Evaluation of automatic face recognition for automatic border control on actual data recorded of travellers at Schiphol Airport

Lieuwe Jan Spreeuwers, A.J. Hendrikse, K.J. Gerritsen

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

18 Citations (Scopus)
1 Downloads (Pure)

Abstract

Automatic border control at airports using automated facial recognition for checking the passport is becoming more and more common. A problem is that it is not clear how reliable these automatic gates are. Very few independent studies exist that assess the reliability of automated facial recognition for border control. In this evaluation study the reliability of automated facial recognition for automatic border passage was investigated. To investigate the quality of the images and face recognition, during 2 weeks data of real passengers were acquired at Schiphol Airport using 2 different automatic gates of about 950 passengers for both gates. This data alone already makes the evaluation study of great value. The evaluation experiment consisted of comparing live images of every passenger to the digital photographs stored on their passports. Every live image is compared to every digital passport photograph. In this way we can estimate both the False Accept Rate as well as the Verification Rate. In spite of the critical analysis in this study, the prospects for automatic border passage using face recognition are very good. We expect that, provided that the quality of the live images acquired by the gates is improved and if possible the quality of the digital photographs stored on the passport, excellent recognition results can be obtained with Verification Rates (VR) of above 99% at a False Accept Rate (FAR) of 0.1% or even lower.
Original languageUndefined
Title of host publication2012 BIOSIG - Proceedings of the International Conference of Biometrics Special Interest Group
EditorsA. Brömme, C. Busch
Place of PublicationDarmstadt
PublisherGesellschaft für Informatik
Pages1-6
Number of pages6
ISBN (Print)978-1-4673-1010-9
Publication statusPublished - 6 Sep 2012
Event11th International Conference of Biometrics Special Interest Group, BIOSIG 2012 - Darmstadt, Germany
Duration: 6 Sep 20127 Sep 2012
Conference number: 11

Publication series

NameProceedings of the International Conference of Biometrics Special Interest Group
PublisherGesellschaft für Informatik e.V.
ISSN (Print)1617-5468

Conference

Conference11th International Conference of Biometrics Special Interest Group, BIOSIG 2012
Abbreviated titleBIOSIG 2012
CountryGermany
CityDarmstadt
Period6/09/127/09/12

Keywords

  • IR-83553
  • EWI-22787
  • SCS-Safety
  • verification rate
  • METIS-293274
  • FAR
  • Schiphol airport
  • VR
  • passport checking
  • false accept rate
  • live passenger image quality
  • automatic border passage control
  • automatic face recognition evaluation
  • automatic gates
  • digital passport photograph
  • traveller data recording

Cite this

Spreeuwers, L. J., Hendrikse, A. J., & Gerritsen, K. J. (2012). Evaluation of automatic face recognition for automatic border control on actual data recorded of travellers at Schiphol Airport. In A. Brömme, & C. Busch (Eds.), 2012 BIOSIG - Proceedings of the International Conference of Biometrics Special Interest Group (pp. 1-6). (Proceedings of the International Conference of Biometrics Special Interest Group). Darmstadt: Gesellschaft für Informatik.
Spreeuwers, Lieuwe Jan ; Hendrikse, A.J. ; Gerritsen, K.J. / Evaluation of automatic face recognition for automatic border control on actual data recorded of travellers at Schiphol Airport. 2012 BIOSIG - Proceedings of the International Conference of Biometrics Special Interest Group. editor / A. Brömme ; C. Busch. Darmstadt : Gesellschaft für Informatik, 2012. pp. 1-6 (Proceedings of the International Conference of Biometrics Special Interest Group).
@inproceedings{d530b7ae815840de8564be09131b92dc,
title = "Evaluation of automatic face recognition for automatic border control on actual data recorded of travellers at Schiphol Airport",
abstract = "Automatic border control at airports using automated facial recognition for checking the passport is becoming more and more common. A problem is that it is not clear how reliable these automatic gates are. Very few independent studies exist that assess the reliability of automated facial recognition for border control. In this evaluation study the reliability of automated facial recognition for automatic border passage was investigated. To investigate the quality of the images and face recognition, during 2 weeks data of real passengers were acquired at Schiphol Airport using 2 different automatic gates of about 950 passengers for both gates. This data alone already makes the evaluation study of great value. The evaluation experiment consisted of comparing live images of every passenger to the digital photographs stored on their passports. Every live image is compared to every digital passport photograph. In this way we can estimate both the False Accept Rate as well as the Verification Rate. In spite of the critical analysis in this study, the prospects for automatic border passage using face recognition are very good. We expect that, provided that the quality of the live images acquired by the gates is improved and if possible the quality of the digital photographs stored on the passport, excellent recognition results can be obtained with Verification Rates (VR) of above 99{\%} at a False Accept Rate (FAR) of 0.1{\%} or even lower.",
keywords = "IR-83553, EWI-22787, SCS-Safety, verification rate, METIS-293274, FAR, Schiphol airport, VR, passport checking, false accept rate, live passenger image quality, automatic border passage control, automatic face recognition evaluation, automatic gates, digital passport photograph, traveller data recording",
author = "Spreeuwers, {Lieuwe Jan} and A.J. Hendrikse and K.J. Gerritsen",
year = "2012",
month = "9",
day = "6",
language = "Undefined",
isbn = "978-1-4673-1010-9",
series = "Proceedings of the International Conference of Biometrics Special Interest Group",
publisher = "Gesellschaft f{\"u}r Informatik",
pages = "1--6",
editor = "A. Br{\"o}mme and C. Busch",
booktitle = "2012 BIOSIG - Proceedings of the International Conference of Biometrics Special Interest Group",
address = "Germany",

