An effective and fast face recognition method that is capable of dealing with faces under variable pose and illumination conditions has been proposed in this paper. First, the face is detected and the eyes are located automatically by the two cameras, eyes located in the two cameras are matched and the pose angle of the face is calculated. Then, the frontal face is generated according to the pose angle with the method of Binocular Stereo Vision. After that, Sparse Representation method is performed on the frontal face in order to be robust to the different illuminating conditions. Experimental results show that our pose angle calculation method is precise and practical, and our face recognition method can maintain good performance with varying pose as well as varying lighting conditions.