A Component-Based Framework for Generalized Face Alignment

This paper presents a component-based deformable model for generalized face alignment, in which a novel bistage statistical model is proposed to account for both local and global shape characteristics. Instead of using statistical analysis on the entire shape, we build separate Gaussian models for s...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on systems, man and cybernetics. Part B, Cybernetics Ročník 41; číslo 1; s. 287 - 298
Hlavní autoři:	Yuchi Huang, Qingshan Liu, Metaxas, D N
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	United States IEEE 01.02.2011
Témata:	Active shape model Algorithms Alignment Bayes Theorem Biometric Identification - methods Bistage statistical model component detection Cybernetics Deformable models Deformation Face - anatomy & histology face alignment Face detection Facial animation Gaussian Gaussian process latent variable model (GPLVM) Gaussian processes Humans Image Processing, Computer-Assisted - methods Image reconstruction Markov Chains Markov network Markov random fields Mathematical models Mouth Normal Distribution Principal Component Analysis Searching Shape control Statistical analysis Video Recording - methods
ISSN:	1083-4419, 1941-0492, 1941-0492
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	This paper presents a component-based deformable model for generalized face alignment, in which a novel bistage statistical model is proposed to account for both local and global shape characteristics. Instead of using statistical analysis on the entire shape, we build separate Gaussian models for shape components to preserve more detailed local shape deformations. In each model of components, a Markov network is integrated to provide simple geometry constraints for our search strategy. In order to make a better description of the nonlinear interrelationships over shape components, the Gaussian process latent variable model is adopted to obtain enough control of shape variations. In addition, we adopt an illumination-robust feature to lead the local fitting of every shape point when light conditions change dramatically. To further boost the accuracy and efficiency of our component-based algorithm, an efficient subwindow search technique is adopted to detect components and to provide better initializations for shape components. Based on this approach, our system can generate accurate shape alignment results not only for images with exaggerated expressions and slight shading variation but also for images with occlusion and heavy shadows, which are rarely reported in previous work.
AbstractList	This paper presents a component-based deformable model for generalized face alignment, in which a novel bistage statistical model is proposed to account for both local and global shape characteristics. Instead of using statistical analysis on the entire shape, we build separate Gaussian models for shape components to preserve more detailed local shape deformations. In each model of components, a Markov network is integrated to provide simple geometry constraints for our search strategy. In order to make a better description of the nonlinear interrelationships over shape components, the Gaussian process latent variable model is adopted to obtain enough control of shape variations. In addition, we adopt an illumination-robust feature to lead the local fitting of every shape point when light conditions change dramatically. To further boost the accuracy and efficiency of our component-based algorithm, an efficient subwindow search technique is adopted to detect components and to provide better initializations for shape components. Based on this approach, our system can generate accurate shape alignment results not only for images with exaggerated expressions and slight shading variation but also for images with occlusion and heavy shadows, which are rarely reported in previous work. This paper presents a component-based deformable model for generalized face alignment, in which a novel bistage statistical model is proposed to account for both local and global shape characteristics. Instead of using statistical analysis on the entire shape, we build separate Gaussian models for shape components to preserve more detailed local shape deformations. In each model of components, a Markov network is integrated to provide simple geometry constraints for our search strategy. In order to make a better description of the nonlinear interrelationships over shape components, the Gaussian process latent variable model is adopted to obtain enough control of shape variations. In addition, we adopt an illumination-robust feature to lead the local fitting of every shape point when light conditions change dramatically. To further boost the accuracy and efficiency of our component-based algorithm, an efficient subwindow search technique is adopted to detect components and to provide better initializations for shape components. Based on this approach, our system can generate accurate shape alignment results not only for images with exaggerated expressions and slight shading variation but also for images with occlusion and heavy shadows, which are rarely reported in previous work.This paper presents a component-based deformable model for generalized face alignment, in which a novel bistage statistical model is proposed to account for both local and global shape characteristics. Instead of using statistical analysis on the entire shape, we build separate Gaussian models for shape components to preserve more detailed local shape deformations. In each model of components, a Markov network is integrated to provide simple geometry constraints for our search strategy. In order to make a better description of the nonlinear interrelationships over shape components, the Gaussian process latent variable model is adopted to obtain enough control of shape variations. In addition, we adopt an illumination-robust feature to lead the local fitting of every shape point when light conditions change dramatically. To further boost the accuracy and efficiency of our component-based algorithm, an efficient subwindow search technique is adopted to detect components and to provide better initializations for shape components. Based on this approach, our system can generate accurate shape alignment results not only for images with exaggerated expressions and slight shading variation but also for images with occlusion and heavy shadows, which are rarely reported in previous work.
