scholarly journals Low prevalence match and mismatch detection in simultaneous face matching: Influence of face recognition ability and feature focus guidance

2021 ◽  
Author(s):  
Josh P Davis ◽  
Callan Dray ◽  
Nikolay Petrov ◽  
Elena Belanova
Keyword(s):  
Face Recognition ◽  
Facial Feature ◽  
Identity Verification ◽  
Theoretical Understanding ◽  
Face Matching ◽  
Recognition Ability ◽  
Shift Effect ◽  
Low Prevalence ◽  
Typical Range ◽  
Unfamiliar Faces

Accurate simultaneous face matching of photos of unfamiliar faces to verify identity is key to many security and policing operations. However, matching is error-prone, especially when the prevalence of target items is low. In two experiments, the current research examined whether the use of internal or external facial feature guidance scales, and recruitment of participants with superior face recognition ability would reduce low prevalence effect impact. In Experiment 1, no information as to low prevalence of items was provided. Super-recognisers (n = 317) significantly outperformed typical-range-ability controls (n = 452), while internal feature guidance significantly enhanced accuracy in all prevalence conditions (10-90%, 50-50%, 90-10% mismatched-matched). However, an unexpected paradoxical prevalence criterion shift effect in controls meant accuracy tended to be highest in low prevalence conditions. In Experiment 2, top-end-of-typical range ability participants (n = 567) were informed as to low matched or mismatched item prevalence, and this time, the expected low prevalence effects were observed. No facial feature focus guidance effects were significant. The results enhance theoretical understanding of low prevalence effects while offering support for the deployment of super-recognisers, and the use of facial feature guidance scales in the identity verification workplace.

The Part-Whole Effect in super-recognisers

2019 ◽  
Author(s):  
Elena Belanova ◽  
Josh P Davis ◽  
Trevor Thompson
Keyword(s):  
Face Recognition ◽  
Opposite Direction ◽  
Holistic Processing ◽  
Recognition Ability ◽  
Performance Patterns ◽  
Optimal Viewing Position ◽  
Underlying Processes ◽  
Typical Range ◽  
Viewing Position

Face recognition skills are distributed on a continuum, with developmental prosopagnosics and super-recognisers at the bottom and top ends, respectively. Holistic processing propensity is associated with face recognition ability and may be impaired in some developmental prosopagnosics and enhanced in some super-recognisers. Across two experiments we compared holistic processing of 75 super-recognisers and 89 typical-range ability controls using The Part-Whole Effect (PWE) paradigm. A subgroup of super-recognisers demonstrated enhanced PWEs in the nose region, suggesting they integrate the nose into the holistic face percept more effectively than controls. Focussed processing of the nose region, an optimal viewing position to extract the holistic properties of faces, has previously been associated with superior face recognition, and this may partly explain the superiority of some super-recognisers. However, a few super-recognisers generated significant nose region performance patterns in an opposite direction across both experiments, suggesting their superiority is driven by alternative mechanisms. These results support proposals that super-recognition is associated with heterogeneous underlying processes.

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 The Goldsmiths Unfamiliar Face Memory and Before They Were Adult Tests

2020 ◽  
Author(s):  
Ashok Jansari ◽  
E. Green ◽  
Francesco Innocenti ◽  
Diego Nardi ◽  
Elena Belanova ◽  
...  
Keyword(s):  
Face Recognition ◽  
Holistic Processing ◽  
Face Identification ◽  
Facial Features ◽  
Face Memory ◽  
Face Matching ◽  
Recognition Ability ◽  
Unfamiliar Face ◽  
The Continuum

Unfamiliar face identification ability varies widely in the population. Those at the extreme top and bottom ends of the continuum have been labelled super-recognisers and prosopagnosics, respectively. Here we describe the development of two new tests - the Goldsmiths Unfamiliar Face Memory Test (GUFMT) and the Before They Were Adult Test (BTWA), that have been designed to measure different aspects of face identity ability across the spectrum. The GUFMT is a test of face memory, the BTWA a test of simultaneous adult-to-child face matching. Their designs draw on theories suggesting face identification is achieved by the recognition of facial features, the consistency across time of configurations between those features, and holistic processing of faces as a Gestalt. In four phases, participants (n = 16737), recruited using different methods, allowed evaluations to drive GUFMT development, the creation of likely population norms, as well as correlations with established face recognition tests. Recommendations for criteria for classification of super-recognition ability are also made.

Associations between self-reported and actual face recognition abilities are only evident in above- and below-average recognisers

2020 ◽  
Author(s):  
Alejandro Estudillo ◽  
Wong Hoo Keat
Keyword(s):  
Face Recognition ◽  
Individual Differences ◽  
Recognition Performance ◽  
Negative Association ◽  
Memory Test ◽  
Self Report ◽  
Recognition Ability ◽  
General Studies ◽  
Typical Range ◽  
Report Measure

The 20-Item Prosopagnosia Items (PI-20) was recently introduced as a self-report measure of face recognition abilities and as an instrument to help the diagnosis of prosopagnosia. In general, studies using this questionnaire have shown that observers have moderate to strong insights into their face recognition abilities. However, it remains unknown whether these insights are equivalent for the whole range of face recognition abilities. The present study investigates this issue using the Mandarin version of the PI-20 and the Cambridge Face Memory Test Chinese (CFMT-Chinese). Our results showed a moderate negative association between the PI-20 and the CFMT-Chinese. However, this association was driven by people with low and high face recognition ability, but absent in people within the typical range of face recognition performance. The implications of these results for the study of individual differences and the diagnosis of prosopagnosia are discussed.

