Humans constantly evaluate the personalities of other people using their faces. Facial trait judgments have been studied in the psychological field, and have been determined to influence important social outcomes of our lives, such as elections outcomes and social relationships. Recent work on textual descriptions of faces has shown that trait judgments are highly correlated. Further, behavioral studies suggest that two orthogonal dimensions, valence and dominance, can describe the basis of the human judgments from faces. In this work, we used a corpus of behavioral data of judgments on different trait dimensions to automatically learn a trait predictor from facial images. We study whether trait evaluations performed by humans can be learned using machine learning classifiers, and used later in automatic evaluations of new facial images. The experiments performed using local point-based descriptors show promising results in the evaluation of the main traits.

This is a collaborative work with A.Todorov, from Department of Psychology, Princeton University, Princeton, New Jersey, United States of America,


This work was partially supported by MEC grants TIN2009-14404-C02-01 and CONSOLIDER-INGENIO 2010 (CSD2007-00018).


Rojas Q. M, Masip D, Todorov A, Vitria J (2011) Automatic Prediction of Facial Trait Judgments: Appearance vs. Structural Models. PLoS ONE 6(8): e23323. doi:10.1371/journal.pone.0023323

M.Rojas, D.Masip, A.Todorov, J.Vitrià, Automatic Point-based Facial Trait Judgments Evaluation, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2010.

Internet Media:

Newspapers and Journals:
TV & Radio Stations: