The Effect of Feedback on Face-Matching Accuracy

Understanding face matching

Many security settings rely on the identity matching of unfamiliar people, which has led this task to be studied extensively in Cognitive Psychology. In these experiments, observers typically decide whether pairs of faces depict one person (an identity match) or two different people (an identity mismatch). The visual similarity of the to-be-compared faces must play a primary role in how observers accurately resolve this task, but the nature of this similarity-accuracy relationship is unclear. The current study investigated the association between accuracy and facial similarity at the level of individual items (Experiments 1 and 2) and facial features (Experiments 3 and 4). All experiments demonstrate a strong link between similarity and matching accuracy, indicating that this forms the basis of identification decisions. At a feature level, however, similarity exhibited distinct relationships with match and mismatch accuracy. In matches, similarity information was generally shared across the features of a face pair under comparison, with greater similarity linked to higher accuracy. Conversely, features within mismatching face pairs exhibited greater variation in similarity information. This indicates that identity matches and mismatches are characterised by different similarity profiles, which present distinct challenges to the cognitive system. We propose that these identification decisions can be resolved through the accumulation of convergent featural information in matches and the evaluation of divergent featural information in mismatches.

Unfamiliar face matching ability predicts the slope of face learning

We provide the first examination of individual differences in the efficiency of face learning. Investigating individual differences in face learning can illuminate potential mechanisms and provide greater understanding of why certain individuals might be more efficient face learners. Participants completed two unfamiliar face matching tasks and a learning task in which learning was assessed after viewing 1, 3, 6, and 9 images of to-be-learned identities. Individual differences in the slope of face learning (i.e., increases in sensitivity to identity) were predicted by the ability to discriminate between matched (same-identity) vs. mismatched (different-identity) pairs of wholly unfamiliar faces. A Dual Process Signal Detection model showed that three parameters increased with learning: Familiarity (an unconscious type of memory that varies in strength), recollection-old (conscious recognition of a learned identity), and recollection-new (conscious/confident rejection of novel identities). Good (vs. poor) matchers had higher Recollection-Old scores throughout learning and showed a steeper increase in Recollection-New. We conclude that good matchers are better able to capitalize on exposure to within-person variability in appearance, an effect that is attributable to their conscious memory for both learned and novel faces. These results have applied implications and will inform contemporary and traditional models of face identification.

Stable individual differences in unfamiliar face identification: Evidence from simultaneous and sequential matching tasks

Matching identity in images of unfamiliar faces is difficult: Images of the same person can look different and images of different people can look similar. Recent studies have capitalized on individual differences in the ability to distinguish match (same ID) vs. mismatch (different IDs) face pairs to inform models of face recognition. We addressed two significant gaps in the literature by examining the stability of individual differences in both sensitivity to identity and response bias. In Study 1, 210 participants completed a battery of four tasks in each of two sessions separated by one week. Tasks varied in protocol (same/different, lineup, sorting) and stimulus characteristics (low vs. high within-person variability in appearance). In Study 2, 148 participants completed a battery of three tasks in a single session. Stimuli were presented simultaneously on some trials and sequentially on others, introducing short-term memory demands. Principal components analysis revealed two components that were stable across time and tasks: sensitivity to identity and bias. Analyses of response times suggest that individual differences in bias reflect decision-making processes. We discuss the implications of our findings in applied settings and for models of face recognition.

High-frequency transcranial random noise stimulation enhances unfamiliar face matching of high resolution and pixelated faces

Face identification is useful for social interactions and its impairment can lead to severe social and mental problems. This ability is also remarkably important in applied settings, including eyewitness identification and ID verification. Several studies have demonstrated the potential of Transcranial Random Noise Stimulation (tRNS) to enhance different cognitive skills. However, research has produced inconclusive results about the effectiveness of tRNS to improve face identification. The present study aims to further explore the effect of tRNS on face identification using an unfamiliar face matching task. Observers firstly received either high-frequency bilateral tRNS or sham stimulation for 20 min. The stimulation targeted occipitotemporal areas, which have been previously involved in face processing. In a subsequent stage, observers were asked to perform an unfamiliar face matching task consisting of unaltered and pixelated face pictures. Compared to the sham stimulation group, the high-frequency tRNS group showed better unfamiliar face matching performance with both unaltered and pixelated faces. Our results show that a single high-frequency tRNS session might suffice to improve face identification abilities. These results have important consequences for the treatment of face recognition disorders, and potential applications in those scenarios whereby the identification of faces is primordial.

