A Low Dimensionality Expression Robust Rejector for 3D Face Recognition

Jiangning Gao, Mehryar Emambakhsh, A N Evans

Research output: Contribution to conferencePaper

4 Citations (Scopus)

Abstract

In the past decade, expression variations have been one of the most challenging sources of variability in 3D face recognition, especially for scenarios where there are a large number of face samples to discriminate between. In this paper, an expression robust rejector is proposed that first robustly locates landmarks on the relatively stable structure of the nose and its environs, termed the cheek/nose region. Then, by defining curves connecting the landmarks, a small set of features (4 curves with only 15 points each) on the cheek/nose surface are selected using the Bosphorus database. The resulting rejector, which can quickly eliminate a large number of candidates at an early stage, is further evaluated on the FRGC database for both the identification and verification scenarios. The classification performance using only 60 points from 4 curves shows the effectiveness of this efficient expression robust rejector.
Original languageEnglish
Pages506
Number of pages511
DOIs
Publication statusPublished - 2014
Event IEEE International Conference on Pattern Recognition (ICPR) 2014 - Stockholm, Sweden
Duration: 24 Aug 201428 Aug 2014

Conference

Conference IEEE International Conference on Pattern Recognition (ICPR) 2014
CountrySweden
CityStockholm
Period24/08/1428/08/14

Fingerprint

Face recognition

Keywords

  • biometrics
  • face recognition
  • pattern rejection
  • feature selection

Cite this

Gao, J., Emambakhsh, M., & Evans, A. N. (2014). A Low Dimensionality Expression Robust Rejector for 3D Face Recognition. 506. Paper presented at IEEE International Conference on Pattern Recognition (ICPR) 2014, Stockholm, Sweden. https://doi.org/10.1109/ICPR.2014.96

A Low Dimensionality Expression Robust Rejector for 3D Face Recognition. / Gao, Jiangning; Emambakhsh, Mehryar; Evans, A N.

2014. 506 Paper presented at IEEE International Conference on Pattern Recognition (ICPR) 2014, Stockholm, Sweden.

Research output: Contribution to conferencePaper

Gao, J, Emambakhsh, M & Evans, AN 2014, 'A Low Dimensionality Expression Robust Rejector for 3D Face Recognition' Paper presented at IEEE International Conference on Pattern Recognition (ICPR) 2014, Stockholm, Sweden, 24/08/14 - 28/08/14, pp. 506. https://doi.org/10.1109/ICPR.2014.96
Gao J, Emambakhsh M, Evans AN. A Low Dimensionality Expression Robust Rejector for 3D Face Recognition. 2014. Paper presented at IEEE International Conference on Pattern Recognition (ICPR) 2014, Stockholm, Sweden. https://doi.org/10.1109/ICPR.2014.96
Gao, Jiangning ; Emambakhsh, Mehryar ; Evans, A N. / A Low Dimensionality Expression Robust Rejector for 3D Face Recognition. Paper presented at IEEE International Conference on Pattern Recognition (ICPR) 2014, Stockholm, Sweden.511 p.
@conference{e5c742bbb7414b1bbb74cd0939dc67d6,
title = "A Low Dimensionality Expression Robust Rejector for 3D Face Recognition",
abstract = "In the past decade, expression variations have been one of the most challenging sources of variability in 3D face recognition, especially for scenarios where there are a large number of face samples to discriminate between. In this paper, an expression robust rejector is proposed that first robustly locates landmarks on the relatively stable structure of the nose and its environs, termed the cheek/nose region. Then, by defining curves connecting the landmarks, a small set of features (4 curves with only 15 points each) on the cheek/nose surface are selected using the Bosphorus database. The resulting rejector, which can quickly eliminate a large number of candidates at an early stage, is further evaluated on the FRGC database for both the identification and verification scenarios. The classification performance using only 60 points from 4 curves shows the effectiveness of this efficient expression robust rejector.",
keywords = "biometrics, face recognition, pattern rejection, feature selection",
author = "Jiangning Gao and Mehryar Emambakhsh and Evans, {A N}",
year = "2014",
doi = "10.1109/ICPR.2014.96",
language = "English",
pages = "506",
note = "IEEE International Conference on Pattern Recognition (ICPR) 2014 ; Conference date: 24-08-2014 Through 28-08-2014",

}

TY - CONF

T1 - A Low Dimensionality Expression Robust Rejector for 3D Face Recognition

AU - Gao, Jiangning

AU - Emambakhsh, Mehryar

AU - Evans, A N

PY - 2014

Y1 - 2014

N2 - In the past decade, expression variations have been one of the most challenging sources of variability in 3D face recognition, especially for scenarios where there are a large number of face samples to discriminate between. In this paper, an expression robust rejector is proposed that first robustly locates landmarks on the relatively stable structure of the nose and its environs, termed the cheek/nose region. Then, by defining curves connecting the landmarks, a small set of features (4 curves with only 15 points each) on the cheek/nose surface are selected using the Bosphorus database. The resulting rejector, which can quickly eliminate a large number of candidates at an early stage, is further evaluated on the FRGC database for both the identification and verification scenarios. The classification performance using only 60 points from 4 curves shows the effectiveness of this efficient expression robust rejector.

AB - In the past decade, expression variations have been one of the most challenging sources of variability in 3D face recognition, especially for scenarios where there are a large number of face samples to discriminate between. In this paper, an expression robust rejector is proposed that first robustly locates landmarks on the relatively stable structure of the nose and its environs, termed the cheek/nose region. Then, by defining curves connecting the landmarks, a small set of features (4 curves with only 15 points each) on the cheek/nose surface are selected using the Bosphorus database. The resulting rejector, which can quickly eliminate a large number of candidates at an early stage, is further evaluated on the FRGC database for both the identification and verification scenarios. The classification performance using only 60 points from 4 curves shows the effectiveness of this efficient expression robust rejector.

KW - biometrics

KW - face recognition

KW - pattern rejection

KW - feature selection

UR - http://www.icpr2014.org/

UR - http://dx.doi.org/10.1109/ICPR.2014.96

U2 - 10.1109/ICPR.2014.96

DO - 10.1109/ICPR.2014.96

M3 - Paper

SP - 506

ER -