TY - JOUR
T1 - Facial emotion recognition based on biorthogonal wavelet entropy, fuzzy support vector machine, and stratified cross validation
AU - Zhang, Yu Dong
AU - Yang, Zhang Jing
AU - Lu, Hui Min
AU - Zhou, Xing Xing
AU - Phillips, Preetha
AU - Liu, Qing Ming
AU - Wang, Shui Hua
N1 - Publisher Copyright:
© 2013 IEEE.
PY - 2016
Y1 - 2016
N2 - Emotion recognition represents the position and motion of facial muscles. It contributes significantly in many fields. Current approaches have not obtained good results. This paper aimed to propose a new emotion recognition system based on facial expression images. We enrolled 20 subjects and let each subject pose seven different emotions: Happy, sadness, surprise, anger, disgust, fear, and neutral. Afterward, we employed biorthogonal wavelet entropy to extract multiscale features, and used fuzzy multiclass support vector machine to be the classifier. The stratified cross validation was employed as a strict validation model. The statistical analysis showed our method achieved an overall accuracy of 96.77±0.10%. Besides, our method is superior to three state-of-the-art methods. In all, this proposed method is efficient.
AB - Emotion recognition represents the position and motion of facial muscles. It contributes significantly in many fields. Current approaches have not obtained good results. This paper aimed to propose a new emotion recognition system based on facial expression images. We enrolled 20 subjects and let each subject pose seven different emotions: Happy, sadness, surprise, anger, disgust, fear, and neutral. Afterward, we employed biorthogonal wavelet entropy to extract multiscale features, and used fuzzy multiclass support vector machine to be the classifier. The stratified cross validation was employed as a strict validation model. The statistical analysis showed our method achieved an overall accuracy of 96.77±0.10%. Besides, our method is superior to three state-of-the-art methods. In all, this proposed method is efficient.
KW - Facial emotion recognition
KW - biorthogonal wavelet entropy
KW - facial expression
KW - fuzzy logic
KW - support vector machine
UR - http://www.scopus.com/inward/record.url?scp=85012969638&partnerID=8YFLogxK
U2 - 10.1109/ACCESS.2016.2628407
DO - 10.1109/ACCESS.2016.2628407
M3 - Article
AN - SCOPUS:85012969638
SN - 2169-3536
VL - 4
SP - 8375
EP - 8385
JO - IEEE Access
JF - IEEE Access
M1 - 7752782
ER -