TY - GEN
T1 - Recognizing facial expression
T2 - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005
AU - Bartlett, Marian Stewart
AU - Littlewort, Gwen
AU - Frank, Mark
AU - Lainscsek, Claudia
AU - Fasel, Ian
AU - Movellan, Javier
PY - 2005
Y1 - 2005
N2 - We present a systematic comparison of machine learning methods applied to the problem of fully automatic recognition of facial expressions. We report results on a series of experiments comparing recognition engines, including AdaBoost, support vector machines, linear discriminant analysis. We also explored feature selection techniques, including the use of AdaBoost for feature selection prior to classification by SVM or LDA. Best results were obtained by selecting a subset of Gabor filters using AdaBoost followed by classification with Support Vector Machines. The system operates in real-time, and obtained 93% correct generalization to novel subjects for a 7-way forced choice on the Cohn-Kanade expression dataset. The outputs of the classifiers change smoothly as a function of time and thus can be used to measure facial expression dynamics. We applied the system to to fully automated recognition of facial actions (FACS). The present system classifies 17 action units, whether they occur singly or in combination with other actions, with a mean accuracy of 94.8%. We present preliminary results for applying this system to spontaneous facial expressions.
AB - We present a systematic comparison of machine learning methods applied to the problem of fully automatic recognition of facial expressions. We report results on a series of experiments comparing recognition engines, including AdaBoost, support vector machines, linear discriminant analysis. We also explored feature selection techniques, including the use of AdaBoost for feature selection prior to classification by SVM or LDA. Best results were obtained by selecting a subset of Gabor filters using AdaBoost followed by classification with Support Vector Machines. The system operates in real-time, and obtained 93% correct generalization to novel subjects for a 7-way forced choice on the Cohn-Kanade expression dataset. The outputs of the classifiers change smoothly as a function of time and thus can be used to measure facial expression dynamics. We applied the system to to fully automated recognition of facial actions (FACS). The present system classifies 17 action units, whether they occur singly or in combination with other actions, with a mean accuracy of 94.8%. We present preliminary results for applying this system to spontaneous facial expressions.
UR - https://www.scopus.com/pages/publications/24644474838
U2 - 10.1109/CVPR.2005.297
DO - 10.1109/CVPR.2005.297
M3 - Conference contribution
SN - 0769523722
SN - 9780769523729
T3 - Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005
SP - 568
EP - 573
BT - Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005
PB - IEEE Computer Society
Y2 - 20 June 2005 through 25 June 2005
ER -