Face recognition by Principle Vectors Subspace

Principle component analysis (PCA) and its improved models have found wide applications in pattern recognition field. PCA is a common method applied to dimensionality reduction and feature extraction. Its goal is to choose a set of projection directions to represent original data with the minimum MSE. In this paper, we propose a Principle Vectors Subspace (PVS) for face recognition. Firstly, we use PCA to extract each dimension vector, so we attain a subspace which conclude principle vectors of each dimension. Then we use a base of this subspace to represent a test sample and classify it by Nearest Neighbor classifier. In order to evaluate the performance of our method, we make a comparison of PCA, KPCA and our method on the ORL and AR databases. The experimental results show our method take a good performance.