Author	Metaxas, D N Qingshan Liu Yuchi Huang
Author_xml	– sequence: 1 surname: Yuchi Huang fullname: Yuchi Huang email: yuchuang@cs.rutgers.edu organization: Dept. of Comput. Sci., Rutgers Univ., New Brunswick, NJ, USA – sequence: 2 surname: Qingshan Liu fullname: Qingshan Liu email: qsliu@cs.rutgers.edu organization: Dept. of Comput. Sci., Rutgers Univ., New Brunswick, NJ, USA – sequence: 3 givenname: D N surname: Metaxas fullname: Metaxas, D N email: dnm@cs.rutgers.edu organization: Dept. of Comput. Sci., Rutgers Univ., New Brunswick, NJ, USA
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/20656659$$D View this record in MEDLINE/PubMed
BookMark	eNp9kbtOwzAUhi0EAlp4AZBQNlgCvjY2Wxtxk0AMwGw59jEK5FLsVAienoS2DAydjo_8ff9w_hHabtoGEDoi-JwQrC6enx7y2TnF_U6xoJTjLbRPFCcp5opu928sWco5UXtoFOMbxlhhle2iPYonYjIRah9dTpO8red9cNOlMxPBJdfB1PDZhvfEtyG5gQaCqcrv4cdYSKZV-drUPX6AdrypIhyu5hi9XF8957fp_ePNXT69Ty2TtEst54VlBHvrReY9gAInLDHKS2alcYSoQiqjCPPWUWkz7qRzxrqCU8uEZWN0usydh_ZjAbHTdRktVJVpoF1ELTlmgnEie_JsI0kwIwyTLBvQkxW6KGpweh7K2oQvvb5MD8glYEMbYwCvbdmZrmybLpiy6rP0UIL-LUEPJehVCb1K_6nr9I3S8VIqAeBPEIJIziT7AXQukYw
CODEN	ITSCFI
CitedBy_id	crossref_primary_10_1109_TIP_2015_2502485 crossref_primary_10_3233_IFS_141513 crossref_primary_10_1016_j_neunet_2014_06_005 crossref_primary_10_1016_j_neunet_2019_12_009 crossref_primary_10_1016_j_cviu_2016_03_009 crossref_primary_10_1109_TCYB_2018_2863790 crossref_primary_10_1007_s13042_012_0074_z crossref_primary_10_1109_TAFFC_2014_2347960 crossref_primary_10_1007_s13042_021_01424_3 crossref_primary_10_1016_j_knosys_2015_04_003
Cites_doi	10.1109/TSMCB.2005.846655 10.1109/TSMCB.2008.2009566 10.1109/TSMCB.2005.862728 10.1109/CVPR.2008.4587586 10.1093/ietisy/e89-d.7.2117 10.1109/34.927464 10.1006/cviu.1995.1004 10.1109/ICIP.1997.647401 10.1109/AFGR.2004.1301513 10.1023/B:VISI.0000013087.49260.fb 10.1109/83.557356 10.5244/C.21.79 10.1109/TSMCB.2004.825931 10.1109/ICCV.2003.1238466 10.1109/34.120328 10.7551/mitpress/4175.001.0001 10.1016/S0262-8856(98)00175-9 10.5244/C.13.48 10.1109/ICCV.2007.4409017 10.1023/A:1026501619075 10.1007/978-3-540-88688-4_6
ContentType	Journal Article
DBID	97E RIA RIE AAYXX CITATION CGR CUY CVF ECM EIF NPM 7SC 7SP 7TB 8FD F28 FR3 JQ2 L7M L~C L~D 7X8
DOI	10.1109/TSMCB.2010.2052240
