Fusion of PCA and KFDA for rapid face recognition
Caikou Chen, Jing-Yu Yang, Jian Jun Yang · 2005
Kernel method-based feature extraction algorithms such as kernel Fisher discriminant analysis (KFDA) have widely been applied to image recognition tasks such as face recognition. For current feature extraction methods based on kernel method, the computation cost to construct kernel matrix mainly depends on the dimension of the original input training samples. Since the dimension of an image vector in face recognition tasks is over ten thousand, kernel-based algorithms have to consume considerable time to build the kernel matrix. In this paper, a fusion of PCA and KFDA for face recognition, shortly called PCA+KFDA, is developed. The algorithm includes two stages: firstly, the classical principal component analysis (PCA) is employed to condense the dimension of face image vector. What follows, kernel Fisher discriminant analysis (KFDA) is applied to the reduced dimensional training samples. Finally, The experimental results on ORL face database indicate that the proposed methods are more efficient than KFDA while retaining the same recognition accuracy.