DocumentCode :
2749503
Title :
A New Facial Expression Analysis System Based on Warp Image
Author :
Li, Hui ; Lin, Hui ; Yang, Guang
Author_Institution :
Sch. of Manage., Dalian Univ. of Technol.
Volume :
2
fYear :
0
fDate :
0-0 0
Firstpage :
10045
Lastpage :
10049
Abstract :
In this paper, a novel facial expression analysis system is proposed, which directly recognizes warp image of face. And the warp image can be obtained by the automatic AAM processing. The system consists of mainly four modules, warp processing, Gabor filtering, Adaboost training processing, SVM training and testing processing. We also compared the performance of our method to the system trained on the output of face detector (geometry normalization images). And the method using warp preprocessing can reach a high level of accuracy above 90%
Keywords :
Gabor filters; emotion recognition; face recognition; support vector machines; Adaboost training; Gabor filtering; SVM; automatic AAM processing; facial expression analysis; geometry normalization images; warp image; warp processing; Active appearance model; Detectors; Face detection; Face recognition; Filtering; Gabor filters; Image analysis; Image recognition; Support vector machines; System testing; Adaboost; Facial expression analysis; Gabor; SVM; Warp;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Intelligent Control and Automation, 2006. WCICA 2006. The Sixth World Congress on
Conference_Location :
Dalian
Print_ISBN :
1-4244-0332-4
Type :
conf
DOI :
10.1109/WCICA.2006.1713964
Filename :
1713964
Link To Document :
بازگشت