基于低秩近似与非局部稀疏的图像去噪

Image Denoising based on Low Rank Approximation and Nonlocally Sparse Representation

基于低秩近似方法进行图像去噪逐渐成为图像处理领域研究的热点。将图像块分解成一个低秩矩阵和噪声矩阵,利用矩阵的秩来约束图像块的相似性,且现有的非局部稀疏表示算法利用图像块的自相似性进行去噪。鉴于此,提出低秩近似与非局部稀疏的图像去噪模型。该算法加强了图像分解的全局稀疏性约束,更好地保留了图像的细节和边缘信息。

Image denoising based on low rank approximation is becoming a hot topic in image processing field. The image block can be decomposed into a low rank matrix and a noise matrix,the rank of the matrix can be used to constrain the similarity of the image blocks. And the most existing algorithms based on nonlocal sparse representation also use the self-similarity of image blocks for denoising. In view of this,the image denoising model of low rank approximation and nonlocal sparse is proposed. This algorithm enhances the global sparsity constraint of image decomposition and preserves the details and edge information of the image better.