Improving Unfamiliar Face Matching by Masking the External Facial Features

Counter‐terrorism and crime prevention often depend on our ability to match images of unfamiliar faces. For example, when issuing passports, staff must establish an applicant's identity by comparing the submitted photograph witht those in the database of current passports to ensure that multiple documents are not issued to the same person under different names. Previous research has shown that this is a difficult and error prone task. We suggest that this ‘passport problem’ may be due to an over‐reliance on the appearance of external facial features that can be unreliable cues to identity. Compatible with this explanation, we demonstrate that in difficult trials involving a change of appearance or attempted fraud involving a similar looking foil, participants are better able to determine whether two images are of the same person when shown only the internal features of the faces rather than whole images. This discovery has significant practical implications and could form the basis of a procedure to improve the detection of identity fraud.Copyright © 2016 John Wiley & Sons, Ltd.     

The Kent Face Matching Test

This study presents the Kent Face Matching Test (KFMT), which comprises 200 same-identity and 20 different-identity pairs of unfamiliar faces. Each face pair consists of a photograph from a student ID card and a high-quality portrait that was taken at least three months later. The test is designed to complement existing resources for face-matching research, by providing a more ecologically valid stimulus set that captures the natural variability that can arise in a person's appearance over time. Two experiments are presented to demonstrate that the KFMT provides a challenging measure of face matching but correlates with established tests. Experiment 1 compares a short version of this test with the optimized Glasgow Face Matching Test (GFMT). In Experiment 2, a longer version of the KFMT, with infrequent identity mismatches, is correlated with performance on the Cambridge Face Memory Test (CFMT) and the Cambridge Face Perception Test (CFPT). The KFMT is freely available for use in face-matching research.     

The Glasgow Face Matching Test

We describe a new test for unfamiliar face matching, the Glasgow Face Matching Test (GFMT). Viewers are shown pairs of faces, photographed in full-face view but with different cameras, and are asked to make same/different judgments. The full version of the test comprises 168 face pairs, and we also describe a shortened version with 40 pairs. We provide normative data for these tests derived from large subject samples. We also describe associations between the GFMT and other tests of matching and memory. The new test correlates moderately with face memory but more strongly with object matching, a result that is consistent with previous research highlighting a link between object and face matching, specific to unfamiliar faces. The test is available free for scientific use.     

Caricature and face recognition

Although caricatures are often gross distortions of faces, they frequently appear to be super-portraits capable of eliciting recognition better than veridical depictions. This may occur because faces are encoded as distinctive feature deviations from a prototype. The exaggeration of these deviations in a caricature may enhance recognition because it emphasizes the features of the face that are encoded. In two experiments, we tested the superportrait hypothesis and the encoding-by-caricature hypothesis. In the first experiment, caricatures were recognized better than faces, and true caricatures of previously seen faces were recognized better than the faces from which the caricatures had been developed. In the second experiment, faces and their caricatures were tachistoscopically presented in a sequential same/different reaction time task. Subjects were slower to distinguish the stimuli when the face preceded its caricature, indicating that caricatures are more similar to the encoded representation of a face than are stimuli in which the distinctive features are deemphasized.     

Crowd Effects in Unfamiliar Face Matching

Psychological research shows that humans can not reliably match unfamiliar faces. This presents a practical problem, because identity verification processes in a variety of occupational settings depend on people to perform these tasks reliably. In this context, it is surprising that very few studies have attempted to improve human performance. Here, we investigate whether distributing face matching tasks across groups of individuals might help to solve this problem. Across four studies, we measure the accuracy of the ‘crowd’ on a standard test of face matching ability and find that aggregating individual responses produces substantial gains in matching accuracy. We discuss the practical implications of this result and also suggest ways in which this approach might be used to improve our understanding of face perception more generally. Copyright © 2013 John Wiley & Sons, Ltd.     

