New hope for recognizing twins by using facial motion

L Zhang, Ning Ye, Elisa MARTINEZ MARROQUIN, Dong Guo, Terence Sim

Research output: A Conference proceeding or a Chapter in BookConference contribution

5 Citations (Scopus)

Abstract

Distinguishing between identical twins is the Holy Grail in face recognition because of the great similarity between the faces of a pair of twins. Most existing face recognition systems choose to simply ignore it. However, as the population of twins increases quickly, such an “ostrich strategy” is no longer acceptable. The biometric systems that overlook the twins problem are presenting a serious security hole. Inspired by recent advances in motion-based face recognition techniques, we propose to use facial motion to address the twins problem. We collect a twins facial expression database and conduct a series of experiments in two assumed scenarios: the Social Party Scenario and the Access Control Scenario. The experimental results show that facial motion ourperforms facial appearance in distinguishing between twins. Based on this finding, we propose a two-stage cascaded General Access Control System, which combines facial appearance with facial motion. The experimental results show that, compared with an appearance-based face recognition system, this cascaded system is much more secure against an “evil-twin” imposter attack, while performing as good for normal population
Original languageEnglish
Title of host publicationApplications of Computer Vision (WACV), 2012 IEEE Workshop on
Place of PublicationBreckenridge, CO
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages209-214
Number of pages6
Volume1
ISBN (Print)9781467302340, 9781467302333
DOIs
Publication statusPublished - 2012
Externally publishedYes
EventIEEE Worshop on Applications of Computer Vision (WACV 2012) - Breckenridge, Breckenridge, United States
Duration: 9 Jan 201211 Jan 2012

Conference

ConferenceIEEE Worshop on Applications of Computer Vision (WACV 2012)
CountryUnited States
CityBreckenridge
Period9/01/1211/01/12

Fingerprint

Face recognition
Access control
Biometrics
Control systems
Experiments

Cite this

Zhang, L., Ye, N., MARTINEZ MARROQUIN, E., Guo, D., & Sim, T. (2012). New hope for recognizing twins by using facial motion. In Applications of Computer Vision (WACV), 2012 IEEE Workshop on (Vol. 1, pp. 209-214). Breckenridge, CO: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/WACV.2012.6163026
Zhang, L ; Ye, Ning ; MARTINEZ MARROQUIN, Elisa ; Guo, Dong ; Sim, Terence. / New hope for recognizing twins by using facial motion. Applications of Computer Vision (WACV), 2012 IEEE Workshop on. Vol. 1 Breckenridge, CO : IEEE, Institute of Electrical and Electronics Engineers, 2012. pp. 209-214
@inproceedings{bd38e8eb81ca4d6bacbf64e40871f682,
title = "New hope for recognizing twins by using facial motion",
abstract = "Distinguishing between identical twins is the Holy Grail in face recognition because of the great similarity between the faces of a pair of twins. Most existing face recognition systems choose to simply ignore it. However, as the population of twins increases quickly, such an “ostrich strategy” is no longer acceptable. The biometric systems that overlook the twins problem are presenting a serious security hole. Inspired by recent advances in motion-based face recognition techniques, we propose to use facial motion to address the twins problem. We collect a twins facial expression database and conduct a series of experiments in two assumed scenarios: the Social Party Scenario and the Access Control Scenario. The experimental results show that facial motion ourperforms facial appearance in distinguishing between twins. Based on this finding, we propose a two-stage cascaded General Access Control System, which combines facial appearance with facial motion. The experimental results show that, compared with an appearance-based face recognition system, this cascaded system is much more secure against an “evil-twin” imposter attack, while performing as good for normal population",
keywords = "face-recognition, facial-motion, twins-recognition",
author = "L Zhang and Ning Ye and {MARTINEZ MARROQUIN}, Elisa and Dong Guo and Terence Sim",
year = "2012",
doi = "10.1109/WACV.2012.6163026",
language = "English",
isbn = "9781467302340",
volume = "1",
pages = "209--214",
booktitle = "Applications of Computer Vision (WACV), 2012 IEEE Workshop on",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States",

