fundername: National Natural Science Foundation of China grantid: 61201164; 61201165; 61201326; 61271240; 61401228; 61571240; 61501253 – fundername: State Key Development Program of Basic Research of China grantid: 2013CB329005 – fundername: University Natural Science Research Project of Jiangsu Province grantid: 11KJB510016 – fundername: Jiangsu Postdoctoral Program grantid: 1201014C; 1501019A – fundername: Specialized Research Fund for the Doctoral Program of Higher Education grantid: 20113223120002 – fundername: China Postdoctoral Science Foundation grantid: 2013M531392; 2015M581841 – fundername: National Natural Science Foundation of China funderid: 61201164; 61201165; 61201326; 61271240; 61401228; 61571240; 61501253 – fundername: Jiangsu Postdoctoral Program funderid: 1201014C; 1501019A – fundername: University Natural Science Research Project of Jiangsu Province funderid: 11KJB510016 – fundername: China Postdoctoral Science Foundation funderid: 2013M531392; 2015M581841 – fundername: State Key Development Program of Basic Research of China funderid: 2013CB329005 – fundername: Specialized Research Fund for the Doctoral Program of Higher Education funderid: 20113223120002 |
| GroupedDBID | 2RA 92L ALMA_UNASSIGNED_HOLDINGS CDYEO CQIGP W92 ~WA 0R O9- 1OC 24P 33P ACCZN AJAOE DCZOG IAO ITC SUPJJ AAYXX CITATION ADTPV AOWAS D93 |
| ID | FETCH-LOGICAL-c4182-47f344e1f4adcbe1ca65a23bdebc3ff40144d231da8d0603478adec50cfd5bcf3 |
| IEDL.DBID | IDLOA |
| ISSN | 1022-4653 2075-5597 |
| IngestDate | Thu Aug 21 06:44:49 EDT 2025 Thu Apr 24 23:05:54 EDT 2025 Tue Jul 01 03:19:53 EDT 2025 Wed Jan 22 16:30:21 EST 2025 Tue Jan 05 21:44:30 EST 2021 Thu May 09 18:24:34 EDT 2019 Wed Feb 14 10:08:24 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 6 |
| Keywords | Face recognition Sparse representation Dense SIFT feature alignment |
| Language | English |
| License | http://doi.wiley.com/10.1002/tdm_license_1.1 http://onlinelibrary.wiley.com/termsAndConditions#vor |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c4182-47f344e1f4adcbe1ca65a23bdebc3ff40144d231da8d0603478adec50cfd5bcf3 |
| Notes | This paper addresses face recognition problem in a more challenging scenario where the training and test samples are both subject to the visual variations of poses, expressions and misalignments. We employ dense Scale-invariant feature transform（SIFT） feature matching as a generic transformation to roughly align training samples; and then identify input facial images via an improved sparse representation model based on the aligned training samples. Compared with previous methods, the extensive experimental results demonstrate the effectiveness of our method for the task of face recognition on three benchmark datasets. Face recognition Dense SIFT feature alignment Sparse representation 10-1284/TN |
| PageCount | 6 |
| ParticipantIDs | wiley_primary_10_1049_cje_2016_10_001_CJE2BF00332 iet_journals_10_1049_cje_2016_10_001 crossref_primary_10_1049_cje_2016_10_001 crossref_citationtrail_10_1049_cje_2016_10_001 swepub_primary_oai_DiVA_org_umu_129909 chongqing_primary_670676943 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | November 2016 |
| PublicationDateYYYYMMDD | 2016-11-01 |
| PublicationDate_xml | – month: 11 year: 2016 text: November 2016 |
| PublicationDecade | 2010 |
| PublicationTitle | Chinese Journal of Electronics |
| PublicationTitleAlternate | Chinese of Journal Electronics |
| PublicationYear | 2016 |
| Publisher | Published by the IET on behalf of the CIE |
| Publisher_xml | – name: Published by the IET on behalf of the CIE |
| SSID | ssib006705112 ssib002062277 ssib051367563 ssib028779094 ssj0002952017 ssib058688246 |
| Score | 2.1109073 |
