Effect of calibration data on forensic likelihood ratio from a face recognition system

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

8 Citations (Scopus)
78 Downloads (Pure)

Abstract

A biometric system used for forensic evaluation requires a conversion of the score to a likelihood ratio. A likelihood ratio can be computed as the ratio of the probability of a score given the prosecution hypothesis is true and the probability of a score given the defense hypothesis is true. In this paper we study two different approaches of a forensic likelihood ratio computation in the context of forensic face recognition. These approaches differ in the databases they use to obtain the score distribution under the prosecution and the defense hypothesis and therefore consider slightly different interpretation of these hypotheses. The goal of this study is to quantify the effect of these approaches on the resultant likelihood ratio in the context of evidence evaluation from a face recognition system. A state-of-the art commercial face recognition system is employed for facial images comparison and computation of scores. A simple forensic case is simulated by randomly selecting a small subset from the FRGC database. Images in this subset are used to estimate the score distribution under the prosecution and the defense hypothesis and the effect of different approaches of a likelihood ratio computation is demonstrated and explained. It is observed that there is a significant variation in the resultant likelihood ratios given the databases which are used to model the prosecution and defense hypothesis are varied.
Original languageUndefined
Title of host publicationIEEE Sixth International Conference on Biometrics: Theory, Applications and Systems, BTAS 2013
Place of PublicationUnited States
PublisherIEEE
Pages1-8
Number of pages8
ISBN (Print)978-1-4799-0527-0
DOIs
Publication statusPublished - 30 Sep 2013

Publication series

NameIEEE explore digital library
PublisherIEEE

Keywords

  • SCS-Safety
  • EWI-24346
  • IR-89303
  • METIS-302665
  • Forensics
  • Image Processing
  • Face Recognition
  • Biometrics

Cite this

Ali, T., Spreeuwers, L. J., Veldhuis, R. N. J., Meuwly, D., & Meuwly, D. (2013). Effect of calibration data on forensic likelihood ratio from a face recognition system. In IEEE Sixth International Conference on Biometrics: Theory, Applications and Systems, BTAS 2013 (pp. 1-8). (IEEE explore digital library). United States: IEEE. https://doi.org/10.1109/BTAS.2013.6712709
Ali, Tauseef ; Spreeuwers, Lieuwe Jan ; Veldhuis, Raymond N.J. ; Meuwly, Didier ; Meuwly, Didier. / Effect of calibration data on forensic likelihood ratio from a face recognition system. IEEE Sixth International Conference on Biometrics: Theory, Applications and Systems, BTAS 2013. United States : IEEE, 2013. pp. 1-8 (IEEE explore digital library).
@inproceedings{58b15c4834584c88953b44a62b982e17,
title = "Effect of calibration data on forensic likelihood ratio from a face recognition system",
abstract = "A biometric system used for forensic evaluation requires a conversion of the score to a likelihood ratio. A likelihood ratio can be computed as the ratio of the probability of a score given the prosecution hypothesis is true and the probability of a score given the defense hypothesis is true. In this paper we study two different approaches of a forensic likelihood ratio computation in the context of forensic face recognition. These approaches differ in the databases they use to obtain the score distribution under the prosecution and the defense hypothesis and therefore consider slightly different interpretation of these hypotheses. The goal of this study is to quantify the effect of these approaches on the resultant likelihood ratio in the context of evidence evaluation from a face recognition system. A state-of-the art commercial face recognition system is employed for facial images comparison and computation of scores. A simple forensic case is simulated by randomly selecting a small subset from the FRGC database. Images in this subset are used to estimate the score distribution under the prosecution and the defense hypothesis and the effect of different approaches of a likelihood ratio computation is demonstrated and explained. It is observed that there is a significant variation in the resultant likelihood ratios given the databases which are used to model the prosecution and defense hypothesis are varied.",
keywords = "SCS-Safety, EWI-24346, IR-89303, METIS-302665, Forensics, Image Processing, Face Recognition, Biometrics",
author = "Tauseef Ali and Spreeuwers, {Lieuwe Jan} and Veldhuis, {Raymond N.J.} and Didier Meuwly and Didier Meuwly",
note = "10.1109/BTAS.2013.6712709",
year = "2013",
month = "9",
day = "30",
doi = "10.1109/BTAS.2013.6712709",
language = "Undefined",
isbn = "978-1-4799-0527-0",
series = "IEEE explore digital library",
publisher = "IEEE",
pages = "1--8",
booktitle = "IEEE Sixth International Conference on Biometrics: Theory, Applications and Systems, BTAS 2013",
address = "United States",

