Repository logo
 

Learning Bases of Activity for Facial Expression Recognition.

Accepted version
Peer-reviewed

Type

Article

Change log

Authors

Sariyanidi, Evangelos 
Cavallaro, Andrea 

Abstract

The extraction of descriptive features from sequences of faces is a fundamental problem in facial expression analysis. Facial expressions are represented by psychologists as a combination of elementary movements known as action units: each movement is localised and its intensity is specified with a score that is small when the movement is subtle and large when the movement is pronounced. Inspired by this approach, we propose a novel data-driven feature extraction framework that represents facial expression variations as a linear combination of localised basis functions, whose coefficients are proportional to movement intensity. We show that the linear basis functions required by this framework can be obtained by training a sparse linear model with Gabor phase shifts computed from facial videos. The proposed framework addresses generalisation issues that are not addressed by existing learnt representations, and achieves, with the same learning parameters, state-of-the-art results in recognising both posed expressions and spontaneous micro-expressions. This performance is confirmed even when the data used to train the model differ from test data in terms of the intensity of facial movements and frame rate.

Description

Keywords

Facial expression recognition, Facial bases, Micro-expressions, Image representation, Spatio-temporal features

Journal Title

IEEE Trans Image Process

Conference Name

Journal ISSN

1057-7149
1941-0042

Volume Title

26

Publisher

Institute of Electrical and Electronics Engineers (IEEE)
Sponsorship
Engineering and Physical Sciences Research Council (EP/L00416X/1)
The work of E. Sariyanidi and H. Gunes are partially supported by the EPSRC under its IDEAS Factory Sandpits call on Digital Personhood under Grant EP/L00416X/1.