Evolutionary Computation for Modelling Social Traits in Realistic Looking Synthetic Faces

Abstract

Human faces play a central role in our lives. Thanks to our behavioural capacity to perceive faces, how a face looks in a painting, a movie, or an advertisement can dramatically influence what we feel about them and what emotions are elicited. Facial information is processed by our brain in such a way that we immediately make judgements like attractiveness or masculinity or interpret personality traits or moods of other people. Due to the importance of appearance-driven judgements of faces, this has become a major focus not only for psychological research, but for neuroscientists, artists, engineers, and software developers. New technologies are now able to create realistic looking synthetic faces that are used in arts, online activities, advertisement, or movies. However, there is not a method to generate virtual faces that convey the desired sensations to the observers. In this work, we present a genetic algorithm based procedure to create realistic faces combining facial features in the adequate relative positions. A model of how observers will perceive a face based on its features’ appearances and relative positions was developed and used as the fitness function of the algorithm. The model is able to predict 15 facial social traits related to aesthetic, moods, and personality. The proposed procedure was validated comparing its results with the opinion of human observers. This procedure is useful not only for creating characters with artistic purposes, but also for online activities, advertising, surgery, or criminology.

Applying Noise‐Based Reverse Correlation to Relate Consumer Perception to Product Complex Form Features

“…When we see a face for the first time, we infer the personality traits of that person by matching the visual input to our mental prototypes of faces with different attributes. From the result of this match, we infer the personality traits of the owner of the face [38], making attributions such as trustworthiness or dominance [41][42][43][44][45][46]. NBRC methods produce relevant CIs displaying the image that the participants use as a referent to evaluate the required judgement, referred to as "prototypical image" [33].…”

Psychologically Valid Social Face Features for Virtual Agents

“…Yet, identifying what specific face features drive these judgments is challenging because the face is a highly complex information space of multivariate 3D shape and complexion [8]. Most work is limited to only on a few specific features such as face width e.g., [4] and existing modeling solutions are often not suited to explore the high-dimensional space of the face [6,8]. This in turn has restricted the generative capacity of virtual agents to display realistic and psychologically impactful face signals, thus necessitating the costly hand-crafting of faces (e.g., [2]) that have low variability [10], which ultimately impacts the effectiveness of human-agent interactions.…”