Principal component analysis (PCA) is a popular tool for linear dimensionality reduction and feature extraction. Kernel PCA is the nonlinear form of PCA, which is promising in exposing the more complicated correlation between original high-dimensional features. In this paper, we first talk about the basic ideas of PCA and kernel PCA, and then focus on the reconstruction of pre-images for kernel PCA. We also give an introduction on how PCA is used in active shape models (ASMs), and discuss how kernel PCA can be applied to improve traditional ASMs. Then we show some experiment results to compare the performance of kernel PCA and traditional PCA for pattern classification. We also implement the kernel PCA-based ASMs, and use it to construct human face models.