Expression-invariant Non-rigid 3D Face Recognition: A Robust Approach to Expression-aware Morphing

F.R.M. Al-Osaimi; Mohammed Bennamoun; Ajmal Mian

Expression-invariant Non-rigid 3D Face Recognition: A Robust Approach to Expression-aware Morphing

F.R.M. Al-Osaimi, Mohammed Bennamoun, Ajmal Mian

Research output: Chapter in Book/Conference paper › Conference paper

Abstract

An automatic approach to the recognition of 3D face under any facial expression is presented. It has the capacity to differentiate between expression deformations, those which are caused by expressions, and interpersonal disparities that are essential for recognition. When two facial scans are matched the expression deformations are morphed out before similarity measure calculation while the interpersonal disparities are retained. A combination of PCA and ICP is used in our system. The PCA subspace is built in such a way it models the facial expressions while it does not model the human face. The approach was applied on the FRGC v2.0 dataset and superior recognition performance was achieved. The verification rates at 0.001FAR were 98.35% and 97.73% for scans under neutral and non-neutral expressions, respectively.

Original language	English
Title of host publication	Proceedings of Fourth International Symposium on 3D Data Processing, Visualization and Transmission
Editors	Stephan Gumhold, Jana Kosecka, Oliver Staadt
Place of Publication	Atlanta, Georgia, U.S.A.
Publisher	Georgia Institute of Technology
Pages	19-26
Volume	1
Edition	Atlanta, Georgia, USA
Publication status	Published - Jun 2008
Event	Expression-invariant Non-rigid 3D Face Recognition: A Robust Approach to Expression-aware Morphing - Atlanta, Georgia, USA Duration: 1 Jan 2008 → …

Conference

Conference	Expression-invariant Non-rigid 3D Face Recognition: A Robust Approach to Expression-aware Morphing
Period	1/01/08 → …

Access to Document

http://www.cc.gatech.edu/conferences/3DPVT08/Program/Papers/paper205.pdf

Fingerprint Dive into the research topics of 'Expression-invariant Non-rigid 3D Face Recognition: A Robust Approach to Expression-aware Morphing'. Together they form a unique fingerprint.

1 Finished

DP0664228 - Unified Representations of Multimodal Biometrics for Robust Authentication and Identification
Bennamoun, M. & Owens, R.
ARC Discovery Projects
1/01/06 → 31/12/08
Project: Research

Cite this

Al-Osaimi, F. R. M., Bennamoun, M., & Mian, A. (2008). Expression-invariant Non-rigid 3D Face Recognition: A Robust Approach to Expression-aware Morphing. In S. Gumhold, J. Kosecka, & O. Staadt (Eds.), Proceedings of Fourth International Symposium on 3D Data Processing, Visualization and Transmission (Atlanta, Georgia, USA ed., Vol. 1, pp. 19-26). Georgia Institute of Technology. http://www.cc.gatech.edu/conferences/3DPVT08/Program/Papers/paper205.pdf

Al-Osaimi, F.R.M. ; Bennamoun, Mohammed ; Mian, Ajmal. / Expression-invariant Non-rigid 3D Face Recognition: A Robust Approach to Expression-aware Morphing. Proceedings of Fourth International Symposium on 3D Data Processing, Visualization and Transmission. editor / Stephan Gumhold ; Jana Kosecka ; Oliver Staadt. Vol. 1 Atlanta, Georgia, USA. ed. Atlanta, Georgia, U.S.A. : Georgia Institute of Technology, 2008. pp. 19-26

@inproceedings{c26eff1f3dba44498dcb96702ef03dc7,

title = "Expression-invariant Non-rigid 3D Face Recognition: A Robust Approach to Expression-aware Morphing",

abstract = "An automatic approach to the recognition of 3D face under any facial expression is presented. It has the capacity to differentiate between expression deformations, those which are caused by expressions, and interpersonal disparities that are essential for recognition. When two facial scans are matched the expression deformations are morphed out before similarity measure calculation while the interpersonal disparities are retained. A combination of PCA and ICP is used in our system. The PCA subspace is built in such a way it models the facial expressions while it does not model the human face. The approach was applied on the FRGC v2.0 dataset and superior recognition performance was achieved. The verification rates at 0.001FAR were 98.35% and 97.73% for scans under neutral and non-neutral expressions, respectively.",

author = "F.R.M. Al-Osaimi and Mohammed Bennamoun and Ajmal Mian",

year = "2008",

month = jun,

language = "English",

volume = "1",

pages = "19--26",

editor = "Stephan Gumhold and Jana Kosecka and Oliver Staadt",

booktitle = "Proceedings of Fourth International Symposium on 3D Data Processing, Visualization and Transmission",

publisher = "Georgia Institute of Technology",

edition = "Atlanta, Georgia, USA",

note = "Expression-invariant Non-rigid 3D Face Recognition: A Robust Approach to Expression-aware Morphing ; Conference date: 01-01-2008",