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE/IET Electronic Library (IEL) (UW System Shared) CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed Computer and Information Systems Abstracts Electronics & Communications Abstracts Mechanical & Transportation Engineering Abstracts Technology Research Database ANTE: Abstracts in New Technology & Engineering Engineering Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional MEDLINE - Academic
DatabaseTitle	CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) 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 ANTE: Abstracts in New Technology & Engineering Computer and Information Systems Abstracts Professional MEDLINE - Academic
DatabaseTitleList	Technology Research Database MEDLINE - Academic MEDLINE
Database_xml	– sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Sciences (General)
EISSN	1941-0492
EndPage	298
ExternalDocumentID	20656659 10_1109_TSMCB_2010_2052240 5518438
Genre	orig-research Journal Article
GroupedDBID	--- -~X 0R~ 29I 4.4 53G 5VS 6IK 85S 97E AAJGR AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFS AETIX AGQYO AGSQL AHBIQ AI. AIBXA ALLEH ALMA_UNASSIGNED_HOLDINGS BEFXN BFFAM BGNUA BKEBE BPEOZ EBS EJD F5P HZ~ IFIPE IFJZH IPLJI JAVBF LAI M43 O9- OCL PZZ RIA RIE RNS RXW TAE TAF VH1 VJK AAYXX CITATION CGR CUY CVF ECM EIF NPM 7SC 7SP 7TB 8FD F28 FR3 JQ2 L7M L~C L~D 7X8
ID	FETCH-LOGICAL-c382t-c44bc310fcf57ffee9ed5c1a9f83c8ad119b89a913fcd28c74d8ddacdb42c35c3
IEDL.DBID	RIE
ISICitedReferencesCount	17
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000286388300023&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1083-4419 1941-0492
IngestDate	Fri Jul 11 14:55:05 EDT 2025 Thu Jul 10 18:46:56 EDT 2025 Mon Jul 21 05:52:53 EDT 2025 Tue Nov 18 21:45:00 EST 2025 Sat Nov 29 08:18:43 EST 2025 Tue Aug 26 17:18:01 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	1
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c382t-c44bc310fcf57ffee9ed5c1a9f83c8ad119b89a913fcd28c74d8ddacdb42c35c3
Notes	ObjectType-Article-2 SourceType-Scholarly Journals-1 ObjectType-Feature-1 content type line 23 ObjectType-Article-1 ObjectType-Feature-2
PMID	20656659
PQID	1031301778
PQPubID	23500
PageCount	12
ParticipantIDs	proquest_miscellaneous_1031301778 proquest_miscellaneous_840353418 crossref_citationtrail_10_1109_TSMCB_2010_2052240 pubmed_primary_20656659 crossref_primary_10_1109_TSMCB_2010_2052240 ieee_primary_5518438
PublicationCentury	2000
PublicationDate	2011-Feb. 2011-02-00 2011-Feb 20110201
PublicationDateYYYYMMDD	2011-02-01
PublicationDate_xml	– month: 02 year: 2011 text: 2011-Feb.
