DocumentCode
457102
Title
Adaptive Processing of Face Emotion Tree Structures
Author
Wong, Jia-Jun ; Cho, Siu-Yeung
Author_Institution
Div. of Comput. Syst., Nanyang Technol. Univ., Singapore
Volume
1
fYear
0
fDate
0-0 0
Firstpage
1184
Lastpage
1187
Abstract
This paper describes a novel recursive neural network for adaptive processing of face emotion tree structures (FEETS). We proposed to use tree structures to represent Gabor face emotion features. We demonstrated the robustness of our proposed system by testing against other well-known classifiers using the Cohn-Kanade AU-coded facial expression database (Cohn et al., 1997). The system yields an accuracy of about 93% and 57% for known and unknown subjects respectively
Keywords
emotion recognition; face recognition; image classification; neural nets; tree data structures; visual databases; Gabor face emotion feature; adaptive processing; face emotion tree structure; facial expression database; recursive neural network; Emotion recognition; Face detection; Face recognition; Feature extraction; Image recognition; Lips; Neural networks; Nose; Pattern recognition; Tree data structures;
fLanguage
English
Publisher
ieee
Conference_Titel
Pattern Recognition, 2006. ICPR 2006. 18th International Conference on
Conference_Location
Hong Kong
ISSN
1051-4651
Print_ISBN
0-7695-2521-0
Type
conf
DOI
10.1109/ICPR.2006.222
Filename
1699101
Link To Document