}

Al-Osaimi, FRM, Bennamoun, M & Mian, A 2008, Expression-invariant Non-rigid 3D Face Recognition: A Robust Approach to Expression-aware Morphing. in S Gumhold, J Kosecka & O Staadt (eds), Proceedings of Fourth International Symposium on 3D Data Processing, Visualization and Transmission. Atlanta, Georgia, USA edn, vol. 1, Georgia Institute of Technology, Atlanta, Georgia, U.S.A., pp. 19-26, Expression-invariant Non-rigid 3D Face Recognition: A Robust Approach to Expression-aware Morphing, 1/01/08. <http://www.cc.gatech.edu/conferences/3DPVT08/Program/Papers/paper205.pdf>

Expression-invariant Non-rigid 3D Face Recognition: A Robust Approach to Expression-aware Morphing. / Al-Osaimi, F.R.M.; Bennamoun, Mohammed ; Mian, Ajmal.

Proceedings of Fourth International Symposium on 3D Data Processing, Visualization and Transmission. ed. / Stephan Gumhold; Jana Kosecka; Oliver Staadt. Vol. 1 Atlanta, Georgia, USA. ed. Atlanta, Georgia, U.S.A. : Georgia Institute of Technology, 2008. p. 19-26.

Research output: Chapter in Book/Conference paper › Conference paper

TY - GEN

T1 - Expression-invariant Non-rigid 3D Face Recognition: A Robust Approach to Expression-aware Morphing

AU - Al-Osaimi, F.R.M.

AU - Bennamoun, Mohammed

AU - Mian, Ajmal

PY - 2008/6

Y1 - 2008/6

N2 - An automatic approach to the recognition of 3D face under any facial expression is presented. It has the capacity to differentiate between expression deformations, those which are caused by expressions, and interpersonal disparities that are essential for recognition. When two facial scans are matched the expression deformations are morphed out before similarity measure calculation while the interpersonal disparities are retained. A combination of PCA and ICP is used in our system. The PCA subspace is built in such a way it models the facial expressions while it does not model the human face. The approach was applied on the FRGC v2.0 dataset and superior recognition performance was achieved. The verification rates at 0.001FAR were 98.35% and 97.73% for scans under neutral and non-neutral expressions, respectively.

AB - An automatic approach to the recognition of 3D face under any facial expression is presented. It has the capacity to differentiate between expression deformations, those which are caused by expressions, and interpersonal disparities that are essential for recognition. When two facial scans are matched the expression deformations are morphed out before similarity measure calculation while the interpersonal disparities are retained. A combination of PCA and ICP is used in our system. The PCA subspace is built in such a way it models the facial expressions while it does not model the human face. The approach was applied on the FRGC v2.0 dataset and superior recognition performance was achieved. The verification rates at 0.001FAR were 98.35% and 97.73% for scans under neutral and non-neutral expressions, respectively.

M3 - Conference paper

VL - 1

SP - 19

EP - 26

BT - Proceedings of Fourth International Symposium on 3D Data Processing, Visualization and Transmission

A2 - Gumhold, Stephan

A2 - Kosecka, Jana

A2 - Staadt, Oliver

PB - Georgia Institute of Technology

CY - Atlanta, Georgia, U.S.A.

T2 - Expression-invariant Non-rigid 3D Face Recognition: A Robust Approach to Expression-aware Morphing

Y2 - 1 January 2008

ER -

Al-Osaimi FRM, Bennamoun M , Mian A. Expression-invariant Non-rigid 3D Face Recognition: A Robust Approach to Expression-aware Morphing. In Gumhold S, Kosecka J, Staadt O, editors, Proceedings of Fourth International Symposium on 3D Data Processing, Visualization and Transmission. Atlanta, Georgia, USA ed. Vol. 1. Atlanta, Georgia, U.S.A.: Georgia Institute of Technology. 2008. p. 19-26

Expression-invariant Non-rigid 3D Face Recognition: A Robust Approach to Expression-aware Morphing

Abstract

Conference

Access to Document

DP0664228 - Unified Representations of Multimodal Biometrics for Robust Authentication and Identification

Cite this