Two face masks are better than one: congruency effects in face matching

Although the positive effects of congruency between stimuli are well replicated in face memory paradigms, mixed findings have been found in face matching. Due to the current COVID-19 pandemic, face masks are now very common during daily life outdoor activities. Thus, the present study aims to further explore congruency effects in matching faces partially occluded by surgical masks. Observers performed a face matching task consisting of pairs of faces presented in full view (i.e., full-view condition), pairs of faces in which only one of the faces had a mask (i.e., one-mask condition), and pairs of faces in which both faces had a mask (i.e., two-mask condition). Although face masks disrupted performance in identity match and identity mismatch trials, in match trials, we found better performance in the two-mask condition compared to the one-mask condition. This finding highlights the importance of congruency between stimuli on face matching when telling faces together.

Picture this: Photographers no better than controls for recognizing unfamiliar faces

With the exception of super recognizers and forensic examiners, people make a surprising number of errors when deciding whether photographs of unfamiliar faces belong to the same person or different people. Training protocols designed to improve professionals’ (e.g., passport officers) performance often include photography. We evaluated the influence of life-time photography experience on the ability to distinguish matched versus mismatched face pairs. Expert photographers were not more sensitive to identity than hobbyists or novices—despite specializing in human subjects; Hobbyists were more liberal (more same responses) than Experts. We conclude that photography experience is not a route to expertise.

The pairs training effect in unfamiliar face matching

A wealth of studies have shown that humans are remarkably poor at determining whether two face images show the same person or not (face matching). Given the prevalence of photo-ID, and the fact that people employed to check photo-ID are typically unfamiliar with the person pictured, there is a need to improve unfamiliar face matching accuracy. One method of improvement is to have participants complete the task in a pair, which results in subsequent improvements in the low performer (“the pairs training effect”). Here, we sought to replicate the original finding, to test the longevity of the pairs training effect, and to shed light on the potential underlying mechanisms. In two experiments, we replicated the pairs training effect and showed it is maintained after a delay (Experiment 1). We found no differences between high and low performers in confidence (Experiment 1) or response times (Experiment 2), and the content of the pairs’ discussions (Experiment 2) did not explain the results. The pairs training effect in unfamiliar face matching is robust, but the mechanisms underlying the effects remain as yet unexplained.

Masked face identification is improved by diagnostic feature training

To slow the spread of COVID-19, many people now wear face masks in public. Face masks impair our ability to identify faces, which can cause problems for professional staff who identify offenders or members of the public. Here, we investigate whether performance on a masked face matching task can be improved by training participants to compare diagnostic facial features (the ears and facial marks)—a validated training method that improves matching performance for unmasked faces. We show this brief diagnostic feature training, which takes less than two minutes to complete, improves matching performance for masked faces by approximately 5%. A control training course, which was unrelated to face identification, had no effect on matching performance. Our findings demonstrate that comparing the ears and facial marks is an effective means of improving face matching performance for masked faces. These findings have implications for professions that regularly perform face identification.

Neurocognitive effects of a training program for poor face recognizers using shape and texture caricatures: A pilot investigation

Recent research suggested disproportional usage of shape information by people with poor face recognition, although texture information appears to be more important for familiar face recognition. Here, we tested a training program with faces that were selectively caricatured in either shape or texture parameters. Forty-eight young adults with poor face recognition skills (1 SD below the mean in at least 2/3 face processing tests: CFMT, GFMT, BFFT) were pseudo-randomly assigned to either one of two training groups or a control group (n = 16 each). Training comprised six sessions over three weeks. Per session, participants studied ten unfamiliar facial identities whose shape or texture characteristics were caricatured. Before and after training (or waiting in the control group), all participants completed EEG experiments on face learning and famous face recognition, and behavioral face processing tests. Results showed small but specific training-induced improvements: Whereas shape training improved face matching (training tasks, and to some extent GFMT), texture training elicited marked improvements in face learning (CFMT). Moreover, for the texture training group the N170 ERP was enhanced for novel faces post-training, suggesting training-induced changes in early markers of face processing. Although further research is necessary, this suggests that parameter-specific caricature training is a promising way to improve performance in people with poor face recognition skills.

