A novel face recognition algorithm based on two kinds of projection is presented in this paper. First, the two dimension principal component analysis (2DPCA) is used to extract one group of features, denoted by α. Second, the fisher linear discriminant analysis (LDA) , or fisherfaces, is used for extracting another group of features, denoted by β.After being standardized, the two kinds of features are combined together in the form of the complex vector α+iβ. Then the fusion features in the complex feature space is extracted by using complex PCA (CPCA). The proposed algorithm is evaluated by using the FERET face database at three different resolutions. The experimental results indicate that the proposed method can achieve about 10% higher recognition accurate rate than 2DPCA and LDA, while only using 28 features for each sample.