Abstract: Novel image matching method based on singular value decomposition （SVD） is proposed in the paper,by taking into account the features of singular values’stability and rotation-invariance.Based on singular values’unique characteristics,this paper further proposes to use weighted distance as the similarity measure between images.In addition,a new coarse-to-fine hierarchical matching approach is proposed to significantly reduce the computation cost. The proposed algorithm has been tested on various corrupted images including noise addition,intensity change and rotation change.Experimental results demonstrate the robustness and accuracy of the proposed algorithm.