An international survey of applied face-matching training courses

Face matching decisions in applied settings are typically carried out by trained face-matching professionals, known as facial reviewers and facial examiners. Recent research has demonstrated that short professional face-matching training courses are limited in improving face-matching accuracy, however, despite the existence of high-level training guidelines produced by the practitioner community the content, duration and delivery of training for facial reviewers and facial examiners are not widely understood in the academic research community. The current study aimed to address this gap in the scientific literature to better understand how different agencies train facial reviewers and facial examiners, using results collected from an international survey. The survey included questions on the duration, delivery and content of an agencies face-matching training. 24 face-matching agencies from five continents took part in the survey. A quantitative analysis of the survey results revealed that at the group level facial examiners received longer durations of training, covering more topics than reviewers and more frequently included one-to-one mentoring. However, the survey revealed large differences in the duration, delivery methods and content of training by individual agencies at both the facial review and facial examiner level and low inclusion of evidence-based training practices. These results should help researchers to better understand the diversity in training practices and durations of training between different agencies and may help explain the individual differences observed in the performance of face matching professionals in the literature.

Surgical face masks impair human face matching performance for familiar and 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.

Differences between and within individuals, and subprocesses of face cognition: implications for theory, research and personnel selection

Recent investigations of individual differences have demonstrated striking variability in performance both within the same subprocess in face cognition (e.g. face perception), but also between two different subprocesses (i.e. face perception versus face recognition) that are assessed using different tasks (face matching versus face memory). Such differences between and within individuals between and within laboratory tests raise practical challenges. This applies in particular to the development of screening tests for the selection of personnel in real-world settings where faces are routinely processed, such as at passport control. The aim of this study, therefore, was to examine the performance profiles of individuals within and across two different subprocesses of face cognition: face perception and face recognition. To this end, 146 individuals completed four different tests of face matching-one novel tool for assessing proficiency in face perception, as well as three established measures-and two benchmark tests of face memory probing face recognition. In addition to correlational analyses, we further scrutinized individual performance profiles of the highest and lowest performing observers identified per test, as well as across all tests. Overall, a number of correlations emerged between tests. However, there was limited evidence at the individual level to suggest that high proficiency in one test generalized to other tests measuring the same subprocess, as well as those that measured a different subprocess. Beyond emphasizing the need to honour inter-individual differences through careful multivariate assessment in the laboratory, our findings have real-world implications: combinations of tests that most accurately map the task(s) and processes of interest are required for personnel selection.

You shall not pass: how facial variability and feedback affect the detection of low-prevalence fake IDs

In many real-world settings, individuals rarely present another person's ID, which increases the likelihood that a screener will fail to detect it. Three experiments examined how within-person variability (i.e., differences between two images of the same person) and feedback may have influenced criterion shifting, thought to be one of the sources of the low-prevalence effect (LPE). Participants made identity judgments of a target face and an ID under either high, medium, or low mismatch prevalence. Feedback appeared after every trial, only error trials, or no trials. Experiment 1 used two controlled images taken on the same day. Experiment 2 used two controlled images taken at least 6 months apart. Experiment 3 used one controlled and one ambient image taken at least 1 year apart. Importantly, receiver operating characteristic curves revealed that feedback and greater within-person variability exacerbated the LPE by affecting both criterion and discriminability. These results carry implications for many real-world settings, such as border crossings and airports, where identity screening plays a major role in securing public safety.

A grey area: how does image hue affect unfamiliar face matching?

