Face masks and fake masks: the effect of real and superimposed masks on face matching with super-recognisers, typical observers, and algorithms

Abstract

Mask wearing has been required in various settings since the outbreak of COVID-19, and research has shown that identity judgements are difficult for faces wearing masks. To date, however, the majority of experiments on face identification with masked faces tested humans and computer algorithms using images with superimposed masks rather than images of people wearing real face coverings. In three experiments we test humans (control participants and super-recognisers) and algorithms with images showing different types of face coverings. In all experiments we tested matching concealed or unconcealed faces to an unconcealed reference image, and we found a consistent decrease in face matching accuracy with masked compared to unconcealed faces. In Experiment 1, typical human observers were most accurate at face matching with unconcealed images, and poorer for three different types of superimposed mask conditions. In Experiment 2, we tested both typical observers and super-recognisers with superimposed and real face masks, and found that performance was poorer for real compared to superimposed masks. The same pattern was observed in Experiment 3 with algorithms. Our results highlight the importance of testing both humans and algorithms with real face masks, as using only superimposed masks may underestimate their detrimental effect on face identification.

Application of artificial intelligence to eyewitness identification

“…Ritchie et al, made this point, stating, It is worth noting that we do not suggest that human observers and algorithms are equivalent or are performing the task in the same way. (p. 10) The comparison between FRS and human performance, as demonstrated by Ritchie et al ( 2024 ), provides context regarding the usefulness of FRS—aligning with one of our study’s objectives. We employed a comparative psychology approach to understand human-AI capacities, similar to studies attempting to link animal cognition to AI to understand shortfalls of either system (Crosby et al, 2019 ).…”

“…It is important to highlight that we do not claim the FRS and participants use the same processes to complete the task, nor do we claim to have gained new insight into human memory based on the FRS results. While comparisons between AI and human performance have been conducted where both complete a matching task (e.g., Ritchie et al, 2024 ), it is unlikely that they use the same processes to complete the task. Ritchie et al, made this point, stating, It is worth noting that we do not suggest that human observers and algorithms are equivalent or are performing the task in the same way.…”