基于总变分加权低秩矩阵恢复的椒盐噪声去噪

Salt-and-pepper denoising based on total variation and reweighted low-rank matrix recovery

传统的基于低秩矩阵恢复的椒盐噪声去噪算法易产生条纹失真,中值滤波去除椒盐噪声后边缘易产生移位和块状效应,纹理细节不太清晰,为此提出一种椒盐噪声去噪模型。在原有的低秩矩阵核范数约束基础上引入总变分约束项,为提高低秩矩阵的低秩性和稀疏矩阵的稀疏性,引入加权的方法。实验结果表明,该算法能增加低秩矩阵的低秩性和稀疏矩阵的稀疏性,保证了去噪效果,保留了图像的细节信息,具有更佳的视觉效果,提高了客观评价指标。

The traditional salt-and-pepper denoising based on low-rank matrix recovery algorithm is easy to produce stripes distortion,median filter may lead to edge shift and blocky,and serious detail loss.To solve the problem,a salt-and-pepper denoising algorithm was proposed,in which total variation was added to the low rank restraint model.Inspired by reweighted L1 minimization for sparsity enhancement,reweighting singular values were used to enhance low rank of matrix,an efficient iterative reweighting scheme was proposed for enhancing low rank and sparsity simultaneously.Experimental results show that the proposed algorithm can enhance low rank and sparsity of a matrix simultaneously,guarantee visual effect and keep the details.At the same time,the objective evaluation indexes are improved.