scholarly journals EXPRESS: Understanding the document bias in face matching

2021 ◽  
pp. 174702182110179
Author(s):  
Xinran Feng ◽  
Anthony Michael Burton
Keyword(s):  
Personal Information ◽  
Textual Information ◽  
Multiple Factors ◽  
Face Matching ◽  
Unfamiliar Faces ◽  
Complex Basis

Matching unfamiliar faces is a well-studied task, apparently capturing important everyday decisions such as ID checks. In typical lab studies participants make same/different judgements to pairs of faces, presented in isolation and without context. However, it has recently become clear that matching faces embedded in documents (e.g. passports and driving licences) induces a bias, resulting in elevated levels of ‘same person’ responses. While practically important, it remains unclear whether this bias arises due to expectations induced by the ID cards or interference between textual information and faces. Here we observe the same bias when faces are embedded in blank (i.e. non-authoritative) cards carrying basic personal information, but not when the same information is presented alongside a face without the card (Experiments 1 & 2). Cards bearing unreadable text (blurred or in an unfamiliar alphabet) do not induce the bias but those bearing arbitrary (non-biographical) words do (Experiments 3 and 4). The results suggest a complex basis for the effect, relying on multiple factors which happen to converge in photo-ID.

scholarly journals Unfamiliar Face Matching With Frontal and Profile Views

Perception ◽  
2018 ◽  
Vol 47 (4) ◽  
pp. 414-431 ◽  
Author(s):  
Robin S. S. Kramer ◽  
Michael G. Reynolds
Keyword(s):  
Real World ◽  
Sources Of Information ◽  
Matching Accuracy ◽  
Face Matching ◽  
Matching Test ◽  
Unfamiliar Face Matching ◽  
Unfamiliar Face ◽  
Unfamiliar Faces

Research has systematically examined how laboratory participants and real-world practitioners decide whether two face photographs show the same person or not using frontal images. In contrast, research has not examined face matching using profile images. In Experiment 1, we ask whether matching unfamiliar faces is easier with frontal compared with profile views. Participants completed the original, frontal version of the Glasgow Face Matching Test, and also an adapted version where all face pairs were presented in profile. There was no difference in performance across the two tasks, suggesting that both views were similarly useful for face matching. Experiments 2 and 3 examined whether matching unfamiliar faces is improved when both frontal and profile views are provided. We compared face matching accuracy when both a frontal and a profile image of each face were presented, with accuracy using each view alone. Surprisingly, we found no benefit when both views were presented together in either experiment. Overall, these results suggest that either frontal or profile views provide substantially overlapping information regarding identity or participants are unable to utilise both sources of information when making decisions. Each of these conclusions has important implications for face matching research and real-world identification development.

The Effect of Face Masks on Forensic Face Matching: An Individual Differences Study

2021 ◽  
Author(s):  
Alejandro Estudillo ◽  
Peter James Hills ◽  
Wong Hoo Keat
Keyword(s):  
Negative Impact ◽  
Face Mask ◽  
Public Spaces ◽  
Matching Task ◽  
Mask Condition ◽  
Full View ◽  
Face Matching ◽  
Face Experiment ◽  
Unfamiliar Faces ◽  
Practical Implications

In the forensic face matching task, observers are presented with two unfamiliar faces and must determine whether they depict the same identity. Due to the Covid-19 pandemic, some governmental authorities require the use of face masks in public spaces. However, face masks impair face identification by disrupting holistic processing of faces. The present study explores the effect of face masks on forensic face matching. Compared to a full-view condition, performance decreased when a face mask was superimposed on one face (Experiment 1) and both faces (Experiment 2) of a pair. Although a positive correlation between the full-view and the mask conditions was found, high proficiency in the full-view condition did not always generalize to the mask condition. Additionally, the mask generally has a more negative impact in those participants with better performance in the full-view condition. The theoretical and practical implications of these findings are discussed.

scholarly journals Surgical face masks impair human face matching performance for familiar and unfamiliar faces

2020 ◽  
Vol 5 (1) ◽  
Author(s):  
Daniel J. Carragher ◽  
Peter J. B. Hancock
Keyword(s):  
Face Recognition ◽  
Recognition System ◽  
Human Face ◽  
Face Matching ◽  
Face Recognition System ◽  
Surgical Masks ◽  
The Face ◽  
Matching Performance ◽  
Recognition Systems ◽  
Unfamiliar Faces

