Face Modeling

Together with my collaborators at the Computer Science Department I developed a method to systematically model perceived personality in faces and to apply these personality models to portraits with natural-looking results. In a first step, a face in a 2D photograph is actively reconstructed in an analysis-by-synthesis approach by linearly combining the 3D scans the Basel Face Model is built upon (fitting and image analysis). In a second step this reconstructed face is systematically modeled in order to appear more or less extreme regarding various personality dimensions (e.g., the Big Five or the Big Two personality dimensions; modeling). In a final step, the resulting face is rendered back into the original photograph (image synthesis).

Validation data attest to the method’s predictive validity. The modeled faces trigger the intended personality impressions. A database consisting of 40 different facial identities in different personalities (i.e., Big Two and Big Five) is freely available to researchers. More information can be found under resources.

Big 2 Agency

Big 2 Communion

Big 5 Agreeableness

Big 2 Conscientiousness

Big 2 Extroversion

Big 2 Neuroticism

Big 2 Openness

Key publications:

Walker, M. & Vetter, T. (2016). Changing the personality of a face: Perceived Big Two and Big Five personality factors modeled in real photographs. Journal of Personality and Social Psychology, 110(4), 609-624. http://dx.doi.org/10.1037/pspp0000064

Walker, M., Schoenborn, S., Greifeneder, R., & Vetter, T. (2018). The Basel Face Database: A validated set of photographs reflecting systematic differences in Big Two and Big Five personality dimensions. PloS one, 13(3). https://doi.org/10.1371/journal.pone.0193190