Redesigning photo-ID to improve unfamiliar face matching performance

David White, A. Mike Burton, Rob Jenkins, Richard I. Kemp

Research output: Contribution to journalArticle

37 Citations (Scopus)
13 Downloads (Pure)

Abstract

Viewers find it difficult to match photos of unfamiliar faces for identity. Despite this, the use of photographic ID is widespread. In this study we ask whether it is possible to improve face matching performance by replacing single photographs on ID documents with multiple photos or an average image of the bearer. In three experiments we compare photo-to-photo matching with photo-to-average matching (where the average is formed from multiple photos of the same person) and photo-to-
array matching (where the array comprises separate photos of the same person). We consistently find an accuracy advantage for average images and photo arrays over single photos, and show that this improvement is driven by performance in match trials. In the final experiment, we find a benefit of four-image arrays relative to average images for unfamiliar faces, but not for familiar faces. We propose that conventional photo-ID format can be improved upon, and discuss this finding in the context of face recognition more generally.
Original languageEnglish
Pages (from-to)166-173
Number of pages8
JournalJournal of Experimental Psychology: Applied
Volume20
Issue number2
DOIs
Publication statusPublished - Jun 2014

Fingerprint

Facial Recognition

Keywords

  • face recognition
  • unfamiliar face matching
  • identity verification
  • facial image comparison
  • image averaging

Cite this

Redesigning photo-ID to improve unfamiliar face matching performance. / White, David; Burton, A. Mike; Jenkins, Rob; Kemp, Richard I.

In: Journal of Experimental Psychology: Applied, Vol. 20, No. 2, 06.2014, p. 166-173.

Research output: Contribution to journalArticle

White, David ; Burton, A. Mike ; Jenkins, Rob ; Kemp, Richard I. / Redesigning photo-ID to improve unfamiliar face matching performance. In: Journal of Experimental Psychology: Applied. 2014 ; Vol. 20, No. 2. pp. 166-173.
@article{3d6a8fcd725347e6928294521464dfd4,
title = "Redesigning photo-ID to improve unfamiliar face matching performance",
abstract = "Viewers find it difficult to match photos of unfamiliar faces for identity. Despite this, the use of photographic ID is widespread. In this study we ask whether it is possible to improve face matching performance by replacing single photographs on ID documents with multiple photos or an average image of the bearer. In three experiments we compare photo-to-photo matching with photo-to-average matching (where the average is formed from multiple photos of the same person) and photo-to-array matching (where the array comprises separate photos of the same person). We consistently find an accuracy advantage for average images and photo arrays over single photos, and show that this improvement is driven by performance in match trials. In the final experiment, we find a benefit of four-image arrays relative to average images for unfamiliar faces, but not for familiar faces. We propose that conventional photo-ID format can be improved upon, and discuss this finding in the context of face recognition more generally.",
keywords = "face recognition , unfamiliar face matching, identity verification, facial image comparison, image averaging",
author = "David White and Burton, {A. Mike} and Rob Jenkins and Kemp, {Richard I.}",
year = "2014",
month = "6",
doi = "10.1037/xap0000009",
language = "English",
volume = "20",
pages = "166--173",
journal = "Journal of Experimental Psychology: Applied",
issn = "1076-898X",
publisher = "American Psychological Association Inc.",
number = "2",

}

TY - JOUR

T1 - Redesigning photo-ID to improve unfamiliar face matching performance

AU - White, David

AU - Burton, A. Mike

AU - Jenkins, Rob

AU - Kemp, Richard I.

PY - 2014/6

Y1 - 2014/6

N2 - Viewers find it difficult to match photos of unfamiliar faces for identity. Despite this, the use of photographic ID is widespread. In this study we ask whether it is possible to improve face matching performance by replacing single photographs on ID documents with multiple photos or an average image of the bearer. In three experiments we compare photo-to-photo matching with photo-to-average matching (where the average is formed from multiple photos of the same person) and photo-to-array matching (where the array comprises separate photos of the same person). We consistently find an accuracy advantage for average images and photo arrays over single photos, and show that this improvement is driven by performance in match trials. In the final experiment, we find a benefit of four-image arrays relative to average images for unfamiliar faces, but not for familiar faces. We propose that conventional photo-ID format can be improved upon, and discuss this finding in the context of face recognition more generally.

AB - Viewers find it difficult to match photos of unfamiliar faces for identity. Despite this, the use of photographic ID is widespread. In this study we ask whether it is possible to improve face matching performance by replacing single photographs on ID documents with multiple photos or an average image of the bearer. In three experiments we compare photo-to-photo matching with photo-to-average matching (where the average is formed from multiple photos of the same person) and photo-to-array matching (where the array comprises separate photos of the same person). We consistently find an accuracy advantage for average images and photo arrays over single photos, and show that this improvement is driven by performance in match trials. In the final experiment, we find a benefit of four-image arrays relative to average images for unfamiliar faces, but not for familiar faces. We propose that conventional photo-ID format can be improved upon, and discuss this finding in the context of face recognition more generally.

KW - face recognition

KW - unfamiliar face matching

KW - identity verification

KW - facial image comparison

KW - image averaging

U2 - 10.1037/xap0000009

DO - 10.1037/xap0000009

M3 - Article

VL - 20

SP - 166

EP - 173

JO - Journal of Experimental Psychology: Applied

JF - Journal of Experimental Psychology: Applied

SN - 1076-898X

IS - 2

ER -