A study on the discriminability of facs from spontaneous facial expressions

This paper investigates the discriminative capabilities of facial action units (AUs) exhibited by an individual while performing a task on a tablet computer in a semi-unconstrained environment. To that end, AUs are measured on a frame-by-frame basis from videos of 96 different subjects participating in a game-show-like quiz game that included a prize incentive. We propose a method that leverages the activation characteristics, as well as the temporal dynamics of facial behavior. In order to demonstrate the discriminative capabilities of the proposed approach, we perform identity matching across all subject pairs. Overall, the rank-1 matching performance of our algorithm ranges from 55% and up to 85%, on scenarios where the emotional disparity between the reference and query samples is largest and smallest, respectively. We believe these results represent a significant improvement relative to existing work relying on the use of AUs for human identification, in particular because the experimental settings guarantee that the facial expressions involved are spontaneous.

[1]  Ralph Gross,et al.  Individual differences in facial expression: stability over time, relation to self-reported emotion, and ability to inform person identification , 2002, Proceedings. Fourth IEEE International Conference on Multimodal Interfaces.

[2]  M. den Uyl,et al.  The FaceReader: Online facial expression recognition , 2006 .

[3]  Donald J. Berndt,et al.  Using Dynamic Time Warping to Find Patterns in Time Series , 1994, KDD Workshop.

[4]  Tom Hintz,et al.  An evaluation of bi-modal facial appearance+facial expression face biometrics , 2008, 2008 19th International Conference on Pattern Recognition.

[5]  P. Ekman,et al.  Facial expression and the affective component of cynical hostility in male coronary heart disease patients. , 1998, Health psychology : official journal of the Division of Health Psychology, American Psychological Association.

[6]  Tom Hintz,et al.  Facial behavior as behavior biometric? an empirical study , 2007, 2007 IEEE International Conference on Systems, Man and Cybernetics.

[7]  Venu Govindaraju,et al.  Facial Expression Biometrics Using Tracker Displacement Features , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[8]  Venu Govindaraju,et al.  Facial behavior as a soft biometric , 2012, 2012 5th IAPR International Conference on Biometrics (ICB).

[9]  Sung-Hyuk Cha.  Comprehensive Survey on Distance/Similarity Measures between Probability Density Functions , 2007 .

[10]  Jeffrey F. Cohn,et al.  Dynamics of facial expression: normative characteristics and individual differences , 2001, IEEE International Conference on Multimedia and Expo, 2001. ICME 2001..