scholarly journals EXPRESS: When Two Fields Collide: Identifying “Super-Recognisers” for Neuropsychological and Forensic Face Recognition Research

2021 ◽  
pp. 174702182110276
Author(s):  
Sarah Bate ◽  
Emma Portch ◽  
Natalie Mestry
Keyword(s):  
Face Recognition ◽  
Individual Differences ◽  
Facial Identity ◽  
Common Definition ◽  
Face Matching ◽  
Recognition Ability ◽  
The Face ◽  
The One ◽  
Definition Of ◽  
Matching Field

In the last decade, a novel individual differences approach has emerged across the face recognition literature. While the field has long been concerned with prosopagnosia (the inability to recognise facial identity), it has more recently become clear that there are vast differences in face recognition ability within the typical population. “Super-recognisers” are those individuals purported to reside at the very top of this spectrum. On the one hand, these people are of interest to cognitive neuropsychologists who are motivated to explore the commonality of the face recognition continuum, whereas researchers from the forensic face matching field evaluate the implementation of super-recognisers into real-world police and security settings. These two rather different approaches have led to discrepancies in the definition of super-recognisers, and perhaps more fundamentally, the approach to identifying them, resulting in a lack of consistency that prohibits theoretical progress. Here, we review the protocols used in published work to identify super-recognisers, and propose a common definition and screening recommendations that can be adhered to across fields.

scholarly journals The Twenty Item Prosopagnosia Index (PI20) provides meaningful evidence of face recognition impairment

2021 ◽  
Vol 8 (11) ◽  
Author(s):  
Maria Tsantani ◽  
Tim Vestner ◽  
Richard Cook
Keyword(s):  
Face Recognition ◽  
Recognition Accuracy ◽  
Self Report ◽  
Objective Measures ◽  
Recognition Ability ◽  
Considerable Debate ◽  
Computer Based ◽  
Typical Range ◽  
Insight Into ◽  
Intended Use

The Twenty Item Prosopagnosia Index (PI20) is a self-report questionnaire used for quantifying prosopagnosic traits. This scale is intended to help researchers identify cases of developmental prosopagnosia by providing standardized self-report evidence to complement diagnostic evidence obtained from objective computer-based tasks. In order to respond appropriately to items, prosopagnosics must have some insight that their face recognition is well below average, while non-prosopagnosics need to understand that their relative face recognition ability falls within the typical range. There has been considerable debate about whether participants have the necessary insight into their face recognition abilities to respond appropriately. In the present study, we sought to determine whether the PI20 provides meaningful evidence of face recognition impairment. In keeping with the intended use of the instrument, we used PI20 scores to identify two groups: high-PI20 scorers (those with self-reported face recognition difficulties) and low-PI20 scorers (those with no self-reported face recognition difficulties). We found that participant groups distinguished on the basis of PI20 scores clearly differed in terms of their mean performance on objective measures of face recognition ability. We also found that high-PI20 scorers were more likely to achieve levels of face recognition accuracy associated with developmental prosopagnosia.

scholarly journals Associations between self-reported and objective face recognition abilities are only evident in above- and below-average recognisers

PeerJ ◽  
2021 ◽  
Vol 9 ◽  
pp. e10629
Author(s):  
Alejandro J. Estudillo ◽  
Hoo Keat Wong
Keyword(s):  
Face Recognition ◽  
Individual Differences ◽  
Recognition Performance ◽  
Negative Association ◽  
Memory Test ◽  
Self Report ◽  
Recognition Ability ◽  
General Studies ◽  
Typical Range ◽  
Report Measure

The 20-Item Prosopagnosia Items (PI-20) was recently introduced as a self-report measure of face recognition abilities and as an instrument to help the diagnosis of prosopagnosia. In general, studies using this questionnaire have shown that observers have moderate to strong insights into their face recognition abilities. However, it remains unknown whether these insights are equivalent for the whole range of face recognition abilities. The present study investigates this issue using the Mandarin version of the PI-20 and the Cambridge Face Memory Test Chinese (CFMT-Chinese). Our results showed a moderate negative association between the PI-20 and the CFMT-Chinese. However, this association was driven by people with low and high face recognition ability, but absent in people within the typical range of face recognition performance. The implications of these results for the study of individual differences and the diagnosis of prosopagnosia are discussed.

A Study on Different Facial Features Extraction Technique

2016 ◽  
pp. 224-249
Author(s):  
Arnab Kumar Maji ◽  
Bandariakor Rymbai ◽  
Debdatta Kandar
Keyword(s):  
Face Recognition ◽  
Facial Feature ◽  
Biometric Identification ◽  
Facial Features ◽  
Human Face ◽  
Challenging Problem ◽  
Identity Verification ◽  
The Face ◽  
Changes Over Time ◽  
Natural Means

Facial recognition is the most natural means of biometric identification as it deals with the measurement of a biological relevance. Since, faces varies from each and every person, therefore, it can be used for security purpose. Face recognition is a very challenging problem, where the human face changes over time, as it depends on the pose, expression, occlusion, aging, etc. It can be used in many areas such as for surveillance purposes, security, general identity verification, criminal justice system, smart cards, etc. The most important part of the face recognition is the evaluation of facial features. With the help of facial feature, the system usually looks for the position of eyes, nose and mouth and distances between them can be detected and computed. This chapter will discuss some of the techniques that can be used to extract important facial features.

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.

Sign in / Sign up

Export Citation Format

Share Document