Detecting morphed passport photos: a training and individual differences approach

David J. Robertson, Andrew Mungall, Derrick G. Watson, Kimberley A. Wade, Sophie J. Nightengale, Stephen Butler

Research output: Contribution to journalArticle

Abstract

Our reliance on face photos for identity verification is at odds with extensive research which shows that matching pairs of unfamiliar faces is highly prone to error. This process can therefore be exploited by identity fraudsters seeking to deceive ID checkers (e.g., using a stolen passport which contains an image of a similar looking individual to deceive border control officials). In this study we build on previous work which sought to quantify the threat posed by a relatively new type of fraud: morphed passport photos. Participants were initially unaware of the presence of morphs in a series of face photo arrays and were simply asked to detect which images they thought had been digitally manipulated (i.e., “images that didn’t look quite right”). All participants then received basic information on morph fraud and rudimentary guidance on how to detect such images, followed by a morph detection training task (Training Group, n = 40), or a non-face control task (Guidance Group, n = 40). Participants also completed a post-guidance/training morph detection task and the Models Face Matching Test (MFMT). Our findings show that baseline morph detection rates were poor, that morph detection training significantly improved the identification of these images over and above basic guidance, and that accuracy in the mismatch condition of the MFMT correlated with morph detection ability. The results are discussed in relation to potential countermeasures for morph-based identity fraud.
LanguageEnglish
Pages1-11
Number of pages11
JournalCognitive Research: Principles and Implications
Volume3
Issue number27
DOIs
Publication statusPublished - 29 Jun 2018

Keywords

  • face morphs
  • identity fraud
  • identity verification
  • individual differences
  • super-recognisers
  • face matching
  • face recognition
  • passports
  • biometrics

Cite this

Robertson, David J. ; Mungall, Andrew ; Watson, Derrick G. ; Wade, Kimberley A. ; Nightengale, Sophie J. ; Butler, Stephen. / Detecting morphed passport photos : a training and individual differences approach. In: Cognitive Research: Principles and Implications. 2018 ; Vol. 3, No. 27. pp. 1-11.
@article{7c39da791bc641929c7cf57fec45ef5a,
title = "Detecting morphed passport photos: a training and individual differences approach",
abstract = "Our reliance on face photos for identity verification is at odds with extensive research which shows that matching pairs of unfamiliar faces is highly prone to error. This process can therefore be exploited by identity fraudsters seeking to deceive ID checkers (e.g., using a stolen passport which contains an image of a similar looking individual to deceive border control officials). In this study we build on previous work which sought to quantify the threat posed by a relatively new type of fraud: morphed passport photos. Participants were initially unaware of the presence of morphs in a series of face photo arrays and were simply asked to detect which images they thought had been digitally manipulated (i.e., “images that didn’t look quite right”). All participants then received basic information on morph fraud and rudimentary guidance on how to detect such images, followed by a morph detection training task (Training Group, n = 40), or a non-face control task (Guidance Group, n = 40). Participants also completed a post-guidance/training morph detection task and the Models Face Matching Test (MFMT). Our findings show that baseline morph detection rates were poor, that morph detection training significantly improved the identification of these images over and above basic guidance, and that accuracy in the mismatch condition of the MFMT correlated with morph detection ability. The results are discussed in relation to potential countermeasures for morph-based identity fraud.",
keywords = "face morphs, identity fraud, identity verification, individual differences, super-recognisers, face matching, face recognition, passports, biometrics",
author = "Robertson, {David J.} and Andrew Mungall and Watson, {Derrick G.} and Wade, {Kimberley A.} and Nightengale, {Sophie J.} and Stephen Butler",
year = "2018",
month = "6",
day = "29",
doi = "10.1186/s41235-018-0113-8",
language = "English",
volume = "3",
pages = "1--11",
journal = "Cognitive Research: Principles and Implications",
issn = "2365-7464",
publisher = "Springer-Verlag",
number = "27",

}

Detecting morphed passport photos : a training and individual differences approach. / Robertson, David J.; Mungall, Andrew; Watson, Derrick G.; Wade, Kimberley A.; Nightengale, Sophie J.; Butler, Stephen.

In: Cognitive Research: Principles and Implications, Vol. 3, No. 27, 29.06.2018, p. 1-11.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Detecting morphed passport photos

T2 - Cognitive Research: Principles and Implications

AU - Robertson, David J.

AU - Mungall, Andrew

AU - Watson, Derrick G.

AU - Wade, Kimberley A.

AU - Nightengale, Sophie J.

AU - Butler, Stephen

PY - 2018/6/29

Y1 - 2018/6/29

N2 - Our reliance on face photos for identity verification is at odds with extensive research which shows that matching pairs of unfamiliar faces is highly prone to error. This process can therefore be exploited by identity fraudsters seeking to deceive ID checkers (e.g., using a stolen passport which contains an image of a similar looking individual to deceive border control officials). In this study we build on previous work which sought to quantify the threat posed by a relatively new type of fraud: morphed passport photos. Participants were initially unaware of the presence of morphs in a series of face photo arrays and were simply asked to detect which images they thought had been digitally manipulated (i.e., “images that didn’t look quite right”). All participants then received basic information on morph fraud and rudimentary guidance on how to detect such images, followed by a morph detection training task (Training Group, n = 40), or a non-face control task (Guidance Group, n = 40). Participants also completed a post-guidance/training morph detection task and the Models Face Matching Test (MFMT). Our findings show that baseline morph detection rates were poor, that morph detection training significantly improved the identification of these images over and above basic guidance, and that accuracy in the mismatch condition of the MFMT correlated with morph detection ability. The results are discussed in relation to potential countermeasures for morph-based identity fraud.

AB - Our reliance on face photos for identity verification is at odds with extensive research which shows that matching pairs of unfamiliar faces is highly prone to error. This process can therefore be exploited by identity fraudsters seeking to deceive ID checkers (e.g., using a stolen passport which contains an image of a similar looking individual to deceive border control officials). In this study we build on previous work which sought to quantify the threat posed by a relatively new type of fraud: morphed passport photos. Participants were initially unaware of the presence of morphs in a series of face photo arrays and were simply asked to detect which images they thought had been digitally manipulated (i.e., “images that didn’t look quite right”). All participants then received basic information on morph fraud and rudimentary guidance on how to detect such images, followed by a morph detection training task (Training Group, n = 40), or a non-face control task (Guidance Group, n = 40). Participants also completed a post-guidance/training morph detection task and the Models Face Matching Test (MFMT). Our findings show that baseline morph detection rates were poor, that morph detection training significantly improved the identification of these images over and above basic guidance, and that accuracy in the mismatch condition of the MFMT correlated with morph detection ability. The results are discussed in relation to potential countermeasures for morph-based identity fraud.

KW - face morphs

KW - identity fraud

KW - identity verification

KW - individual differences

KW - super-recognisers

KW - face matching

KW - face recognition

KW - passports

KW - biometrics

U2 - 10.1186/s41235-018-0113-8

DO - 10.1186/s41235-018-0113-8

M3 - Article

VL - 3

SP - 1

EP - 11

JO - Cognitive Research: Principles and Implications

JF - Cognitive Research: Principles and Implications

SN - 2365-7464

IS - 27

ER -