Portraits made to measure: Manipulating social judgments about individuals with a statistical face model

Abstract

The social judgments people make on the basis of the facial appearance of strangers strongly affect their behavior in different contexts. However, almost nothing is known about the physical information underlying these judgments. In this article, we present a new technology (a) to quantify the information in faces that is used for social judgments and (b) to manipulate the image of a human face in a way which is almost imperceptible but changes the personality traits ascribed to the depicted person. This method was developed in a high-dimensional face space by identifying vectors that capture maximum variability in judgments of personality traits. Our method of manipulating the salience of these vectors in faces was successfully transferred to novel photographs from an independent database. We evaluated this method by showing pairs of face photographs which differed only in the salience of one of six personality traits. Subjects were asked to decide which face was more extreme with respect to the trait in question. Results show that the image manipulation produced the intended attribution effect. All response accuracies were significantly above chance level. This approach to understanding and manipulating how a person is socially perceived could be useful in psychological research and could also be applied in advertising or the film industries.

Changing the personality of a face: Perceived Big Two and Big Five personality factors modeled in real photographs.

“…These approaches to modeling and visualizing personality in faces (Dotsch & Todorov, 2011;Mangini & Biederman, 2004;Oosterhof & Todorov, 2008;Todorov & Oosterhof, 2011;Todorov, Said, & Verosky, 2011;Walker, Jiang, Vetter, & Sczesny, 2011;Walker & Vetter, 2009) were conducted in a bottom-up way by starting with personality traits individuals spontaneously ascribe based on faces. Here we take a top-down approach by starting with the theoretically relevant and well-established Big Two and Big Five personality concepts and systematically modeling and visualizing the facial characteristics individuals use to make such judgments.…”

“…Any of the 200 face scans can now be manipulated with respect to this personality dimension by adding or subtracting multiples of ΔS, ΔC (Blanz & Vetter, 1999;Walker & Vetter, 2009). …”

Modelling perceptions of criminality and remorse from faces using a data-driven computational approach

“…Todorov, Dotsch and colleagues (2013) have further validated models of attractiveness, competence, extraversion, and likeability. Using pictures of real people, Walker and Vetter (2009) Walker & Vetter, 2016).…”

“…Different from earlier work that relied on a single data-driven approach to extract the information that people use when making social judgments about faces, we used two approaches -the one pioneered by Oosterhof and Todorov (2008; referred to as the Princeton approach here) and the one pioneered by Walker and Vetter (2009;referred to as the Basel approach here) -to PERCEIVED CRIMINALITY AND REMORSE 4 identify the looks of perceived criminality and remorse. The former approach has been described in detail by Todorov and colleagues (2008;; and the latter approach by Walker and Vetter (2009;2016).…”

Copula Eigenfaces with Attributes: Semiparametric Principal Component Analysis for a Combined Color, Shape and Attribute Model

“…The ability to synthesize random and natural instances is important when generating new face instances [13] and in face manipulation [23]. This is because human perception is very sensitive to unnatural variability in a face.…”