Face averages enhance user recognition for smartphone security

David J. Robertson, Robin S. S. Kramer, A. Mike Burton

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

Our recognition of familiar faces is excellent, and generalises across viewing conditions. However, unfamiliar face recognition is much poorer. For this reason, automatic face recognition systems might benefit from incorporating the advantages of familiarity. Here we put this to the test using the face verification system available on a popular smartphone (the Samsung Galaxy). In two experiments we tested the recognition performance of the smartphone when it was encoded with an individual’s 'face-average' – a representation derived from theories of human face perception. This technique significantly improved performance for both unconstrained celebrity images (Experiment 1) and for real faces (Experiment 2): users could unlock their phones more reliably when the device stored an average of the user’s face than when they stored a single image. This advantage was consistent across a wide variety of everyday viewing conditions. Furthermore, the benefit did not reduce the rejection of imposter faces. This benefit is brought about solely by consideration of suitable representations for automatic face recognition, and we argue that this is just as important as development of matching algorithms themselves. We propose that this representation could significantly improve recognition rates in everyday settings.
LanguageEnglish
Article numbere0119460
Pages1-11
Number of pages11
JournalPLOS One
Volume10
Issue number3
DOIs
Publication statusPublished - 25 Mar 2015

Fingerprint

Smartphones
Face recognition
Galaxies
Experiments
Recognition (Psychology)
Smartphone
Equipment and Supplies
Facial Recognition

Keywords

  • face recognition
  • smartphone

Cite this

Robertson, David J. ; Kramer, Robin S. S. ; Burton, A. Mike. / Face averages enhance user recognition for smartphone security. In: PLOS One. 2015 ; Vol. 10, No. 3. pp. 1-11.
@article{5a69dbeca9574eea9cfce650445f9d7f,
title = "Face averages enhance user recognition for smartphone security",
abstract = "Our recognition of familiar faces is excellent, and generalises across viewing conditions. However, unfamiliar face recognition is much poorer. For this reason, automatic face recognition systems might benefit from incorporating the advantages of familiarity. Here we put this to the test using the face verification system available on a popular smartphone (the Samsung Galaxy). In two experiments we tested the recognition performance of the smartphone when it was encoded with an individual’s 'face-average' – a representation derived from theories of human face perception. This technique significantly improved performance for both unconstrained celebrity images (Experiment 1) and for real faces (Experiment 2): users could unlock their phones more reliably when the device stored an average of the user’s face than when they stored a single image. This advantage was consistent across a wide variety of everyday viewing conditions. Furthermore, the benefit did not reduce the rejection of imposter faces. This benefit is brought about solely by consideration of suitable representations for automatic face recognition, and we argue that this is just as important as development of matching algorithms themselves. We propose that this representation could significantly improve recognition rates in everyday settings.",
keywords = "face recognition, smartphone",
author = "Robertson, {David J.} and Kramer, {Robin S. S.} and Burton, {A. Mike}",
year = "2015",
month = "3",
day = "25",
doi = "10.1371/journal.pone.0119460",
language = "English",
volume = "10",
pages = "1--11",
journal = "PLOS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "3",

}

Face averages enhance user recognition for smartphone security. / Robertson, David J.; Kramer, Robin S. S.; Burton, A. Mike.

In: PLOS One, Vol. 10, No. 3, e0119460, 25.03.2015, p. 1-11.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Face averages enhance user recognition for smartphone security

AU - Robertson, David J.

AU - Kramer, Robin S. S.

AU - Burton, A. Mike

PY - 2015/3/25

Y1 - 2015/3/25

N2 - Our recognition of familiar faces is excellent, and generalises across viewing conditions. However, unfamiliar face recognition is much poorer. For this reason, automatic face recognition systems might benefit from incorporating the advantages of familiarity. Here we put this to the test using the face verification system available on a popular smartphone (the Samsung Galaxy). In two experiments we tested the recognition performance of the smartphone when it was encoded with an individual’s 'face-average' – a representation derived from theories of human face perception. This technique significantly improved performance for both unconstrained celebrity images (Experiment 1) and for real faces (Experiment 2): users could unlock their phones more reliably when the device stored an average of the user’s face than when they stored a single image. This advantage was consistent across a wide variety of everyday viewing conditions. Furthermore, the benefit did not reduce the rejection of imposter faces. This benefit is brought about solely by consideration of suitable representations for automatic face recognition, and we argue that this is just as important as development of matching algorithms themselves. We propose that this representation could significantly improve recognition rates in everyday settings.

AB - Our recognition of familiar faces is excellent, and generalises across viewing conditions. However, unfamiliar face recognition is much poorer. For this reason, automatic face recognition systems might benefit from incorporating the advantages of familiarity. Here we put this to the test using the face verification system available on a popular smartphone (the Samsung Galaxy). In two experiments we tested the recognition performance of the smartphone when it was encoded with an individual’s 'face-average' – a representation derived from theories of human face perception. This technique significantly improved performance for both unconstrained celebrity images (Experiment 1) and for real faces (Experiment 2): users could unlock their phones more reliably when the device stored an average of the user’s face than when they stored a single image. This advantage was consistent across a wide variety of everyday viewing conditions. Furthermore, the benefit did not reduce the rejection of imposter faces. This benefit is brought about solely by consideration of suitable representations for automatic face recognition, and we argue that this is just as important as development of matching algorithms themselves. We propose that this representation could significantly improve recognition rates in everyday settings.

KW - face recognition

KW - smartphone

U2 - 10.1371/journal.pone.0119460

DO - 10.1371/journal.pone.0119460

M3 - Article

VL - 10

SP - 1

EP - 11

JO - PLOS One

T2 - PLOS One

JF - PLOS One

SN - 1932-6203

IS - 3

M1 - e0119460

ER -