KPCA Based on LS-SVM for Face Recognition
Xie Jianhong · 2008
Kernel principal component analysis (KPCA) is an improved PCA, which possesses the property of extracting optimal features by adopting a nonlinear kernel function method. Based on the duality between least square support vector machine (LS-SVM) and KPCA, the optimization problem of KPCA can be transformed into the solving of quadratic equations by means of LS-SVM method, and thus leads to the computational complexity being simplified largely. Based on ORL face database, KPCA combined with LS-SVM is applied to realize faces recognition. The experimental results show that KPCA based on LS-SVM has a higher correct recognition rate, and a faster computational speed.