}

Ali, T, Spreeuwers, LJ, Veldhuis, RNJ, Meuwly, D & Meuwly, D 2013, Effect of calibration data on forensic likelihood ratio from a face recognition system. in IEEE Sixth International Conference on Biometrics: Theory, Applications and Systems, BTAS 2013. IEEE explore digital library, IEEE, United States, pp. 1-8. https://doi.org/10.1109/BTAS.2013.6712709

Effect of calibration data on forensic likelihood ratio from a face recognition system. / Ali, Tauseef; Spreeuwers, Lieuwe Jan; Veldhuis, Raymond N.J.; Meuwly, Didier; Meuwly, Didier.

IEEE Sixth International Conference on Biometrics: Theory, Applications and Systems, BTAS 2013. United States : IEEE, 2013. p. 1-8 (IEEE explore digital library).

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

TY - GEN

T1 - Effect of calibration data on forensic likelihood ratio from a face recognition system

AU - Ali, Tauseef

AU - Spreeuwers, Lieuwe Jan

AU - Veldhuis, Raymond N.J.

AU - Meuwly, Didier

AU - Meuwly, Didier

N1 - 10.1109/BTAS.2013.6712709

PY - 2013/9/30

Y1 - 2013/9/30

N2 - A biometric system used for forensic evaluation requires a conversion of the score to a likelihood ratio. A likelihood ratio can be computed as the ratio of the probability of a score given the prosecution hypothesis is true and the probability of a score given the defense hypothesis is true. In this paper we study two different approaches of a forensic likelihood ratio computation in the context of forensic face recognition. These approaches differ in the databases they use to obtain the score distribution under the prosecution and the defense hypothesis and therefore consider slightly different interpretation of these hypotheses. The goal of this study is to quantify the effect of these approaches on the resultant likelihood ratio in the context of evidence evaluation from a face recognition system. A state-of-the art commercial face recognition system is employed for facial images comparison and computation of scores. A simple forensic case is simulated by randomly selecting a small subset from the FRGC database. Images in this subset are used to estimate the score distribution under the prosecution and the defense hypothesis and the effect of different approaches of a likelihood ratio computation is demonstrated and explained. It is observed that there is a significant variation in the resultant likelihood ratios given the databases which are used to model the prosecution and defense hypothesis are varied.

AB - A biometric system used for forensic evaluation requires a conversion of the score to a likelihood ratio. A likelihood ratio can be computed as the ratio of the probability of a score given the prosecution hypothesis is true and the probability of a score given the defense hypothesis is true. In this paper we study two different approaches of a forensic likelihood ratio computation in the context of forensic face recognition. These approaches differ in the databases they use to obtain the score distribution under the prosecution and the defense hypothesis and therefore consider slightly different interpretation of these hypotheses. The goal of this study is to quantify the effect of these approaches on the resultant likelihood ratio in the context of evidence evaluation from a face recognition system. A state-of-the art commercial face recognition system is employed for facial images comparison and computation of scores. A simple forensic case is simulated by randomly selecting a small subset from the FRGC database. Images in this subset are used to estimate the score distribution under the prosecution and the defense hypothesis and the effect of different approaches of a likelihood ratio computation is demonstrated and explained. It is observed that there is a significant variation in the resultant likelihood ratios given the databases which are used to model the prosecution and defense hypothesis are varied.

KW - SCS-Safety

KW - EWI-24346

KW - IR-89303

KW - METIS-302665

KW - Forensics

KW - Image Processing

KW - Face Recognition

KW - Biometrics

U2 - 10.1109/BTAS.2013.6712709

DO - 10.1109/BTAS.2013.6712709

M3 - Conference contribution

SN - 978-1-4799-0527-0

T3 - IEEE explore digital library

SP - 1

EP - 8

BT - IEEE Sixth International Conference on Biometrics: Theory, Applications and Systems, BTAS 2013

PB - IEEE

CY - United States

ER -

Ali T, Spreeuwers LJ, Veldhuis RNJ, Meuwly D, Meuwly D. Effect of calibration data on forensic likelihood ratio from a face recognition system. In IEEE Sixth International Conference on Biometrics: Theory, Applications and Systems, BTAS 2013. United States: IEEE. 2013. p. 1-8. (IEEE explore digital library). https://doi.org/10.1109/BTAS.2013.6712709