TY - GEN
T1 - 3D Facial expression recognition based on automatically selected features
AU - Tang, Hao
AU - Huang, Thomas S.
PY - 2008
Y1 - 2008
N2 - In this paper, the problem of person-independent facial expression recognition from 3D facial shapes is investigated. We propose a novel automatic feature selection method based on maximizing the average relative entropy of marginalized class-conditional feature distributions and apply it to a complete pool of candidate features composed of normalized Euclidean distances between 83 facial feature points in the 3D space. Using a regularized multi-class AdaBoost classification algorithm, we achieve a 95.1% average recognition rate for six universal facial expressions on the publicly available 3D facial expression database BU-3DFE [1], with a highest average recognition rate of 99.2% for the recognition of surprise. We compare these results with the results based on a set of manually devised features and demonstrate that the auto features yield better results than the manual features. Our results outperform the results presented in the previous work [2] and [3], namely average recognition rates of 83.6% and 91.3% on the same database, respectively.
AB - In this paper, the problem of person-independent facial expression recognition from 3D facial shapes is investigated. We propose a novel automatic feature selection method based on maximizing the average relative entropy of marginalized class-conditional feature distributions and apply it to a complete pool of candidate features composed of normalized Euclidean distances between 83 facial feature points in the 3D space. Using a regularized multi-class AdaBoost classification algorithm, we achieve a 95.1% average recognition rate for six universal facial expressions on the publicly available 3D facial expression database BU-3DFE [1], with a highest average recognition rate of 99.2% for the recognition of surprise. We compare these results with the results based on a set of manually devised features and demonstrate that the auto features yield better results than the manual features. Our results outperform the results presented in the previous work [2] and [3], namely average recognition rates of 83.6% and 91.3% on the same database, respectively.
UR - http://www.scopus.com/inward/record.url?scp=51849110283&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=51849110283&partnerID=8YFLogxK
U2 - 10.1109/CVPRW.2008.4563052
DO - 10.1109/CVPRW.2008.4563052
M3 - Conference contribution
AN - SCOPUS:51849110283
SN - 9781424423408
T3 - 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops
BT - 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops
T2 - 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops
Y2 - 23 June 2008 through 28 June 2008
ER -