Motivational Incentives Improve Unfamiliar Face Matching Accuracy

Unfamiliar face matching is the process of simultaneously verifying the equivalence of two faces. Accuracy within this task is crucial given its importance and prevalence in security domains. However, research has consistently demonstrated that unfamiliar face matching is error prone, suggesting the need for improvement techniques. Motivational incentives have been shown to reliably enhance performance on a wide array of cognitive tasks. Therefore, the current study examined the effect of motivational incentives on unfamiliar face matching. Experiment 1 showed increased accuracy in mismatch trials with the addition of a motivational incentive. The improvement was associated with an increase in reaction time and bias towards making a mismatch response. This bias, however, did not produce a decrease in accuracy on match trials. Experiment 2 replicated this result with a more ecologically valid methodology. The results suggest motivational incentives to be effective at improving performance on mismatch trials, arguably the most important aspect of real‐world unfamiliar face matching. Copyright © 2013 John Wiley & Sons, Ltd.     

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.     

Disguising Superman: How Glasses Affect Unfamiliar Face Matching

Could a simple pair of glasses really fool us into thinking Superman and Clark Kent are two different people? Here, we investigated the perception of identity from face images with a task that relies on visual comparison rather than memory. Participants were presented with two images simultaneously and were asked whether the images depicted the same person or two different people. The image pairs showed neither image with glasses, both images with glasses, and ‘mixed’ pairs of one image with and one without glasses. Participants' accuracies, measured by both percentage correct and d′ sensitivity, were significantly lower for ‘mixed’ trials. Analysis of response bias showed that when only one face wore glasses, people tended to respond ‘different’. We demonstrate that glasses affect face matching ability using unconstrained images, and this has implications for both disguise research and authenticating identity in the real world. Copyright © 2016 John Wiley & Sons, Ltd.     

Effects of Image Preprocessing on Face Matching and Recognition in Human Observers

In person identification, recognition failure due to variations of illumination is common. In this study, we employed image‐processing techniques to tackle this problem. Participants performed recognition and matching tasks where the face stimuli were either original images or computer‐processed images in which shading was weakened via a number of image‐processing techniques. The results show that whereas recognition accuracy in a memory task was unaffected, some of the techniques significantly improved the identification performance in a face‐matching task. We conclude that relative to long‐term face memory, face matching is more susceptible to discrepancy of shading in different images of a face. Reducing the discrepancy by certain preprocessing techniques can facilitate person identification when original face images contain large illumination differences. Copyright © 2013 John Wiley & Sons, Ltd.     

Non-Violent Survival Strategies in the Face of Intimate Partner Violence and Economic Discrimination

Intimate partner violence (IPV) theory often locates violence equitably between women and men. Women, however, sustain greater degrees of injury than men and often use violence as a measure of protection rather than as an act of aggression. Yet measures of protection must be viewed in multiple contexts. In this case, the context is poverty, which reveals that violence by women in response to IPV is not the only way that women deal with the violence in their lives. This article explicates four strategies that battered women in poverty deploy in their protective trajectory and highlight alternative resistance strategies women use to overcome multiple structural barriers.     

The Effect of Image Pixelation on Unfamiliar‐Face Matching

Low‐resolution, pixelated images from closed‐circuit television (CCTV) can be used to compare the perpetrators of crime with high‐resolution photographs of potential suspects. The current study investigated the accuracy of person identification under these conditions, by comparing high‐resolution and pixelated photographs of unfamiliar faces in a series of matching tasks. Performance decreased gradually with different levels of pixelation and was close to chance with a horizontal image resolution of only 8 pixels per face (Experiment 1). Matching accuracy could be improved by reducing the size of pixelated faces (Experiment 2) or by varying the size of the to‐be‐compared‐with high‐resolution face image (Experiment 3). In addition, pixelation produced effects that appear to be separable from other factors that might affect matching performance, such as changes in face view (Experiment 4). These findings reaffirm that criminal identifications from CCTV must be treated with caution and provide some basic estimates for identification accuracy with different pixelation levels. This study also highlights potential methods for improving performance in this task. Copyright © 2013 John Wiley & Sons, Ltd.     

