Measures and metrics for automatic emotion classification via FACET

For dynamic emotions to be modelled in a natural and convincing way, systems must rely on accurate affective analysis of facial expressions in the first place. The present work introduces two measures for evaluating automatic emotion classification performance. It further provides a systematic comparison between 14 databases of dynamic expressions. Machine analysis was conducted using the FACET system, with an algorithm calculating recognition sensitivity and confidence. Results revealed the proportion of facial stimuli that could be recognised by the machine algorithm above threshold evidence, showing significant differences in recognition performance between the databases.

[1]  Eva Krumhuber,et al.  Boxing the face: A comparison of dynamic facial databases used in facial analysis and animation , 2015, AVSP.

[2]  Lina I Skora,et al.  Perceptual Study on Facial Expressions , 2016 .

[3]  Genyue Fu,et al.  Differential emotion attribution to neutral faces of own and other races , 2017, Cognition & emotion.

[4]  A. Manstead,et al.  Effects of Dynamic Aspects of Facial Expressions: A Review , 2013 .

[5]  Lijun Yin,et al.  Static and dynamic 3D facial expression recognition: A comprehensive survey , 2012, Image Vis. Comput..

[6]  P. Petta,et al.  Computational models of emotion , 2010 .

[7]  Louis-Philippe Morency,et al.  Deep multimodal fusion for persuasiveness prediction , 2016, ICMI.

[8]  Lina I Skora,et al.  A Review of Dynamic Datasets for Facial Expression Research , 2017 .

[9]  Gwen Littlewort,et al.  The computer expression recognition toolbox (CERT) , 2011, Face and Gesture 2011.

[10]  P. Ekman An argument for basic emotions , 1992 .

[11]  Mario Del Líbano,et al.  What makes a smiling face look happy? Visual saliency, distinctiveness, and affect , 2018, Psychological research.

[12]  Jeffrey F. Cohn,et al.  Observer-based measurement of facial expression with the Facial Action Coding System. , 2007 .

[13]  P. Ekman,et al.  Facial action coding system , 2019 .

[14]  Zhihong Zeng,et al.  A Survey of Affect Recognition Methods: Audio, Visual, and Spontaneous Expressions , 2009, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Arvid Kappas,et al.  Nonverbal Behavior Online: A Focus on Interactions with and via Artificial Agents and Avatars , 2015 .