AbstractIn response to the COVID-19 pandemic, many governments around the world now recommend, or require, that their citizens cover the lower half of their face in public. Consequently, many people now wear surgical face masks in public. We investigated whether surgical face masks affected the performance of human observers, and a state-of-the-art face recognition system, on tasks of perceptual face matching. Participants judged whether two simultaneously presented face photographs showed the same person or two different people. We superimposed images of surgical masks over the faces, creating three different mask conditions: control (no masks), mixed (one face wearing a mask), and masked (both faces wearing masks). We found that surgical face masks have a large detrimental effect on human face matching performance, and that the degree of impairment is the same regardless of whether one or both faces in each pair are masked. Surprisingly, this impairment is similar in size for both familiar and unfamiliar faces. When matching masked faces, human observers are biased to reject unfamiliar faces as “mismatches” and to accept familiar faces as “matches”. Finally, the face recognition system showed very high classification accuracy for control and masked stimuli, even though it had not been trained to recognise masked faces. However, accuracy fell markedly when one face was masked and the other was not. Our findings demonstrate that surgical face masks impair the ability of humans, and naïve face recognition systems, to perform perceptual face matching tasks. Identification decisions for masked faces should be treated with caution.

scholarly journals About Face: Matching Unfamiliar Faces Across Rotations of View and Lighting

i-Perception ◽  
2017 ◽  
Vol 8 (6) ◽  
pp. 204166951774422 ◽  
Author(s):  
Simone Favelle ◽  
Harold Hill ◽  
Peter Claes
Keyword(s):  
Face Matching ◽  
Unfamiliar Faces

scholarly journals Feature-by-feature comparison and holistic processing in unfamiliar face matching

PeerJ ◽  
2018 ◽  
Vol 6 ◽  
pp. e4437 ◽  
Author(s):  
Ahmed M. Megreya
Keyword(s):  
Research Topic ◽  
Holistic Processing ◽  
Matching Accuracy ◽  
New Methods ◽  
Verbal Instructions ◽  
Face Matching ◽  
Unfamiliar Face Matching ◽  
Unfamiliar Face ◽  
Unfamiliar Faces ◽  
Passport Control

Identity comparisons of photographs of unfamiliar faces are prone to error but imperative for security settings, such as the verification of face identities at passport control. Therefore, finding techniques to improve face-matching accuracy is an important contemporary research topic. This study investigates whether matching accuracy can be enhanced by verbal instructions that address feature comparisons or holistic processing. Findings demonstrate that feature-by-feature comparison strategy had no effect on face matching. In contrast, verbal instructions focused on holistic processing made face matching faster, but they impaired accuracy. Given the recent evidence for the heredity of face perception and the previously reported small or no improvements of face-matching ability, it seems reasonable to suggest that improving unfamiliar face matching is not an easy task, but it is presumably worthwhile to explore new methods for improvement nonetheless.

Exploring Levels of Face Familiarity by Using an Indirect Face-Matching Measure

Perception ◽  
10.1068/p3335 ◽  
2002 ◽  
Vol 31 (8) ◽  
pp. 985-994 ◽  
Author(s):  
Ruth Clutterbuck ◽  
Robert A Johnston
Keyword(s):  
Face Processing ◽  
Matching Task ◽  
Indirect Measure ◽  
Face Matching ◽  
External Feature ◽  
Unfamiliar Face ◽  
Matching Performance ◽  
Unfamiliar Faces

An experiment is reported in which participants matched complete images of unfamiliar, moderately familiar, and highly familiar faces with simultaneously presented images of internal and external features. Participants had to decide if the two images depicted same or different individuals. Matches to internal features were made faster to highly familiar faces than both to moderately familiar and to unfamiliar faces, and matches to moderately familiar faces were made faster than to unfamiliar faces. For external feature matches, this advantage was only found for “different” decision matches to highly familiar faces compared to unfamiliar faces. The results indicate that the differences in familiar and unfamiliar face processing are not the result of all-or-none effects, but seem to have a graded impact on matching performance. These findings extend the earlier work of Young et al (1985 Perception14 737–746), and we discuss the possibility of using the matching task as an indirect measure of face familiarity.