Caricature generalization benefits for faces learned with enhanced idiosyncratic shape or texture

Recent findings show benefits for learning and subsequent recognition of faces caricatured in shape or texture, but there is little evidence on whether this caricature learning advantage generalizes to recognition of veridical counterparts at test. Moreover, it has been reported that there is a relatively higher contribution of texture information, at the expense of shape information, for familiar compared to unfamiliar face recognition. The aim of this study was to examine whether veridical faces are recognized better when they were learned as caricatures compared to when they were learned as veridicals—what we call a caricature generalization benefit. Photorealistic facial stimuli derived from a 3-D camera system were caricatured selectively in either shape or texture by 50 %. Faces were learned across different images either as veridicals, shape caricatures, or texture caricatures. At test, all learned and novel faces were presented as previously unseen frontal veridicals, and participants performed an old–new task. We assessed accuracies, reaction times, and face-sensitive event-related potentials (ERPs). Faces learned as caricatures were recognized more accurately than faces learned as veridicals. At learning, N250 and LPC were largest for shape caricatures, suggesting encoding advantages of distinctive facial shape. At test, LPC was largest for faces that had been learned as texture caricatures, indicating the importance of texture for familiar face recognition. Overall, our findings demonstrate that caricature learning advantages can generalize to and, importantly, improve recognition of veridical versions of faces.     

Evolutionary Relevance and Experience Contribute to Face Discrimination in Infant Macaques (Macaca mulatta)

In human children and adults, familiar face types—typically own-age and own-species faces—are discriminated better than other face types; however, human infants do not appear to exhibit an own-age bias but instead better discriminate adult faces, which they see more often. There are two possible explanations for this pattern: Perceptual attunement predicts advantages in discrimination for the most experienced face types. Additionally or alternatively, there may be an experience-independent bias for infants to discriminate own-species faces, an adaptation for evolutionarily relevant faces. These possibilities have not been disentangled in studies thus far, and these studies did not control infants’ early experiences with faces. In the present study, we tested these predictions in infant macaques (Macaca mulatta) reared under controlled environments, not exposed to adult conspecifics. We measured newborns’ (15–25 days; n = 27) and 6- to 7-month-olds’ (n = 35) discrimination of human and macaque faces at 3 ages—young infants, old infants, and adults—in a visual paired comparison task. We found that 6- to 7-month-olds were the best at discriminating adult macaque faces; however, in the first few seconds of looking, tthey additionally discriminated familiar face types—same-aged peer and adult human faces—thereby highlighting the importance of experience with certain face categories. The present data suggest that macaque infants possess both experience-independent and experientially tuned face biases. In human infants, early face skills may likewise be driven by both experience and evolutionary relevance; future studies should consider both of these factors.     

Improving Identity Matching of Newly Encountered Faces: Effects of Multi-image Training

1. Download high-res image (107KB)
2. Download full-size image

     

Caricature effects, distinctiveness, and identification: testing the face-space framework

According to the multidimensional space framework, faces are represented as locations in a psychological face-space. Our aim was to test whether the locations of veridical, caricatured, and anticaricatured face stimuli in face-space, derived from multidimensional scaling analyses, could account for identification accuracy and distinctiveness ratings for these stimuli. Caricatures were identified more accurately and rated as more distinctive than veridical images, whereas anticaricatures were identified less accurately but were not significantly less distinctive than veridical images. In the face-space derived from multidimensional scaling, caricatures were further from the origin and less densely clustered than veridical images, whereas anticaricatures were closer to the origin and located in denser regions of the space. A quantitative model successfully predicted identification performance from the spatial locations of the stimuli. In general, the physically transformed faces were systematically mapped in the psychological space.     

Matching and maximizing with variable-time schedules.

Pigeons were offered choices between a variable-time schedule that arranged reinforcers throughout the session and a variable-time schedule that arranged reinforcers only when the pigeon was spending time on it. The subjects could maximize the overall rate of reinforcement in this situation by biasing their time allocation towards the latter schedule. This arrangement provides an alternative to concurrent variable-interval variable-ratio schedules for testing whether animals maximize overall rates or match relative rates, and has the advantage of being free of the asymmetrical response requirements present with those schedules. The results were contrary to those predicted by maximizing: The bias it predicts did not appear.