PublicationDecade	2010
PublicationPlace	United States
PublicationPlace_xml	– name: United States
PublicationTitle	IEEE transactions on systems, man and cybernetics. Part B, Cybernetics
PublicationTitleAbbrev	TSMCB
PublicationTitleAlternate	IEEE Trans Syst Man Cybern B Cybern
PublicationYear	2011
Publisher	IEEE
Publisher_xml	– name: IEEE
References	lawrence (ref14) 2005; 6 zhou (ref31) 2003 ref12 ref15 ref30 ref11 ref10 ref2 ref1 ref18 huang (ref9) 2004 liu (ref20) 2001 lawrence (ref13) 2004 tu (ref26) 2004 scholkopf (ref25) 2001 liang (ref16) 2006 ref24 coughlan (ref3) 2002 ref23 ref22 martinez (ref21) 1998 ref28 ref27 ref29 ref8 ref7 ref4 liang (ref17) 2006 ref6 ref5 liu (ref19) 2002
References_xml	– ident: ref28 doi: 10.1109/TSMCB.2005.846655 – volume: 6 start-page: 1783 year: 2005 ident: ref14 article-title: probabilistic non-linear principal component analysis with gaussian process latent variable models publication-title: J Mach Learn Res – ident: ref5 doi: 10.1109/TSMCB.2008.2009566 – ident: ref22 doi: 10.1109/TSMCB.2005.862728 – ident: ref12 doi: 10.1109/CVPR.2008.4587586 – start-page: 329 year: 2004 ident: ref13 article-title: gaussian process latent variable models for visualization of high dimensional data publication-title: Proc Adv Neural Inf Process Syst – start-page: 687 year: 2002 ident: ref19 article-title: hierarchical shape modeling for automatic face localization publication-title: Proc Eur Conf Comput Vis – ident: ref15 doi: 10.1093/ietisy/e89-d.7.2117 – ident: ref8 doi: 10.1109/34.927464 – ident: ref1 doi: 10.1006/cviu.1995.1004 – ident: ref29 doi: 10.1109/ICIP.1997.647401 – start-page: 85 year: 2004 ident: ref9 article-title: face alignment under variable illumination publication-title: Proc Int Conf Automat Face Gesture Recog doi: 10.1109/AFGR.2004.1301513 – ident: ref27 doi: 10.1023/B:VISI.0000013087.49260.fb – year: 1998 ident: ref21 publication-title: The AR face database – ident: ref11 doi: 10.1109/83.557356 – ident: ref4 doi: 10.5244/C.21.79 – ident: ref23 doi: 10.1109/TSMCB.2004.825931 – start-page: 109 year: 2003 ident: ref31 article-title: bayesian tangent shape model: estimating shape and pose parameters via bayesian inference publication-title: Proc IEEE Conf Comput Vis Pattern Recognit – ident: ref30 doi: 10.1109/ICCV.2003.1238466 – ident: ref6 doi: 10.1109/34.120328 – start-page: 719 year: 2004 ident: ref26 article-title: face localization via hierarchical condensation with fisher boosting feature selection publication-title: Proc IEEE Conf Comput Vis Pattern Recognit – start-page: 333 year: 2006 ident: ref16 article-title: an integrated model for accurate shape alignment publication-title: Proc Eur Conf Comput Vis – start-page: 1313 year: 2006 ident: ref17 article-title: accurate face alignment using shape constrained markov network publication-title: Proc IEEE Conf Comput Vis Pattern Recognit – year: 2001 ident: ref25 publication-title: Learning With Kernels Support Vector Machines Regularization Optimization and Beyond doi: 10.7551/mitpress/4175.001.0001 – start-page: 281 year: 2001 ident: ref20 article-title: learning inhomogeneous gibbs model of faces by minimax entropy publication-title: Proc IEEE Int Conf Comput Vis – ident: ref2 doi: 10.1016/S0262-8856(98)00175-9 – start-page: 453 year: 2002 ident: ref3 article-title: finding deformable shapes using loopy belief propagation publication-title: Proc 7th Eur Conf Comput Vis – ident: ref24 doi: 10.5244/C.13.48 – ident: ref10 doi: 10.1109/ICCV.2007.4409017 – ident: ref7 doi: 10.1023/A:1026501619075 – ident: ref18 doi: 10.1007/978-3-540-88688-4_6
SSID	ssj0009097
Score	1.9887224
Snippet	This paper presents a component-based deformable model for generalized face alignment, in which a novel bistage statistical model is proposed to account for...