}

Zhang, L, Ye, N, MARTINEZ MARROQUIN, E, Guo, D & Sim, T 2012, New hope for recognizing twins by using facial motion. in Applications of Computer Vision (WACV), 2012 IEEE Workshop on. vol. 1, IEEE, Institute of Electrical and Electronics Engineers, Breckenridge, CO, pp. 209-214, IEEE Worshop on Applications of Computer Vision (WACV 2012), Breckenridge, United States, 9/01/12. https://doi.org/10.1109/WACV.2012.6163026

New hope for recognizing twins by using facial motion. / Zhang, L; Ye, Ning; MARTINEZ MARROQUIN, Elisa; Guo, Dong; Sim, Terence.

Applications of Computer Vision (WACV), 2012 IEEE Workshop on. Vol. 1 Breckenridge, CO : IEEE, Institute of Electrical and Electronics Engineers, 2012. p. 209-214.

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - New hope for recognizing twins by using facial motion

AU - Zhang, L

AU - Ye, Ning

AU - MARTINEZ MARROQUIN, Elisa

AU - Guo, Dong

AU - Sim, Terence

PY - 2012

Y1 - 2012

N2 - Distinguishing between identical twins is the Holy Grail in face recognition because of the great similarity between the faces of a pair of twins. Most existing face recognition systems choose to simply ignore it. However, as the population of twins increases quickly, such an “ostrich strategy” is no longer acceptable. The biometric systems that overlook the twins problem are presenting a serious security hole. Inspired by recent advances in motion-based face recognition techniques, we propose to use facial motion to address the twins problem. We collect a twins facial expression database and conduct a series of experiments in two assumed scenarios: the Social Party Scenario and the Access Control Scenario. The experimental results show that facial motion ourperforms facial appearance in distinguishing between twins. Based on this finding, we propose a two-stage cascaded General Access Control System, which combines facial appearance with facial motion. The experimental results show that, compared with an appearance-based face recognition system, this cascaded system is much more secure against an “evil-twin” imposter attack, while performing as good for normal population

AB - Distinguishing between identical twins is the Holy Grail in face recognition because of the great similarity between the faces of a pair of twins. Most existing face recognition systems choose to simply ignore it. However, as the population of twins increases quickly, such an “ostrich strategy” is no longer acceptable. The biometric systems that overlook the twins problem are presenting a serious security hole. Inspired by recent advances in motion-based face recognition techniques, we propose to use facial motion to address the twins problem. We collect a twins facial expression database and conduct a series of experiments in two assumed scenarios: the Social Party Scenario and the Access Control Scenario. The experimental results show that facial motion ourperforms facial appearance in distinguishing between twins. Based on this finding, we propose a two-stage cascaded General Access Control System, which combines facial appearance with facial motion. The experimental results show that, compared with an appearance-based face recognition system, this cascaded system is much more secure against an “evil-twin” imposter attack, while performing as good for normal population

KW - face-recognition

KW - facial-motion

KW - twins-recognition

U2 - 10.1109/WACV.2012.6163026

DO - 10.1109/WACV.2012.6163026

M3 - Conference contribution

SN - 9781467302340

SN - 9781467302333

VL - 1

SP - 209

EP - 214

BT - Applications of Computer Vision (WACV), 2012 IEEE Workshop on

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Breckenridge, CO

ER -

Zhang L, Ye N, MARTINEZ MARROQUIN E, Guo D, Sim T. New hope for recognizing twins by using facial motion. In Applications of Computer Vision (WACV), 2012 IEEE Workshop on. Vol. 1. Breckenridge, CO: IEEE, Institute of Electrical and Electronics Engineers. 2012. p. 209-214 https://doi.org/10.1109/WACV.2012.6163026