Facial metrics generated from manually and automatically placed image landmarks are highly correlated

Abstract

Research on social judgments of faces often investigates relationships between measures of face shape taken from images (facial metrics), and either perceptual ratings of the faces on various traits (e.g., attractiveness) or characteristics of the photographed individual (e.g., their health). A barrier to carrying out this research using large numbers of face images is the time it takes to manually position the landmarks from which these facial metrics are derived. Although research in face recognition has led to the development of algorithms that can automatically position landmarks on face images, the utility of such methods for deriving facial metrics commonly used in research on social judgments of faces has not yet been established. Thus, across two studies, we investigated the correlations between four facial metrics commonly used in social perception research (sexual dimorphism, distinctiveness, bilateral asymmetry, and facial width to height ratio) when measured from manually and automatically placed landmarks. In the first study, in two independent sets of open access face images, we found that facial metrics derived from manually and automatically placed landmarks were typically highly correlated, in both raw and Procrustes-fitted representations. In study two, we investigated the potential for automatic landmark placement to differ between White and East Asian faces. We found that two metrics, facial width to height ratio and sexual dimorphism, were better approximated by automatic landmarks in East Asian faces. However, this difference was small, and easily corrected with outlier detection. These data validate the use of automatically placed landmarks for calculating facial metrics to use in VALIDATING AUTOMATIC FACIAL LANDMARKS 3 research on social judgments of faces, but we urge caution in their use. We also provide a tutorial for the automatic placement of landmarks on face images.

Facial width‐to‐height ratio predicts fighting success: A direct replication and extension of Zilioli et al. (2014)

“…(2014) using a statistically well-powered sample of 520 UFC fighters using computer-automated fWHR measurements. Recent research suggests an advantage, when using large datasets, in employing anthropometric measurements generated automatically using programmed algorithms (Jones et al, 2021). Study 1 also extended Dixson et al, 2018;Lane & Briffa, 2020).…”

“…In Study 1, we aimed to replicate the significant associations of Zilioli et al (2014) using a statistically well‐powered sample of 520 UFC fighters using computer‐automated fWHR measurements. Recent research suggests an advantage, when using large datasets, in employing anthropometric measurements generated automatically using programmed algorithms (Jones et al, 2021). Study 1 also extended Zilioli et al (2014) by examining whether a suite underlying components associated RHP were also positively associated with men's fWHR: physical aggression, blunt‐force trauma resistance, and/or force output.…”

“…Consistent with other research (Kosinski, 2017), the present work also showed some discrepancies between automatic and manual measurements. Automatic measurements are definitely invaluable for their speed in large samples (Jones et al, 2021) but some caution should be exercised when using automatic calculators that do not allow for the manual adjustment of misaligned landmarks (de Kok, 2017). Future research could employ automatic measurements that can be manually realigned to balance speed and accuracy (e.g., Webmorph).…”

A Cautionary Note on Predicting Social Judgments from Faces with Deep Neural Networks

“…In our present study, given the large number of faces we used, we aimed to generate a subset of those physical and geometric features that could be automatically measured, but were still easily interpretable. A recent study showed that automatically measured physical and geometric features are highly correlated with those that are manually measured (Jones et al, 2021 ). Here, to automatically measure physical and geometric features, we used a pre-trained model of facial landmark detection implemented in the dlib C + + library to estimate the location of 68 key points on each face image.…”

Face Templates for the Chicago Face Database

“…Either the template can be automatically placed by software or the template can be hand-placed. Computer-generated templates are often used by computer scientists (Baddar et al, 2016;Juhong & Pintavirooj, 2017) and have been used in psychological research as well (Jones et al, 2021). Dlib is one such machine learning toolkit (King, 2009) that can be used in conjunction with other python packages to template faces.…”