Skip to main content

Human-computer interaction in face matching

Fysh, Matthew C., Bindemann, Markus (2018) Human-computer interaction in face matching. Cognitive Science, 42 (5). pp. 1714-1732. ISSN 0364-0213. (doi:10.1111/cogs.12633)

PDF - Author's Accepted Manuscript
Download (689kB) Preview
[img]
Preview
Official URL
https://doi.org/10.1111/cogs.12633

Abstract

Automatic facial recognition is becoming increasingly ubiquitous in security contexts such as passport control. Currently, Automated Border Crossing (ABC) systems in the United Kingdom (UK) and the European Union (EU) require supervision from a human operator who validates correct identity judgements and overrules incorrect decisions. As the accuracy of this human-computer interaction is unknown, this research investigated how human validation is impacted by a priori face-matching decisions such as those made by automated face recognition software. Observers matched pairs of faces that were already labelled onscreen as depicting the same identity or two different identities. The majority of these labels provided information that was consistent with the stimuli presented, but some were also inconsistent or provided ‘unresolved’ information. Across three experiments, accuracy consistently deteriorated on trials that were inconsistently labelled, indicating that observers’ face-matching decisions are biased by external information such as that provided by ABCs.

Item Type: Article
DOI/Identification number: 10.1111/cogs.12633
Uncontrolled keywords: face matching; face processing; human-computer interaction; passport control; response bias
Subjects: B Philosophy. Psychology. Religion > BF Psychology
H Social Sciences
Divisions: Faculties > Social Sciences > School of Psychology > Cognitive Psychology
Depositing User: Markus Bindemann
Date Deposited: 11 Sep 2018 09:51 UTC
Last Modified: 25 Jul 2019 10:24 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/69051 (The current URI for this page, for reference purposes)
  • Depositors only (login required):

Downloads

Downloads per month over past year