A Novel Expression Deformation Model for 3D Face Recognition

Chuanjun WANG; Li LI; Xuefeng BAI; Xiamu NIU

doi:10.1587/transinf.E95.D.3113

A Novel Expression Deformation Model for 3D Face Recognition

Chuanjun WANG, Li LI, Xuefeng BAI, Xiamu NIU

Full Text Views

0

Share
Cite this

Summary :

The accuracy of non-rigid 3D face recognition is highly influenced by the capability to model the expression deformations. Given a training set of non-neutral and neutral 3D face scan pairs from the same subject, a set of Fourier series coefficients for each face scan is reconstructed. The residues on each frequency of the Fourier series between the finely aligned pairs contain the expression deformation patterns and PCA is applied to learn these patterns. The proposed expression deformation model is then built by the eigenvectors with top eigenvalues from PCA. Recognition experiments are conducted on a 3D face database that features a rich set of facial expression deformations, and experimental results demonstrate the feasibility and merits of the proposed model.

Publication: IEICE TRANSACTIONS on Information Vol.E95-D No.12 pp.3113-3116

Publication Date: 2012/12/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1587/transinf.E95.D.3113

Type of Manuscript: LETTER

Category: Image Recognition, Computer Vision

Cite this

Copy

Chuanjun WANG, Li LI, Xuefeng BAI, Xiamu NIU, "A Novel Expression Deformation Model for 3D Face Recognition" in IEICE TRANSACTIONS on Information, vol. E95-D, no. 12, pp. 3113-3116, December 2012, doi: 10.1587/transinf.E95.D.3113.
Abstract: The accuracy of non-rigid 3D face recognition is highly influenced by the capability to model the expression deformations. Given a training set of non-neutral and neutral 3D face scan pairs from the same subject, a set of Fourier series coefficients for each face scan is reconstructed. The residues on each frequency of the Fourier series between the finely aligned pairs contain the expression deformation patterns and PCA is applied to learn these patterns. The proposed expression deformation model is then built by the eigenvectors with top eigenvalues from PCA. Recognition experiments are conducted on a 3D face database that features a rich set of facial expression deformations, and experimental results demonstrate the feasibility and merits of the proposed model.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.E95.D.3113/_p

Copy

@ARTICLE{e95-d_12_3113,
author={Chuanjun WANG, Li LI, Xuefeng BAI, Xiamu NIU, },
journal={IEICE TRANSACTIONS on Information},
title={A Novel Expression Deformation Model for 3D Face Recognition},
year={2012},
volume={E95-D},
number={12},
pages={3113-3116},
abstract={The accuracy of non-rigid 3D face recognition is highly influenced by the capability to model the expression deformations. Given a training set of non-neutral and neutral 3D face scan pairs from the same subject, a set of Fourier series coefficients for each face scan is reconstructed. The residues on each frequency of the Fourier series between the finely aligned pairs contain the expression deformation patterns and PCA is applied to learn these patterns. The proposed expression deformation model is then built by the eigenvectors with top eigenvalues from PCA. Recognition experiments are conducted on a 3D face database that features a rich set of facial expression deformations, and experimental results demonstrate the feasibility and merits of the proposed model.},
keywords={},
doi={10.1587/transinf.E95.D.3113},
ISSN={1745-1361},
month={December},}

Copy

TY - JOUR
TI - A Novel Expression Deformation Model for 3D Face Recognition
T2 - IEICE TRANSACTIONS on Information
SP - 3113
EP - 3116
AU - Chuanjun WANG
AU - Li LI
AU - Xuefeng BAI
AU - Xiamu NIU
PY - 2012
DO - 10.1587/transinf.E95.D.3113
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E95-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2012
AB - The accuracy of non-rigid 3D face recognition is highly influenced by the capability to model the expression deformations. Given a training set of non-neutral and neutral 3D face scan pairs from the same subject, a set of Fourier series coefficients for each face scan is reconstructed. The residues on each frequency of the Fourier series between the finely aligned pairs contain the expression deformation patterns and PCA is applied to learn these patterns. The proposed expression deformation model is then built by the eigenvectors with top eigenvalues from PCA. Recognition experiments are conducted on a 3D face database that features a rich set of facial expression deformations, and experimental results demonstrate the feasibility and merits of the proposed model.
ER -