The role of image colour in face identification has received little attention in research despite the importance of identifying people from photographs in identity documents (IDs). Here, in two experiments, we investigated whether colour congruency of two photographs, shown side by side, affects face-matching accuracy. Participants were presented with two images from the Models Face Matching Test (experiment 1) and a newly devised matching task incorporating female faces (experiment 2) and asked to decide whether they show the same person or two different people. The photographs were either both in colour, both in grayscale, or mixed (one in grayscale and one in colour). Participants were more likely to accept a pair of images as a "match", i.e. same person, in the mixed condition, regardless of whether the identity of the pair was the same or not. This demonstrates a clear shift in bias between "congruent" colour conditions and the mixed trials. In addition, there was a small decline in accuracy in the mixed condition, relative to when the images were presented in colour. Our study provides the first evidence that the hue of document photographs matters for face-matching performance. This finding has important implications for the design and regulation of photographic ID worldwide.

Use-inspired basic research on individual differences in face identification: implications for criminal investigation and security

This journal is dedicated to "use-inspired basic research" where a problem in the world shapes the hypotheses for study in the laboratory. This review considers the role of individual variation in face identification and the challenges and opportunities this presents in security and criminal investigations. We show how theoretical work conducted on individual variation in face identification has, in part, been stimulated by situations presented in the real world. In turn, we review the contribution of theoretical work on individual variation in face processing and how this may help shape the practical identification of faces in applied situations. We consider two cases in detail. The first case is that of security officers; gatekeepers who use facial ID to grant entry or deny access. One applied example, where much research has been conducted, is passport control officers who are asked to match a person in front of them to a photograph shown on their ID. What happens if they are poor at making such face matching decisions and can they be trained to improve their performance? Second, we outline the case of "super-recognisers", people who are excellent at face recognition. Here it is interesting to consider whether these individuals can be strategically allocated to security and criminal roles, to maximise the identification of suspects. We conclude that individual differences are one of the largest documented sources of error in face matching and face recognition but more work is needed to account for these differences within theoretical models of face processing.

Individual differences in eyewitness accuracy across multiple lineups of faces

Theories of face recognition in cognitive psychology stipulate that the hallmark of accurate identification is the ability to recognize a person consistently, across different encounters. In this study, we apply this reasoning to eyewitness identification by assessing the recognition of the same target person repeatedly, over six successive lineups. Such repeat identifications are challenging and can be performed only by a proportion of individuals, both when a target exhibits limited and more substantial variability in appearance across lineups (Experiments 1 and 2). The ability to do so correlates with individual differences in identification accuracy on two established tests of unfamiliar face recognition (Experiment 3). This indicates that most observers have limited facial representations of target persons in eyewitness scenarios, which do not allow for robust identification in most individuals, partly due to limitations in their ability to recognize unfamiliar faces. In turn, these findings suggest that consistency of responses across multiple lineups of faces could be applied to assess which individuals are accurate eyewitnesses.

Enhancement of face-sensitive ERPs in older adults induced by face recognition training

A common cognitive problem reported by older people is compromised face recognition, which is often paralleled by age-related changes in face-sensitive and memory-related components in event-related brain potentials (ERPs). We developed a new training using photorealistic caricatures based on evidence that caricatures are beneficial for people with compromised face processing. Twenty-four older participants (62-75 yrs, 13 female) completed 12 training sessions (3 per week, 60 min each) and 24 older participants (61-76 yrs, 12 female) acted as controls. Before and after training (or waiting), participants took part in a diagnostic test battery for face processing abilities, and in ERP experiments on face learning and recognition. Although performance improvements during the training provided little evidence for generalization to other face processing tasks, ERPs showed substantial training-related enhancements of face-sensitive ERPs. Specifically, we observed marked increases of the N170, P200 and N250 components, which may indicate training-induced enhancement of face detection and activation of identity-specific representations. Thus, neuronal correlates of face processing are plastic in older age, and can be modulated by caricature training.

Human-Computer Interaction in Face Matching

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 judgments and overrules incorrect decisions. As the accuracy of this human-computer interaction remains 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 labeled 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 labeled, indicating that observers' face-matching decisions are biased by external information such as that provided by ABCs.

