Face identification proficiency test designed using item response theory.

Measures of face-identification proficiency are essential to ensure accurate and consistent performance by professional forensic face examiners and others who perform face-identification tasks in applied scenarios. Current proficiency tests rely on static sets of stimulus items and so cannot be administered validly to the same individual multiple times. To create a proficiency test, a large number of items of "known" difficulty must be assembled. Multiple tests of equal difficulty can be constructed then using subsets of items. We introduce the Triad Identity Matching (TIM) test and evaluate it using item response theory (IRT). Participants view face-image "triads" (N = 225) (two images of one identity, one image of a different identity) and select the different identity. In Experiment 3, university students (N = 197) showed wide-ranging accuracy on the TIM test, and IRT modeling demonstrated that the TIM items span various difficulty levels. In Experiment 3, we used IRT-based item metrics to partition the test into subsets of specific difficulties. Simulations showed that subsets of the TIM items yielded reliable estimates of subject ability. In Experiments 3a and b, we found that the student-derived IRT model reliably evaluated the ability of non-student participants and that ability generalized across different test sessions. In Experiment 3c, we show that TIM test performance correlates with other common face-recognition tests. In summary, the TIM test provides a starting point for developing a framework that is flexible and calibrated to measure proficiency across various ability levels (e.g., professionals or populations with face-processing deficits).

Confidence judgments are associated with face identification accuracy: Findings from a confidence forced-choice task.

Confidence is assumed to be an indicator of identification accuracy in legal practices (e.g., forensic face examination). However, it is not clear whether people can evaluate the correctness of their face-identification decisions reliably using confidence reports. In the current experiment, confidence in the correctness of the perceptual decision was measured with a confidence forced-choice methodology: Upon completion of two perceptual face-identity matching trials, the participants were asked to compare the two decisions and to select the trial on which they felt more confident. On each face-identity matching trial, participants viewed three face images (two same-identity images, one different-identity image) and were instructed to select the image of the different identity. In order to measure the extent to which difficulty level informs confidence decisions, we selected face-image triads using item-difficulty estimates extracted from psychometric modeling applied in a prior study. The difference in difficulty between the paired face-image triads predicted the proportion of high-confidence judgments allocated to the easier trial of the pair. Consistent with the impact of difficulty monitoring on confidence judgments, performance was significantly more accurate on trials associated with higher confidence. Overall, the results suggested that people reliably evaluate the correctness of their perceptual face-identity matching decisions and use trial difficulty to evaluate confidence.

Face recognition accuracy of forensic examiners, superrecognizers, and face recognition algorithms.

Achieving the upper limits of face identification accuracy in forensic applications can minimize errors that have profound social and personal consequences. Although forensic examiners identify faces in these applications, systematic tests of their accuracy are rare. How can we achieve the most accurate face identification: using people and/or machines working alone or in collaboration? In a comprehensive comparison of face identification by humans and computers, we found that forensic facial examiners, facial reviewers, and superrecognizers were more accurate than fingerprint examiners and students on a challenging face identification test. Individual performance on the test varied widely. On the same test, four deep convolutional neural networks (DCNNs), developed between 2015 and 2017, identified faces within the range of human accuracy. Accuracy of the algorithms increased steadily over time, with the most recent DCNN scoring above the median of the forensic facial examiners. Using crowd-sourcing methods, we fused the judgments of multiple forensic facial examiners by averaging their rating-based identity judgments. Accuracy was substantially better for fused judgments than for individuals working alone. Fusion also served to stabilize performance, boosting the scores of lower-performing individuals and decreasing variability. Single forensic facial examiners fused with the best algorithm were more accurate than the combination of two examiners. Therefore, collaboration among humans and between humans and machines offers tangible benefits to face identification accuracy in important applications. These results offer an evidence-based roadmap for achieving the most accurate face identification possible.

The Influence of the Other-Race Effect on Susceptibility to Face Morphing Attacks.

Facial morphs created between two identities resemble both of the faces used to create the morph. Consequently, humans and machines are prone to mistake morphs made from two identities for either of the faces used to create the morph. This vulnerability has been exploited in "morph attacks" in security scenarios. Here, we asked whether the "other-race effect" (ORE)-the human advantage for identifying own- vs. other-race faces-exacerbates morph attack susceptibility for humans. We also asked whether face-identification performance in a deep convolutional neural network (DCNN) is affected by the race of morphed faces. Caucasian (CA) and East-Asian (EA) participants performed a face-identity matching task on pairs of CA and EA face images in two conditions. In the morph condition, different-identity pairs consisted of an image of identity "A" and a 50/50 morph between images of identity "A" and "B". In the baseline condition, morphs of different identities never appeared. As expected, morphs were identified mistakenly more often than original face images. Of primary interest, morph identification was substantially worse for cross-race faces than for own-race faces. Similar to humans, the DCNN performed more accurately for original face images than for morphed image pairs. Notably, the deep network proved substantially more accurate than humans in both cases. The results point to the possibility that DCNNs might be useful for improving face identification accuracy when morphed faces are presented. They also indicate the significance of the race of a face in morph attack susceptibility in applied settings.

Collaboration to improve cross-race face identification: Wisdom of the multi-racial crowd?

Face identification is particularly prone to error when individuals identify people of a race other than their own - a phenomenon known as the other-race effect (ORE). Here, we show that collaborative "wisdom-of-crowds" decision-making substantially improves face identification accuracy for own- and other-race faces over individuals working alone. In two online experiments, East Asian and White individuals recognized own- and other-race faces as individuals and as part of a collaborative dyad. Collaboration never proved more beneficial in a social setting than when individual identification decisions were combined computationally. The reliable benefit of non-social collaboration may stem from its ability to avoid the potential negative outcomes of group diversity such as conflict. Consistent with this benefit, the racial diversity of collaborators did not influence either general or race-specific face identification accuracy. Our findings suggest that collaboration between two individuals is a promising strategy for improving cross-race face identification that may translate effectively into forensic and eyewitness settings.

Wisdom of the social versus non-social crowd in face identification.

Face identification is more accurate when people collaborate in social dyads than when they work alone (Dowsett & Burton, 2015, Br. J. Psychol., 106, 433). Identification accuracy is also increased when the responses of two people are averaged for each item to create a 'non-social' dyad (White, Burton, Kemp, & Jenkins, 2013, Appl. Cogn. Psychol., 27, 769; White et al., 2015, Proc. R. Soc. B Biol. Sci., 282, 20151292). Does social collaboration add to the benefits of response averaging for face identification? We compared individuals, social dyads, and non-social dyads on an unfamiliar face identity-matching test. We also simulated non-social collaborations for larger groups of people. Individuals and social dyads judged whether face image pairs depicted the same- or different identities, responding on a 5-point certainty scale. Non-social dyads were constructed by averaging the responses of paired individuals. Both social and non-social dyads were more accurate than individuals. There was no advantage for social over non-social dyads. For larger non-social groups, performance peaked at near perfection with a crowd size of eight participants. We tested three computational models of social collaboration and found that social dyad performance was predicted by the decision of the more accurate partner. We conclude that social interaction does not bolster accuracy for unfamiliar face identity matching in dyads beyond what can be achieved by averaging judgements.