Recently the Sparse Representation-based Classification (SRC) has been successfully used in face recognition. In SRC, a test image is coded by a linear combination of the training dictionary. In this paper, we propose a model extends from SRC named Multi-scale SRC (MSRC). The MSRC build the multi-scale dictionary for the training. A test image is then coded using this multi-scale dictionary. In addition, a voting scheme is applied which not only helps improving the recognition rate significantly, but also makes the algorithm more robust with occlusion. Experiments on representative face databases demonstrate that the MSRC is much more effective than the SRC.