TY - JOUR
T1 - Recognition of 3D facial expression dynamics
AU - Sandbach, Georgia
AU - Zafeiriou, Stefanos
AU - Pantic, Maja
AU - Rueckert, Daniel
N1 - Funding Information:
This work has been funded by the European Research Council under the ERC Starting Grant agreement no. ERC-2007-StG-203143 (MAHNOB). The work of Georgia Sandbach is funded by the Engineering and Physical Sciences Research Council (EPSRC) through a Doctoral Training Account Studentship. The work of S. Zafeiriou was funded in part by the Junior Research Fellowship of Imperial College London .
PY - 2012/10
Y1 - 2012/10
N2 - 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.
AB - 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.
KW - 2D/3D comparison
KW - 3D facial geometries
KW - Facial expression recognition
KW - Motion-based features
KW - Quad-tree decomposition
UR - http://www.scopus.com/inward/record.url?scp=84866741228&partnerID=8YFLogxK
U2 - 10.1016/j.imavis.2012.01.006
DO - 10.1016/j.imavis.2012.01.006
M3 - Article
AN - SCOPUS:84866741228
SN - 0262-8856
VL - 30
SP - 762
EP - 773
JO - Image and Vision Computing
JF - Image and Vision Computing
IS - 10
ER -