Although many of methods have accomplished good success in face recognition systems, but most of them are unable to achieve recognition by using a single sample per person. In this paper, a combination of three techniques represented by local binary pattern (LBP), principal component analysis (PCA) and support vector machine (SVM) is used to present face recognition system has the ability to recognize face depending on Single Sample per Person only. The LBP and PCA are applied to extract the important features as well as reduce the dimension of the image face while the SVM is applied to classify these features according to the classes that belong to its. The proposed approach was evaluated on Yale database and the experimental results showed distinct improvement of the proposed method compared with traditional PCA based SVM classifier.