DocumentCode :
528664
Title :
Gabor feature selection for facial expression recognition
Author :
Lee, Chien-Cheng ; Shih, Cheng-Yuan
Author_Institution :
Dept. of Commun. Eng., Yuan Ze Univ., Chungli, Taiwan
fYear :
2010
fDate :
7-10 Sept. 2010
Firstpage :
139
Lastpage :
142
Abstract :
This paper presents an effective Gabor features for recognizing the seven basic facial expressions (anger, disgust, fear, happiness, sadness, surprise and neutral) from static images. Entropy criterion selects informative and non-redundant Gabor features. This feature selection reduces the feature dimension without losing much information and also decreases computation and storage requirements. This paper uses improved RBF networks with the proposed effective Gabor features to recognize facial expressions. Experiment results show that our approach can accurately and robustly recognize facial expressions.
Keywords :
Gabor filters; entropy; face recognition; feature extraction; radial basis function networks; Gabor feature selection; entropy criterion; facial expression recognition; nonredundant Gabor features; radial basis function network; static images; Databases; Entropy; Face; Face recognition; Feature extraction; Image recognition;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Signals and Electronic Systems (ICSES), 2010 International Conference on
Conference_Location :
Gliwice
Print_ISBN :
978-1-4244-5307-8
Electronic_ISBN :
978-83-9047-4-2
Type :
conf
Filename :
5595233
Link To Document :
بازگشت