Photo ID verification remains challenging despite years of practice

Background

Matching unfamiliar faces to photographic identification (ID) documents occurs across many domains, including financial transactions (e.g., mortgage documents), controlling the purchase of age-restricted goods (e.g., alcohol sales), and airport security. Laboratory research has repeatedly documented the fallibility of this process in novice observers, but little research has assessed individual differences based on occupational expertise (cf. White et al., PLoS One 9:e103510, 2014; White et al., Proceedings of the Royal Society B 282(1814):20151292, 2015). In the present study, over 800 professional notaries (who routinely verify identity prior to witnessing signatures on legal documents), 70 bank tellers, and 35 undergraduate students completed an online unfamiliar face-matching test. In this test, observers made match/nonmatch decisions to 30 face ID pairs (half of which were matches), with no time constraints and no trial-by-trial feedback.

Results

Results showed that all groups performed similarly, although age was negatively correlated with accuracy. Critically, weekly and yearly experience with unfamiliar face matching did not impact performance.

Conclusions

These results suggest that accumulated occupational experience has no bearing on unfamiliar face ID abilities and that cognitive declines associated with aging also manifest in unfamiliar face matching.

Smiles in face matching: Idiosyncratic information revealed through a smile improves unfamiliar face matching performance

Unfamiliar face matching is a surprisingly difficult task, yet we often rely on people's matching decisions in applied settings (e.g., border control). Most attempts to improve accuracy (including training and image manipulation) have had very limited success. In a series of studies, we demonstrate that using smiling rather than neutral pairs of images brings about significant improvements in face matching accuracy. This is true for both match and mismatch trials, implying that the information provided through a smile helps us detect images of the same identity as well as distinguishing between images of different identities. Study 1 compares matching performance when images in the face pair display either an open-mouth smile or a neutral expression. In Study 2, we add an intermediate level, closed-mouth smile, to identify the effect of teeth being exposed, and Study 3 explores face matching accuracy when only information about the lower part of the face is available. Results demonstrate that an open-mouth smile changes the face in an idiosyncratic way which aids face matching decisions. Such findings have practical implications for matching in the applied context where we typically use neutral images to represent ourselves in official documents.

Feature instructions improve face-matching accuracy

Identity comparisons of photographs of unfamiliar faces are prone to error but important for applied settings, such as person identification at passport control. Finding techniques to improve face-matching accuracy is therefore an important contemporary research topic. This study investigated whether matching accuracy can be improved by instruction to attend to specific facial features. Experiment 1 showed that instruction to attend to the eyebrows enhanced matching accuracy for optimized same-day same-race face pairs but not for other-race faces. By contrast, accuracy was unaffected by instruction to attend to the eyes, and declined with instruction to attend to ears. Experiment 2 replicated the eyebrow-instruction improvement with a different set of same-race faces, comprising both optimized same-day and more challenging different-day face pairs. These findings suggest that instruction to attend to specific features can enhance face-matching accuracy, but feature selection is crucial and generalization across face sets may be limited.

Effects of time pressure and time passage on face-matching accuracy

This study investigated the impact of time pressure on matching accuracy with face pairs that combined photographs from student ID cards with high-quality person portraits, and under conditions that provided infrequent identity mismatches. Time pressure was administered via two onscreen displays that observers could use to adjust the amount of time that was allocated to a given trial while completing a block of trials within a required timeframe. Under these conditions, observers matched faces under time pressure that varied from 10 to 2 s (Experiment 1) and 8 to 2 s (Experiment 2). An effect of time pressure was found in each experiment, whereby performance deteriorated under time targets of 4 s. Additionally, a match response bias emerged consistently across blocks, and indicated that separately to time pressure, performance also deteriorated due to time passage. These results therefore indicate that both time passage and pressure exert detrimental effects on face matching.

The Headscarf Effect Revisited: Further Evidence for a Culture-Based Internal Face Processing Advantage

Encoding the internal features of unfamiliar faces poses a perceptual challenge that occasionally results in face recognition errors. Extensive experience with faces framed by a headscarf may, however, enhance perceivers' ability to process internal facial information. To examine this claim empirically, participants in the United Arab Emirates and the United States of America completed a standard part-whole face recognition task. Accuracy on the task was examined using a 2 (perceiver culture: Emirati vs American) x 2 (face race: Arab vs white) x 2 (probe type: part vs whole) x 3 (probe feature: eyes vs nose vs mouth) mixed-measures analysis of variance. As predicted, Emiratis outperformed Americans on the administered task. Although their recognition advantage occurred regardless of probe type, it was most pronounced for Arab faces and for trials that captured the processing of nose or mouth information. The findings demonstrate that culture-based experiences hone perceivers' face processing skills.