SourceID	proquest pubmed crossref ieee
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	287
SubjectTerms	Active shape model Algorithms Alignment Bayes Theorem Biometric Identification - methods Bistage statistical model component detection Cybernetics Deformable models Deformation Face - anatomy & histology face alignment Face detection Facial animation Gaussian Gaussian process latent variable model (GPLVM) Gaussian processes Humans Image Processing, Computer-Assisted - methods Image reconstruction Markov Chains Markov network Markov random fields Mathematical models Mouth Normal Distribution Principal Component Analysis Searching Shape control Statistical analysis Video Recording - methods
Title	A Component-Based Framework for Generalized Face Alignment
URI	https://ieeexplore.ieee.org/document/5518438 https://www.ncbi.nlm.nih.gov/pubmed/20656659 https://www.proquest.com/docview/1031301778 https://www.proquest.com/docview/840353418
Volume	41
WOSCitedRecordID	wos000286388300023&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: 1941-0492 dateEnd: 20121231 omitProxy: false ssIdentifier: ssj0009097 issn: 1083-4419 databaseCode: RIE dateStart: 19960101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT8MwDLYAcYADj_EajylIHEBQaJqWJNwGYuICQmJIu1Wtk6JJaENs48Cvx0nbsQMgoV4q1W2j2I6_JM5ngCNrRWQEp5mq5iqIjfELTZrcPbuUNqYL0RebkA8PqtfTj3NwNj0LY631yWf23N36vXwzxIlbKrtw7GGxUPMwL-VleVbrm2A3LAupEKQIKMTr-oBMqC-6T_c312UWVxQmLoY5CuDQIRlHUToTj3yBld-xpo85ndX_tXYNVipsydqlMazDnB00YHmGcbAB65Uvj9hxRTh9sgFXbeaGheGAvhdcU1gzrFPnbDECtawS7X-6Jxla1n7tv_g0gk147tx2b-6CqqZCgEJF4wDjOEeCdAUWiSwKa7U1CfJMF0qgygznOlc601wUaCKFMjbKmAxNHkcoEhRbsDCg9uwAI08XsTJRoQmSYJTnaHOZKUxCVBFH3gRe92yKFeG4q3vxmvqJR6hTr5jUKSatFNOE0-k7byXdxp_SG67bp5JVjzfhsFZgSs7idkCygR1ORqmraUEjmpQkw36RoRmvSCi2k8h2qfzp92ub2f35v3uwVK44u2SXfVgYv0_sASzix7g_em-R0fZUyxvtFzl65Kg
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT9wwEB5RQCocCsujbHkZiUMRpBvHCbG5LYgVCFghdZG4RcnYqVZCu9U-euivZ-w4yx5KJZRLJE8cy-PxfLbH3wAcGyMiLTitVBWXQay122hSZO75eWpiehBdsom025XPz-pxAc5md2GMMS74zPywr-4sXw9xarfKWpY9LBbyEyzZzFn-ttYbxW5YpVIhUBFQsaqvyISq1fv5cHVZxXFFYWK9mCUBDi2WsSSlcx7JpVh5H206r9NZ-1h71-GLR5esXQ2HBiyYwQasznEObkDDW_OYffeU0yebcNFmdmIYDqi-4JIcm2adOmqLEaxlXrT_15bkaFj7pf_LBRJswVPnund1E_isCgEKGU0CjOMCCdSVWCZpWRqjjE6Q56qUAmWuOVeFVLniokQdSUxjLbXOURdxhCJBsQ2LA2rPDjCydRFLHZWKQAlGRYGmSHOJSYgy4sibwOuezdBTjtvMFy-ZW3qEKnOKyaxiMq-YJpzOvvldEW78V3rTdvtM0vd4E45qBWZkLvYMJB-Y4XSc2awWNKelKcmwd2RozSsS8u4k8rVS_qz-esx8-_d_D-HzTe_hPru_7d7twkq1_2xDX_ZgcTKamn1Yxj-T_nh04IbuK-fv5wk
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=A+Component-Based+Framework+for+Generalized+Face+Alignment&rft.jtitle=IEEE+transactions+on+systems%2C+man+and+cybernetics.+Part+B%2C+Cybernetics&rft.au=Yuchi+Huang&rft.au=Qingshan+Liu&rft.au=Metaxas%2C+D+N&rft.date=2011-02-01&rft.pub=IEEE&rft.issn=1083-4419&rft.volume=41&rft.issue=1&rft.spage=287&rft.epage=298&rft_id=info:doi/10.1109%2FTSMCB.2010.2052240&rft_id=info%3Apmid%2F20656659&rft.externalDocID=5518438
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1083-4419&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1083-4419&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1083-4419&client=summon