Matching face images taken on the same day or months apart

the limitations of photo ID

Ahmed M. Megreya, Adam Sandford, A. Mike Burton

Research output: Contribution to journalArticle

40 Citations (Scopus)
3 Downloads (Pure)

Abstract

It is well-established that matching images of unfamiliar faces is rather error prone. However, there is an important mismatch between face matching in laboratory and realistic settings. All of the currently available face-matching databases were designed to establish the baseline level of unfamiliar face perception. Therefore, target and test images for each face identity have been taken on the same day, minimizing within-face variations. In realistic settings, on the other hand, faces do vary, even day to day. This study examined the proficiency of matching images of unfamiliar faces, which were taken on the same day or months apart. In two experiments, same-day images were matched substantially more accurately and faster than different-date photographs using the standard 1-in-10 and pairwise face-matching tasks. This suggests that experimental studies on face matching underestimate its difficulty in real-world situations. Photographs of unfamiliar faces seem to be unreliable proofs of identity, especially if the ID documents do not use very recent images of the holders.
Original languageEnglish
Pages (from-to)700-706
Number of pages7
JournalApplied Cognitive Psychology
Volume27
Issue number6
DOIs
Publication statusPublished - 1 Nov 2013

Fingerprint

Databases
Data Base
Proficiency
Mismatch
Face Perception
Experimental Study
Experiment
Real World
Facial Recognition

Cite this

Matching face images taken on the same day or months apart : the limitations of photo ID. / Megreya, Ahmed M.; Sandford, Adam; Burton, A. Mike.

In: Applied Cognitive Psychology, Vol. 27, No. 6, 01.11.2013, p. 700-706.

Research output: Contribution to journalArticle

Megreya, Ahmed M. ; Sandford, Adam ; Burton, A. Mike. / Matching face images taken on the same day or months apart : the limitations of photo ID. In: Applied Cognitive Psychology. 2013 ; Vol. 27, No. 6. pp. 700-706.
@article{48a0d3402ba54079807184318c400c8c,
title = "Matching face images taken on the same day or months apart: the limitations of photo ID",
abstract = "It is well-established that matching images of unfamiliar faces is rather error prone. However, there is an important mismatch between face matching in laboratory and realistic settings. All of the currently available face-matching databases were designed to establish the baseline level of unfamiliar face perception. Therefore, target and test images for each face identity have been taken on the same day, minimizing within-face variations. In realistic settings, on the other hand, faces do vary, even day to day. This study examined the proficiency of matching images of unfamiliar faces, which were taken on the same day or months apart. In two experiments, same-day images were matched substantially more accurately and faster than different-date photographs using the standard 1-in-10 and pairwise face-matching tasks. This suggests that experimental studies on face matching underestimate its difficulty in real-world situations. Photographs of unfamiliar faces seem to be unreliable proofs of identity, especially if the ID documents do not use very recent images of the holders.",
author = "Megreya, {Ahmed M.} and Adam Sandford and Burton, {A. Mike}",
year = "2013",
month = "11",
day = "1",
doi = "10.1002/acp.2965",
language = "English",
volume = "27",
pages = "700--706",
journal = "Applied Cognitive Psychology",
issn = "0888-4080",
publisher = "John Wiley and Sons Ltd",
number = "6",

}

TY - JOUR

T1 - Matching face images taken on the same day or months apart

T2 - the limitations of photo ID

AU - Megreya, Ahmed M.

AU - Sandford, Adam

AU - Burton, A. Mike

PY - 2013/11/1

Y1 - 2013/11/1

N2 - It is well-established that matching images of unfamiliar faces is rather error prone. However, there is an important mismatch between face matching in laboratory and realistic settings. All of the currently available face-matching databases were designed to establish the baseline level of unfamiliar face perception. Therefore, target and test images for each face identity have been taken on the same day, minimizing within-face variations. In realistic settings, on the other hand, faces do vary, even day to day. This study examined the proficiency of matching images of unfamiliar faces, which were taken on the same day or months apart. In two experiments, same-day images were matched substantially more accurately and faster than different-date photographs using the standard 1-in-10 and pairwise face-matching tasks. This suggests that experimental studies on face matching underestimate its difficulty in real-world situations. Photographs of unfamiliar faces seem to be unreliable proofs of identity, especially if the ID documents do not use very recent images of the holders.

AB - It is well-established that matching images of unfamiliar faces is rather error prone. However, there is an important mismatch between face matching in laboratory and realistic settings. All of the currently available face-matching databases were designed to establish the baseline level of unfamiliar face perception. Therefore, target and test images for each face identity have been taken on the same day, minimizing within-face variations. In realistic settings, on the other hand, faces do vary, even day to day. This study examined the proficiency of matching images of unfamiliar faces, which were taken on the same day or months apart. In two experiments, same-day images were matched substantially more accurately and faster than different-date photographs using the standard 1-in-10 and pairwise face-matching tasks. This suggests that experimental studies on face matching underestimate its difficulty in real-world situations. Photographs of unfamiliar faces seem to be unreliable proofs of identity, especially if the ID documents do not use very recent images of the holders.

UR - http://www.scopus.com/inward/record.url?scp=84888339902&partnerID=8YFLogxK

U2 - 10.1002/acp.2965

DO - 10.1002/acp.2965

M3 - Article

VL - 27

SP - 700

EP - 706

JO - Applied Cognitive Psychology

JF - Applied Cognitive Psychology

SN - 0888-4080

IS - 6

ER -