Face Matching Impairment in Developmental Prosopagnosia

Developmental prosopagnosia (DP) is commonly referred to as ‘face blindness’, a term that implies a perceptual basis to the condition. However, DP presents as a deficit in face recognition and is diagnosed using memory-based tasks. Here, we test face identification ability in six people with DP, who are severely impaired on face memory tasks, using tasks that do not rely on memory. First, we compared DP to control participants on a standardized test of unfamiliar face matching using facial images taken on the same day and under standardized studio conditions ( Glasgow Face Matching Test; GFMT). Scores for DP participants did not differ from normative accuracy scores on the GFMT. Second, we tested face matching performance on a test created using images that were sourced from the Internet and so varied substantially due to changes in viewing conditions and in a person's appearance ( Local Heroes Test; LHT). DP participants showed significantly poorer matching accuracy on the LHT than control participants, for both unfamiliar and familiar face matching. Interestingly, this deficit is specific to ‘match’ trials, suggesting that people with DP may have particular difficulty in matching images of the same person that contain natural day-to-day variations in appearance. We discuss these results in the broader context of individual differences in face matching ability.

Matching Faces Against the Clock

This study examined the effect of time pressure on face-matching accuracy. Across two experiments, observers decided whether pairs of faces depict one person or different people. Time pressure was exerted via two additional displays, which were constantly updated to inform observers on whether they were on track to meet or miss a time target. In this paradigm, faces were matched under increasing or decreasing (Experiment 1) and constant time pressure (Experiment 2), which varied from 10 to 2 seconds. In both experiments, time pressure reduced accuracy, but the point at which this declined varied from 8 to 2 seconds. A separate match response bias was found, which developed over the course of the experiments. These results indicate that both time pressure and the repetitive nature of face matching are detrimental to performance.

Face Recognition by Metropolitan Police Super-Recognisers

Face recognition is used to prove identity across a wide variety of settings. Despite this, research consistently shows that people are typically rather poor at matching faces to photos. Some professional groups, such as police and passport officers, have been shown to perform just as poorly as the general public on standard tests of face recognition. However, face recognition skills are subject to wide individual variation, with some people showing exceptional ability-a group that has come to be known as 'super-recognisers'. The Metropolitan Police Force (London) recruits 'super-recognisers' from within its ranks, for deployment on various identification tasks. Here we test four working super-recognisers from within this police force, and ask whether they are really able to perform at levels above control groups. We consistently find that the police 'super-recognisers' perform at well above normal levels on tests of unfamiliar and familiar face matching, with degraded as well as high quality images. Recruiting employees with high levels of skill in these areas, and allocating them to relevant tasks, is an efficient way to overcome some of the known difficulties associated with unfamiliar face recognition.

Solving the Border Control Problem: Evidence of Enhanced Face Matching in Individuals with Extraordinary Face Recognition Skills

Photographic identity documents (IDs) are commonly used despite clear evidence that unfamiliar face matching is a difficult and error-prone task. The current study set out to examine the performance of seven individuals with extraordinary face recognition memory, so called “super recognisers” (SRs), on two face matching tasks resembling border control identity checks. In Experiment 1, the SRs as a group outperformed control participants on the “Glasgow Face Matching Test”, and some case-by-case comparisons also reached significance. In Experiment 2, a perceptually difficult face matching task was used: the “Models Face Matching Test”. Once again, SRs outperformed controls both on group and mostly in case-by-case analyses. These findings suggest that SRs are considerably better at face matching than typical perceivers, and would make proficient personnel for border control agencies.

Face learning with multiple images leads to fast acquisition of familiarity for specific individuals

Matching unfamiliar faces is a difficult task. Here we ask whether it is possible to improve performance by providing multiple images to support matching. In two experiments we observe that accuracy improves as viewers are provided with additional images on which to base their match. This technique leads to fast learning of an individual, but the effect is identity-specific: Despite large improvements in viewers’ ability to match a particular person's face, these improvements do not generalize to other faces. Experiment 2 demonstrated that trial-by-trial feedback provided no additional benefits over the provision of multiple images. We discuss these results in terms of familiar and unfamiliar face processing and draw out some implications for training regimes.