}

Spreeuwers, LJ, Hendrikse, AJ & Gerritsen, KJ 2012, Evaluation of automatic face recognition for automatic border control on actual data recorded of travellers at Schiphol Airport. in A Brömme & C Busch (eds), 2012 BIOSIG - Proceedings of the International Conference of Biometrics Special Interest Group. Proceedings of the International Conference of Biometrics Special Interest Group, Gesellschaft für Informatik, Darmstadt, pp. 1-6, 11th International Conference of Biometrics Special Interest Group, BIOSIG 2012, Darmstadt, Germany, 6/09/12.

Evaluation of automatic face recognition for automatic border control on actual data recorded of travellers at Schiphol Airport. / Spreeuwers, Lieuwe Jan; Hendrikse, A.J.; Gerritsen, K.J.

2012 BIOSIG - Proceedings of the International Conference of Biometrics Special Interest Group. ed. / A. Brömme; C. Busch. Darmstadt : Gesellschaft für Informatik, 2012. p. 1-6 (Proceedings of the International Conference of Biometrics Special Interest Group).

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Evaluation of automatic face recognition for automatic border control on actual data recorded of travellers at Schiphol Airport

AU - Spreeuwers, Lieuwe Jan

AU - Hendrikse, A.J.

AU - Gerritsen, K.J.

PY - 2012/9/6

Y1 - 2012/9/6

N2 - Automatic border control at airports using automated facial recognition for checking the passport is becoming more and more common. A problem is that it is not clear how reliable these automatic gates are. Very few independent studies exist that assess the reliability of automated facial recognition for border control. In this evaluation study the reliability of automated facial recognition for automatic border passage was investigated. To investigate the quality of the images and face recognition, during 2 weeks data of real passengers were acquired at Schiphol Airport using 2 different automatic gates of about 950 passengers for both gates. This data alone already makes the evaluation study of great value. The evaluation experiment consisted of comparing live images of every passenger to the digital photographs stored on their passports. Every live image is compared to every digital passport photograph. In this way we can estimate both the False Accept Rate as well as the Verification Rate. In spite of the critical analysis in this study, the prospects for automatic border passage using face recognition are very good. We expect that, provided that the quality of the live images acquired by the gates is improved and if possible the quality of the digital photographs stored on the passport, excellent recognition results can be obtained with Verification Rates (VR) of above 99% at a False Accept Rate (FAR) of 0.1% or even lower.

AB - Automatic border control at airports using automated facial recognition for checking the passport is becoming more and more common. A problem is that it is not clear how reliable these automatic gates are. Very few independent studies exist that assess the reliability of automated facial recognition for border control. In this evaluation study the reliability of automated facial recognition for automatic border passage was investigated. To investigate the quality of the images and face recognition, during 2 weeks data of real passengers were acquired at Schiphol Airport using 2 different automatic gates of about 950 passengers for both gates. This data alone already makes the evaluation study of great value. The evaluation experiment consisted of comparing live images of every passenger to the digital photographs stored on their passports. Every live image is compared to every digital passport photograph. In this way we can estimate both the False Accept Rate as well as the Verification Rate. In spite of the critical analysis in this study, the prospects for automatic border passage using face recognition are very good. We expect that, provided that the quality of the live images acquired by the gates is improved and if possible the quality of the digital photographs stored on the passport, excellent recognition results can be obtained with Verification Rates (VR) of above 99% at a False Accept Rate (FAR) of 0.1% or even lower.

KW - IR-83553

KW - EWI-22787

KW - SCS-Safety

KW - verification rate

KW - METIS-293274

KW - FAR

KW - Schiphol airport

KW - VR

KW - passport checking

KW - false accept rate

KW - live passenger image quality

KW - automatic border passage control

KW - automatic face recognition evaluation

KW - automatic gates

KW - digital passport photograph

KW - traveller data recording

M3 - Conference contribution

SN - 978-1-4673-1010-9

T3 - Proceedings of the International Conference of Biometrics Special Interest Group

SP - 1

EP - 6

BT - 2012 BIOSIG - Proceedings of the International Conference of Biometrics Special Interest Group

A2 - Brömme, A.

A2 - Busch, C.

PB - Gesellschaft für Informatik

CY - Darmstadt

ER -

Spreeuwers LJ, Hendrikse AJ, Gerritsen KJ. Evaluation of automatic face recognition for automatic border control on actual data recorded of travellers at Schiphol Airport. In Brömme A, Busch C, editors, 2012 BIOSIG - Proceedings of the International Conference of Biometrics Special Interest Group. Darmstadt: Gesellschaft für Informatik. 2012. p. 1-6. (Proceedings of the International Conference of Biometrics Special Interest Group).