Synthesizing 3D face shapes using tensor-based multivariate statistical discriminant methods
N/D
Tipo de produção
Artigo de evento
Data de publicação
2011-11-14
Texto completo (DOI)
Periódico
Communications in Computer and Information Science
Editor
Texto completo na Scopus
Citações na Scopus
0
Autores
MONOI, J.-L.
Plinio Thomaz Aquino Junior
GILLIES, D. F.
Orientadores
Resumo
We have implemented methods to reconstruct and model 3D face shapes and to synthesize facial expressions from a set of real human 3D face surface maps. The method employed tensor-based statistical shape modelling and statistical discriminant modelling methods. In the statistical shape modelling approach, new face shapes are created by moving the surface points along the appropriate expressive direction in the training set space. In the statistical discriminant model, new face shapes, such as facial expressions, can be synthesized by moving the surface points along the most discriminant direction found from the classes of expressions in the training set. The advantage of the tensor-based statistical discriminant analysis method is that face shapes of varying degrees can be generated from a small number of examples available in the 3D face shape datasets. The results of the reconstructions and synthesis of three-dimensional faces are illustrated in the paper. © 2011 Springer-Verlag.
Citação
MONOI, J.-L.; AQUINO JUNIOR, O. T.; GILLIES, D. F. Synthesizing 3D face shapes using tensor-based multivariate statistical discriminant methods. Communications in Computer and Information Science, v. 254 CCIS, n. PART 4, p. 413-426, Nov. 2011.
Palavras-chave
Keywords
3D face shapes; multivariate statistical discriminant analysis; reconstructing and synthesizing facial expression; tensor model
Assuntos Scopus
3D faces; Data sets; Discriminant models; Face shapes; Facial Expressions; Modelling method; Statistical shape modelling; Surface points; tensor model; Training sets