DocumentCode :
623387
Title :
Research on the selection of kernel function in SVM based facial expression recognition
Author :
Fuguang Wang ; Ketai He ; Ying Liu ; Li Li ; Xiaoguang Hu
Author_Institution :
Sch. of Mech. Eng., Univ. of Sci. & Technol. Beijing, Beijing, China
fYear :
2013
fDate :
19-21 June 2013
Firstpage :
1404
Lastpage :
1408
Abstract :
Support vector machine(SVM) means that structural risk minimization principle is used to substitute Empirical risk minimization principle. SVM has shown the excellent performance in pattern recognition. The kernel function is the core of SVM, with which SVM can help to resolve many kinds of non-linear classification problems. Different kernel models and parameters have different result in the performance of the facial expression recognition system. The authors analyze the capability of polynomial kernel function and RBF kernel function in the facial expression recognition using the JAFFE expressions library. The work is valuable in the choise of kernel and its parameters in practice.
Keywords :
emotion recognition; face recognition; image classification; polynomials; radial basis function networks; support vector machines; JAFFE expressions library; RBF kernel function; SVM based facial expression recognition; empirical risk minimization principle; kernel function estimation; kernel models; kernel parameter; nonlinear classification problems; pattern recognition; polynomial kernel function; structural risk minimization principle; support vector machine; Conferences; Face recognition; Feature extraction; Kernel; Polynomials; Support vector machines; Facial expression recognition; RBF kernal function; Support vector machine; polynomial kernel function;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Industrial Electronics and Applications (ICIEA), 2013 8th IEEE Conference on
Conference_Location :
Melbourne, VIC
Print_ISBN :
978-1-4673-6320-4
Type :
conf
DOI :
10.1109/ICIEA.2013.6566586
Filename :
6566586
Link To Document :
بازگشت