DocumentCode
495101
Title
Facial Expression Recognition Based on FB2DPCA and Multi-classifier Fusion
Author
Hua, Bin ; Liu, Ting
Author_Institution
Inst. of Technol., Tianjin Univ. of Finance & Econ., Tianjin, China
Volume
2
fYear
2009
fDate
21-22 May 2009
Firstpage
353
Lastpage
356
Abstract
A method of feature block two-dimensional principal component analysis (FB2DPCA) and multi-classifier combination is proposed for facial expression recognition. First, FB2DPCA is applied to extract human facial expression features, and then the expression classified result is obtained based on multi-classifier fusion with fuzzy integral. This proposed method is validated through the results of experiments on JAFFE facial expression database, and a high recognition rate is also achieved.
Keywords
face recognition; feature extraction; image fusion; pattern classification; principal component analysis; FB2DPCA; facial expression recognition; feature block 2D principal component analysis; feature extraction; multiclassifier fusion; Covariance matrix; Eyebrows; Eyes; Face recognition; Feature extraction; Humans; Image recognition; Mouth; Principal component analysis; Vectors; FB2DPCA; facial expression recognition; feature extraction; multi-classifier fusion;
fLanguage
English
Publisher
ieee
Conference_Titel
Information and Computing Science, 2009. ICIC '09. Second International Conference on
Conference_Location
Manchester
Print_ISBN
978-0-7695-3634-7
Type
conf
DOI
10.1109/ICIC.2009.200
Filename
5169084
Link To Document