Can facial uniqueness be inferred from impostor scores?

A. Dutta, Raymond N.J. Veldhuis, Lieuwe Jan Spreeuwers

Abstract

In Biometrics, facial uniqueness is commonly inferred from impostor similarity scores. In this paper, we show that such uniqueness measures are highly unstable in the presence of image quality variations like pose, noise and blur. We also experimentally demonstrate the instability of a recently introduced impostor-based uniqueness measure of [Klare and Jain 2013] when subject to poor quality facial images.
Original languageUndefined
Title of host publicationBiometric Technologies in Forensic Science, BTFS 2013
Place of PublicationNijmegen
PublisherCentre for Language and Speech Technology, Radboud University
Pages-
Number of pages6
ISBN (Print)not assigned
StatePublished - Oct 2013

Publication series

Name
PublisherCentre for Language and Speech Technology, Radboud University

Fingerprint

Biometrics
Image quality

Keywords

  • EC Grant Agreement nr.: FP7-PEOPLE-ITN-2008
  • SCS-Safety
  • facial uniqueness
  • IR-87561
  • EWI-23857
  • Image quality
  • METIS-300102
  • impostor based uniqueness measure

Cite this

Dutta, A., Veldhuis, R. N. J., & Spreeuwers, L. J. (2013). Can facial uniqueness be inferred from impostor scores? In Biometric Technologies in Forensic Science, BTFS 2013 (pp. -). Nijmegen: Centre for Language and Speech Technology, Radboud University.

Dutta, A.; Veldhuis, Raymond N.J.; Spreeuwers, Lieuwe Jan / Can facial uniqueness be inferred from impostor scores?

Biometric Technologies in Forensic Science, BTFS 2013. Nijmegen : Centre for Language and Speech Technology, Radboud University, 2013. p. -.

Research output: Scientific - peer-review › Conference contribution

@inbook{b7510461053d4e3ebb5d21438ec3935a,
title = "Can facial uniqueness be inferred from impostor scores?",
abstract = "In Biometrics, facial uniqueness is commonly inferred from impostor similarity scores. In this paper, we show that such uniqueness measures are highly unstable in the presence of image quality variations like pose, noise and blur. We also experimentally demonstrate the instability of a recently introduced impostor-based uniqueness measure of [Klare and Jain 2013] when subject to poor quality facial images.",
keywords = "EC Grant Agreement nr.: FP7-PEOPLE-ITN-2008, SCS-Safety, facial uniqueness, IR-87561, EWI-23857, Image quality, METIS-300102, impostor based uniqueness measure",
author = "A. Dutta and Veldhuis, {Raymond N.J.} and Spreeuwers, {Lieuwe Jan}",
note = "http://cls.ru.nl/staff/dvleeuwen/btfs-2013/dutta-btfs2013.pdf",
year = "2013",
month = "10",
isbn = "not assigned",
publisher = "Centre for Language and Speech Technology, Radboud University",
pages = "--",
booktitle = "Biometric Technologies in Forensic Science, BTFS 2013",

}

Dutta, A, Veldhuis, RNJ & Spreeuwers, LJ 2013, Can facial uniqueness be inferred from impostor scores? in Biometric Technologies in Forensic Science, BTFS 2013. Centre for Language and Speech Technology, Radboud University, Nijmegen, pp. -.

Can facial uniqueness be inferred from impostor scores? / Dutta, A.; Veldhuis, Raymond N.J.; Spreeuwers, Lieuwe Jan.

Biometric Technologies in Forensic Science, BTFS 2013. Nijmegen : Centre for Language and Speech Technology, Radboud University, 2013. p. -.

Research output: Scientific - peer-review › Conference contribution

TY - CHAP

T1 - Can facial uniqueness be inferred from impostor scores?

AU - Dutta,A.

AU - Veldhuis,Raymond N.J.

AU - Spreeuwers,Lieuwe Jan

N1 - http://cls.ru.nl/staff/dvleeuwen/btfs-2013/dutta-btfs2013.pdf

PY - 2013/10

Y1 - 2013/10

N2 - In Biometrics, facial uniqueness is commonly inferred from impostor similarity scores. In this paper, we show that such uniqueness measures are highly unstable in the presence of image quality variations like pose, noise and blur. We also experimentally demonstrate the instability of a recently introduced impostor-based uniqueness measure of [Klare and Jain 2013] when subject to poor quality facial images.

AB - In Biometrics, facial uniqueness is commonly inferred from impostor similarity scores. In this paper, we show that such uniqueness measures are highly unstable in the presence of image quality variations like pose, noise and blur. We also experimentally demonstrate the instability of a recently introduced impostor-based uniqueness measure of [Klare and Jain 2013] when subject to poor quality facial images.

KW - EC Grant Agreement nr.: FP7-PEOPLE-ITN-2008

KW - SCS-Safety

KW - facial uniqueness

KW - IR-87561

KW - EWI-23857

KW - Image quality

KW - METIS-300102

KW - impostor based uniqueness measure

M3 - Conference contribution

SN - not assigned

SP - -

BT - Biometric Technologies in Forensic Science, BTFS 2013

PB - Centre for Language and Speech Technology, Radboud University

ER -

Dutta A, Veldhuis RNJ, Spreeuwers LJ. Can facial uniqueness be inferred from impostor scores? In Biometric Technologies in Forensic Science, BTFS 2013. Nijmegen: Centre for Language and Speech Technology, Radboud University. 2013. p. -.

Access to Document