Steps Towards a Cognitive Theory of Unfamiliar Face Matching

2021 ◽  
pp. 38-61
Author(s):  
Markus Bindemann ◽  
A. Mike Burton
Keyword(s):  
Cognitive Theory ◽  
Theory Development ◽  
Cognitive Mechanisms ◽  
Person Identification ◽  
Face Matching ◽  
Unfamiliar Face Matching ◽  
The Face ◽  
Unfamiliar Face ◽  
Unfamiliar Faces

The visual comparison of unfamiliar faces—or ‘face matching’—is utilized widely for person identification in applied settings and has generated substantial research interest in psychology, but a cognitive theory to explain how observers perform this task does not exist. This chapter outlines issues of importance to support the development of a cognitive account of unfamiliar face matching. Characteristics of the face, such as within-person variability and between-person similarity in appearance, are considered as the visual input upon which identification must build. The cognitive mechanisms that observers may bring to bear on faces during identity comparison are analysed, focusing on attention, perception, evaluation, and decision processes, including sources of individual differences at each of these stages. Finally, the role of different experimental and occupational contexts in understanding face matching and for optimizing theory development is discussed.

scholarly journals Surgical face masks impair human face matching performance for familiar and unfamiliar faces

2020 ◽  
Author(s):  
Daniel James Carragher ◽  
Peter Hancock
Keyword(s):  
Face Recognition ◽  
Recognition System ◽  
Human Face ◽  
Face Matching ◽  
Face Recognition System ◽  
Surgical Masks ◽  
The Face ◽  
Matching Performance ◽  
Recognition Systems ◽  
Unfamiliar Faces

In response to the COVID-19 pandemic, many governments around the world now recommend, or require, that their citizens cover the lower half of their face in public. Consequently, many people now wear surgical face masks in public. We investigated whether surgical face masks affected the performance of human observers, and a state-of-the-art face recognition system, on tasks of perceptual face matching. Participants judged whether two simultaneously presented face photographs showed the same person or two different people. We superimposed images of surgical masks over the faces, creating three different mask conditions: control (no masks), mixed (one face wearing a mask), and masked (both faces wearing masks). We found that surgical face masks have a large detrimental effect on human face matching performance, and that the degree of impairment is the same regardless of whether one or both faces in each pair are masked. Surprisingly, this impairment is similar in size for both familiar and unfamiliar faces. When matching masked faces, human observers are biased to reject unfamiliar faces as “mismatches” and to accept familiar faces as “matches”. Finally, the face recognition system showed very high classification accuracy for control and masked stimuli, even though it had not been trained to recognise masked faces. However, accuracy fell markedly when one face was masked and the other was not. Our findings demonstrate that surgical face masks impair the ability of humans, and naïve face recognition systems, to perform perceptual face matching tasks. Identification decisions for masked faces should be treated with caution.

scholarly journals Image Variability and Face Matching

2021 ◽  
Author(s):  
Taylor Diarmuid Gogan ◽  
Jennifer L Beaudry ◽  
Julian Oldmeadow
Keyword(s):  
Matching Task ◽  
Lower Face ◽  
Face Images ◽  
Face Matching ◽  
Total Data ◽  
Data Points ◽  
Matching Performance ◽  
Image Variability ◽  
Unfamiliar Faces

This study investigates whether variability in perceived trait judgements disrupts our ability to match unfamiliar faces. In this preregistered study, 174 participants completed a face matching task where they were asked to indicate whether two face images belonged to the same person or different people (17,748 total data points). Participants completed 51 match trials consisting of images of the same person that differed substantially on one trait (either trustworthiness, dominance, or attractiveness) with minimal differences in the alternate traits. Participants also completed 51 mismatch trials which contained two photos of similar-looking individuals. We hypothesised that participants would make more errors on match trials when images differed in terms of attractiveness ratings than those that differed on trustworthiness or dominance. Contrary to expectations, images that differed in terms of attractiveness were matched most accurately, and there was no relationship between the extent of attractiveness differences and accuracy. There was some evidence that differences in perceived dominance and, to a lesser extent, trustworthiness was associated with lower face matching performance. However, these relationships were not significant when alternate traits were accounted for. The findings of our study suggest that face matching performance is largely robust against variation in trait judgements. fi

Sign in / Sign up

Export Citation Format

Share Document