Synthesizing realistic expressions in 3D face data sets

Página do item simplificado
dc.contributor.authorMinoi J.-L.
dc.contributor.authorAmin S.H.
dc.contributor.authorCarlos E. Thomaz
dc.contributor.authorGillies D.F.
dc.contributor.authorOrcidhttps://orcid.org/0000-0001-5566-1963
dc.date.accessioned2022-01-12T22:04:51Z
dc.date.available2022-01-12T22:04:51Z
dc.date.issued2008-09-29
dc.description.abstractThis paper presents a robust method for synthesizing realistic expressions on 3D human face surfaces captured from frontal photographs with neutral expression. The generated facial expressions could be used to improve the performance of existing face identification systems, or to enhance human recognition. Firstly, the 3D face surface map is recovered using an analysis-by-synthesis approach based on a statistical model for encoding face shape information. Then a statistical discriminant model approach is employed to synthesize new facial expressions. The synthetic expression data is created by dividing a training set into two classes, for example smiling and frowning, and then finding the most discriminant direction between the classes. The expressions are applied to a human face by moving the surface points along this most discriminant direction. The resulting 3D models can be rendered under a variety of pose and illumination conditions. The key advantage of the proposed method is that expressions of varying degrees can be easily generated without having detailed changes in the 3D expression database. Besides altering human facial expressions, SDM could also be used to generate facial aging to aid the process of identifying missing children or adults after a time lapse. Moreover, synthetic biometric data contains 3D topology information, which is useful in analysing geometric facial shape changes over different facial expressions. © 2008 IEEE.
dc.identifier.citationMONOI, J.-L.; AMIN, S. H.; THOMAZ, C. E.; GILIES, D. F. Synthesizing realistic expressions in 3D face data sets. BTAS 2008 - IEEE 2nd International Conference on Biometrics: Theory, Applications and Systems, Sept. 2008.
dc.identifier.doi10.1109/BTAS.2008.4699374
dc.identifier.urihttps://repositorio.fei.edu.br/handle/FEI/4299
dc.relation.ispartofBTAS 2008 - IEEE 2nd International Conference on Biometrics: Theory, Applications and Systems
dc.rightsAcesso Restrito
dc.titleSynthesizing realistic expressions in 3D face data sets
dc.typeArtigo de evento
fei.scopus.citations8
fei.scopus.eid2-s2.0-67549091885
fei.scopus.subject3D faces
fei.scopus.subject3D Human Faces
fei.scopus.subject3D models
fei.scopus.subject3D topology
fei.scopus.subjectAnalysis-by-synthesis approach
fei.scopus.subjectBiometric data
fei.scopus.subjectDiscriminant models
fei.scopus.subjectExpression data
fei.scopus.subjectFace identification
fei.scopus.subjectFace shapes
fei.scopus.subjectFacial aging
fei.scopus.subjectFacial Expressions
fei.scopus.subjectFacial shape
fei.scopus.subjectHuman faces
fei.scopus.subjectHuman facial expressions
fei.scopus.subjectHuman recognition
fei.scopus.subjectIllumination conditions
fei.scopus.subjectRobust methods
fei.scopus.subjectStatistical models
fei.scopus.subjectSurface points
fei.scopus.subjectTraining sets
fei.scopus.updated2024-07-01
fei.scopus.urlhttps://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=67549091885&origin=inward
Arquivos
Coleções
Artigos