Journal
IMAGE AND VISION COMPUTING
Volume 30, Issue 10, Pages 762-773Publisher
ELSEVIER
DOI: 10.1016/j.imavis.2012.01.006
Keywords
Facial expression recognition; 3D facial geometries; Motion-based features; Quad-tree decomposition; 2D/3D comparison
Categories
Funding
- European Research Council under the ERC Starting Grant [ERC-2007-StG-203143]
- Engineering and Physical Sciences Research Council (EPSRC) through a Doctoral Training Account Studentship
- Junior Research Fellowship of Imperial College London
- Engineering and Physical Sciences Research Council [980172, EP/H016988/1] Funding Source: researchfish
- EPSRC [EP/H016988/1] Funding Source: UKRI
Ask authors/readers for more resources
In this paper we propose a method that exploits 3D motion-based features between frames of 3D facial geometry sequences for dynamic facial expression recognition. An expressive sequence is modelled to contain an onset followed by an apex and an offset. Feature selection methods are applied in order to extract features for each of the onset and offset segments of the expression. These features are then used to train GentleBoost classifiers and build a Hidden Markov Model in order to model the full temporal dynamics of the expression. The proposed fully automatic system was employed on the BU-4DFE database for distinguishing between the six universal expressions: Happy, Sad, Angry, Disgust, Surprise and Fear. Comparisons with a similar 2D system based on the motion extracted from facial intensity images was also performed. The attained results suggest that the use of the 3D information does indeed improve the recognition accuracy when compared to the 2D data in a fully automatic manner. (c) 2012 Elsevier B.V. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available