Regional registration for expression resistant 3-D face recognition

Nese Alyuz, B. Gökberk, Lale Akarun

Research output: Contribution to journalArticleAcademicpeer-review

76 Citations (Scopus)

Abstract

Biometric identification from three-dimensional (3-D) facial surface characteristics has become popular, especially in high security applications. In this paper, we propose a fully automatic expression insensitive 3-D face recognition system. Surface deformations due to facial expressions are a major problem in 3-D face recognition. The proposed approach deals with such challenging conditions in several aspects. First, we employ a fast and accurate region-based registration scheme that uses common region models. These common models make it possible to establish correspondence to all the gallery samples in a single registration pass. Second, we utilize curvature-based 3-D shape descriptors. Last, we apply statistical feature extraction methods. Since all the 3-D facial features are regionally registered to the same generic facial component, subspace construction techniques may be employed. We show that linear discriminant analysis significantly boosts the identification accuracy. We demonstrate the recognition ability of our system using the multiexpression Bosphorus and the most commonly used 3-D face database, Face Recognition Grand Challenge (FRGCv2). Our experimental results show that in both databases we obtain comparable performance to the best rank-1 correct classification rates reported in the literature so far: 98.19% for the Bosphorus and 97.51% for the FRGCv2 database. We have also carried out the standard receiver operating characteristics (ROC III) experiment for the FRGCv2 database. At an FAR of 0.1%, the verification performance was 86.09%. This shows that model-based registration is beneficial in identification scenarios where speed-up is important, whereas for verification one-to-one registration can be more beneficial.
Original languageUndefined
Pages (from-to)425-440
Number of pages16
JournalIEEE transactions on information forensics and security
Volume5
Issue number3
DOIs
Publication statusPublished - Sep 2010

Keywords

  • CR-I.4
  • IR-76447
  • face expression
  • METIS-275955
  • Pattern Recognition
  • Face Recognition
  • CR-I.5
  • Computer Vision
  • EWI-19834
  • Biometrics

Cite this

Alyuz, Nese ; Gökberk, B. ; Akarun, Lale. / Regional registration for expression resistant 3-D face recognition. In: IEEE transactions on information forensics and security. 2010 ; Vol. 5, No. 3. pp. 425-440.
@article{2fab04dc1694444caceca0fc7f9e40b5,
title = "Regional registration for expression resistant 3-D face recognition",
abstract = "Biometric identification from three-dimensional (3-D) facial surface characteristics has become popular, especially in high security applications. In this paper, we propose a fully automatic expression insensitive 3-D face recognition system. Surface deformations due to facial expressions are a major problem in 3-D face recognition. The proposed approach deals with such challenging conditions in several aspects. First, we employ a fast and accurate region-based registration scheme that uses common region models. These common models make it possible to establish correspondence to all the gallery samples in a single registration pass. Second, we utilize curvature-based 3-D shape descriptors. Last, we apply statistical feature extraction methods. Since all the 3-D facial features are regionally registered to the same generic facial component, subspace construction techniques may be employed. We show that linear discriminant analysis significantly boosts the identification accuracy. We demonstrate the recognition ability of our system using the multiexpression Bosphorus and the most commonly used 3-D face database, Face Recognition Grand Challenge (FRGCv2). Our experimental results show that in both databases we obtain comparable performance to the best rank-1 correct classification rates reported in the literature so far: 98.19{\%} for the Bosphorus and 97.51{\%} for the FRGCv2 database. We have also carried out the standard receiver operating characteristics (ROC III) experiment for the FRGCv2 database. At an FAR of 0.1{\%}, the verification performance was 86.09{\%}. This shows that model-based registration is beneficial in identification scenarios where speed-up is important, whereas for verification one-to-one registration can be more beneficial.",
keywords = "CR-I.4, IR-76447, face expression, METIS-275955, Pattern Recognition, Face Recognition, CR-I.5, Computer Vision, EWI-19834, Biometrics",
author = "Nese Alyuz and B. G{\"o}kberk and Lale Akarun",
note = "10.1109/TIFS.2010.2054081",
year = "2010",
month = "9",
doi = "10.1109/TIFS.2010.2054081",
language = "Undefined",
volume = "5",
pages = "425--440",
journal = "IEEE transactions on information forensics and security",
issn = "1556-6013",
publisher = "IEEE",
number = "3",

}

Regional registration for expression resistant 3-D face recognition. / Alyuz, Nese; Gökberk, B.; Akarun, Lale.