| Snippet | This paper addresses face recognition problem in a more challenging scenario where the training and test samples are both subject to the visual variations of... |
| SourceID | swepub crossref wiley iet chongqing |
| SourceType | Open Access Repository Enrichment Source Index Database Publisher |
| StartPage | 1034 |
| SubjectTerms | dense scale‐invariant feature transform feature matching Dense SIFT feature alignment dense SIFT feature matching Face recognition generic transformation image matching image representation learning (artificial intelligence) Sparse representation test samples training samples transforms |
| Title | Face Recognition Using Dense SIFT Feature Alignment |
| URI | http://lib.cqvip.com/qk/86774X/201606/670676943.html http://digital-library.theiet.org/content/journals/10.1049/cje.2016.10.001 https://onlinelibrary.wiley.com/doi/abs/10.1049%2Fcje.2016.10.001 https://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-129909 |
| Volume | 25 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1NT-MwELWgXPaCQIDIFlAOCHEJJI7tJMdCiQABB77EzXL80S2CFBD9_8w4SaFCaDk6cmxrPPK8l4zfELLLdOoSrpKIOlpEjOI5yBWPFFAgw2xuKp_tfnklTu_Y-QN_-Mx_MuMR1sqIui9u-LXcNjcPMHUbzuHD1sZNQRLAt4f6EeUuE3Hgs7SACS3RLEt4jyydDS9aguWDUSwo_XLrUmQxoo2uDdQhK2JfORFZUITCY50W0PdZUIrh36QevUKAmQtpi7DemezoPOL1IatcIcst1gwHjXOskgVbr5G0VNqG113e0KQOfdZAOAQ-a8Obs_I2RFg4fbPh4Gk88skC6-SuPLk9Po3aygmRZkAYIpa5lDGbOKaMrmyileCKppWxFeyNY0ijDCA7o3ITizhlWa6M1TzWzvBKu3SD9OpJbTdJCJjIWaCBueIVc1zlQmQut3HmqsKJggakPzOEfGkUMiSYFlNnWRqQg840Urei41j74kn6n9-skGBXiXbFB2DXgOzPXuhG-7HrLthadv7wc7f-XLfj8xMJKJjlsXwxLiB7zVbNZkO97eH4fiDB6eT0GbW2IWIXAUn8Vv5vVTg-PSqxRh79-7sV9skfbDU3HLdI7_1tarcB6rxXO60PfwCOgPAD |
| linkProvider | Institution of Engineering and Technology |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Lb9QwELZKe4BLBSoVYaHNoUJcUhLHdpLj0jbaPg90t6q4WI4fy6KSbZfd_8-M86CLVCH1mGhsR-PHfOPMfEPIAdOpS7hKIupoETGK5yBXPFLgAhlmc1P5aPfLKzGasLNbfvsoF6bhh-gv3HBn-PMaNzheSDcOJ0OSTP0TaS4Tceijs8AD2kJsAyt7a3gz-T75a4RiQemjbEuRxYgyumeOpGW8JaHC85sWHLr1VVkw1B0JyDpOIFZ8-WdUpGT4Ma-nD2Bo1kzbi5ld9vSj68jXm67yNdluMWc4bBbJG7Jh6x2Slkrb8FsXPzSvQx89EB6DX2vD69NyHCI8XC1sOLybTX3QwFsyKU_GR6OoraAQaQaOQ8QylzJmE8eU0ZVNtBJc0bQytoI5cgzdKQMIz6jcxCJOWZYrYzWPtTO80i7dJZv1vLbvSAjYyFlwB3PFK-a4yoXIXG7jzFWFEwUNyKBXhLxvmDIkqBpDaFkakMNONVK35ONYA-NO-p_grJCgV4l6xReg14B87ht0vT0pegC6lu3e-_202GBN7OjsRAIaZnks740LyKdmqvrRkHf7eHYzlPPFVK5-Iec2WO4iIImfyv99FfZPv5ZYK4--f0abffJyNL68kBenV-cD8gqlmhTID2RzuVjZj4CFltVeu9j_AGl-9og |
| linkToPdf | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LT9wwELbaRap6qahK1bCF5oCqXkITx3aS48ISAW0RallU9WI5fiyLaJYuu_-fGecBWwlV6jHR2InGj_km-fwNIXtMpy7hKomoo0XEKO6DXPFIQQpkmM1N5dnu387E8YSd_uQdmxDPwjT6EP0HN1wZfr_GBX5rXJNvMtTI1NeocpmIfU_OggRog0NsigdkY3Q5-TV5iEGxoPTRYUuRxQgyumuOmmW81aDC7ZsWHLr1RVmQ6Y76Y50kECs-__VUVGS4mtfTPxBn1iLb85ld9uqj68DXR65yk7xqIWc4aubIa_LM1m9IWiptw-8dfWheh548EI4hrbXhj5PyIkR0uFrYcHQzm3rOwBaZlEcXh8dRW0Ah0gzyhohlLmXMJo4poyubaCW4omllbAVD5BhmUwYAnlG5iUWcsixXxmoea2d4pV36lgzqeW3fkRCgkbOQDeaKV8xxlQuRudzGmasKJwoakGHvCHnbCGVIcDUyaFkakP3ONVK32uNYAuNG-n_grJDgV4l-xRvg14B86ht0vT1puge-lu3Su3vabLhmdnh6JAEMszyWMK8C8rEZqv5pKLs9nl2O5HwxlavfKLkNgbsISOKH8l9vhf3TgxJL5dHt_2jzgbw4H5fy68nZlyF5iUbNAcj3ZLBcrOwOIKFltdvO9Xu7Y_Wo |
| 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=Face+Recognition+Using+Dense+SIFT+Feature+Alignment&rft.jtitle=Chinese+Journal+of+Electronics&rft.au=Quan%2C+Zhou&rft.au=Rehman%2C+Shafiq+Ur&rft.au=Yu%2C+Zhou&rft.au=Xin%2C+Wei&rft.date=2016-11-01&rft.issn=1022-4653&rft.eissn=2075-5597&rft.volume=25&rft.issue=6&rft.spage=1034&rft_id=info:doi/10.1049%2Fcje.2016.10.001&rft.externalDocID=oai_DiVA_org_umu_129909 |
| thumbnail_s | http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fimage.cqvip.com%2Fvip1000%2Fqk%2F86774X%2F86774X.jpg |