Error Rates in Users of Automatic Face Recognition Software

In recent years, wide deployment of automatic face recognition systems has been accompanied by substantial gains in algorithm performance. However, benchmarking tests designed to evaluate these systems do not account for the errors of human operators, who are often an integral part of face recognition solutions in forensic and security settings. This causes a mismatch between evaluation tests and operational accuracy. We address this by measuring user performance in a face recognition system used to screen passport applications for identity fraud. Experiment 1 measured target detection accuracy in algorithm-generated 'candidate lists' selected from a large database of passport images. Accuracy was notably poorer than in previous studies of unfamiliar face matching: participants made over 50% errors for adult target faces, and over 60% when matching images of children. Experiment 2 then compared performance of student participants to trained passport officers-who use the system in their daily work-and found equivalent performance in these groups. Encouragingly, a group of highly trained and experienced "facial examiners" outperformed these groups by 20 percentage points. We conclude that human performance curtails accuracy of face recognition systems-potentially reducing benchmark estimates by 50% in operational settings. Mere practise does not attenuate these limits, but superior performance of trained examiners suggests that recruitment and selection of human operators, in combination with effective training and mentorship, can improve the operational accuracy of face recognition systems.

Face matching in a long task: enforced rest and desk-switching cannot maintain identification accuracy

In face matching, observers have to decide whether two photographs depict the same person or different people. This task is not only remarkably difficult but accuracy declines further during prolonged testing. The current study investigated whether this decline in long tasks can be eliminated with regular rest-breaks (Experiment 1) or room-switching (Experiment 2). Both experiments replicated the accuracy decline for long face-matching tasks and showed that this could not be eliminated with rest or room-switching. These findings suggest that person identification in applied settings, such as passport control, might be particularly error-prone due to the long and repetitive nature of the task. The experiments also show that it is difficult to counteract these problems.

Generalization across view in face memory and face matching

While a change in view is considered to be one of the most damaging manipulations for facial identification, this phenomenon has been measured traditionally with tasks that confound perceptual processes with recognition memory. This study explored facial identification with a pairwise matching task to determine whether view generalization is possible when memory factors are minimised. Experiment 1 showed that the detrimental view effect in recognition memory is attenuated in face matching. Moreover, analysis of individual differences revealed that some observers can identify faces across view with perfect accuracy. This was replicated in Experiment 2, which also showed that view generalization is unaffected when only the internal facial features are shown. These results indicate that the view effect in recognition memory does not arise from data limits, whereby faces contain insufficient visual information to allow identification across views. Instead, these findings point to resource limits, within observers, that hamper such person identification in recognition memory.

Unfamiliar face matching: Pairs out-perform individuals and provide a route to training

Matching unfamiliar faces is known to be difficult. Here, we ask whether performance can be improved by asking viewers to work in pairs, a manipulation known to increase accuracy for low-level visual discrimination tasks. Across four experiments we consistently find that face matching accuracy is higher for pairs of viewers than for individuals. This 'pairs advantage' is generally driven by adopting the response of the higher scoring partner. However, when the task becomes difficult, both partners' performance is improved by working in a pair. In two experiments, we find evidence that working in a pair can lead to subsequent improvements in individual performance, specifically for viewers whose accuracy is initially low. The pairs' technique therefore offers the opportunity for substantial improvements in face matching performance, along with an added training benefit.

Evaluating Training Methods for Facial Image Comparison: The Face Shape Strategy Does Not Work

Human performance on unfamiliar face matching is known to be highly error prone. However, in organisations where staff are required to perform this task as part of their daily work, attempts are often made to mitigate risk by providing training. Importantly, the methods used in these training courses have not been subjected to empirical validation. In this study we evaluate a common component of many training programmes which encourages viewers to classify face shape. Our results show very low agreement in face shape classification, both within and between participants, and across repeated presentations of a single image to a single participant. Furthermore, face shape classification training did not improve face matching accuracy, suggesting that the face shape strategy does not facilitate identification.