In: IEEE transactions on information forensics and security, Vol. 5, No. 3, 09.2010, p. 425-440.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Regional registration for expression resistant 3-D face recognition

AU - Alyuz, Nese

AU - Gökberk, B.

AU - Akarun, Lale

N1 - 10.1109/TIFS.2010.2054081

PY - 2010/9

Y1 - 2010/9

N2 - Biometric identification from three-dimensional (3-D) facial surface characteristics has become popular, especially in high security applications. In this paper, we propose a fully automatic expression insensitive 3-D face recognition system. Surface deformations due to facial expressions are a major problem in 3-D face recognition. The proposed approach deals with such challenging conditions in several aspects. First, we employ a fast and accurate region-based registration scheme that uses common region models. These common models make it possible to establish correspondence to all the gallery samples in a single registration pass. Second, we utilize curvature-based 3-D shape descriptors. Last, we apply statistical feature extraction methods. Since all the 3-D facial features are regionally registered to the same generic facial component, subspace construction techniques may be employed. We show that linear discriminant analysis significantly boosts the identification accuracy. We demonstrate the recognition ability of our system using the multiexpression Bosphorus and the most commonly used 3-D face database, Face Recognition Grand Challenge (FRGCv2). Our experimental results show that in both databases we obtain comparable performance to the best rank-1 correct classification rates reported in the literature so far: 98.19% for the Bosphorus and 97.51% for the FRGCv2 database. We have also carried out the standard receiver operating characteristics (ROC III) experiment for the FRGCv2 database. At an FAR of 0.1%, the verification performance was 86.09%. This shows that model-based registration is beneficial in identification scenarios where speed-up is important, whereas for verification one-to-one registration can be more beneficial.

AB - Biometric identification from three-dimensional (3-D) facial surface characteristics has become popular, especially in high security applications. In this paper, we propose a fully automatic expression insensitive 3-D face recognition system. Surface deformations due to facial expressions are a major problem in 3-D face recognition. The proposed approach deals with such challenging conditions in several aspects. First, we employ a fast and accurate region-based registration scheme that uses common region models. These common models make it possible to establish correspondence to all the gallery samples in a single registration pass. Second, we utilize curvature-based 3-D shape descriptors. Last, we apply statistical feature extraction methods. Since all the 3-D facial features are regionally registered to the same generic facial component, subspace construction techniques may be employed. We show that linear discriminant analysis significantly boosts the identification accuracy. We demonstrate the recognition ability of our system using the multiexpression Bosphorus and the most commonly used 3-D face database, Face Recognition Grand Challenge (FRGCv2). Our experimental results show that in both databases we obtain comparable performance to the best rank-1 correct classification rates reported in the literature so far: 98.19% for the Bosphorus and 97.51% for the FRGCv2 database. We have also carried out the standard receiver operating characteristics (ROC III) experiment for the FRGCv2 database. At an FAR of 0.1%, the verification performance was 86.09%. This shows that model-based registration is beneficial in identification scenarios where speed-up is important, whereas for verification one-to-one registration can be more beneficial.

KW - CR-I.4

KW - IR-76447

KW - face expression

KW - METIS-275955

KW - Pattern Recognition

KW - Face Recognition

KW - CR-I.5

KW - Computer Vision

KW - EWI-19834

KW - Biometrics

U2 - 10.1109/TIFS.2010.2054081

DO - 10.1109/TIFS.2010.2054081

M3 - Article

VL - 5

SP - 425

EP - 440

JO - IEEE transactions on information forensics and security

JF - IEEE transactions on information forensics and security

SN - 1556-6013

IS - 3

ER -