一种新的去噪模型的分裂Bregman算法

Split Bregman Algorithm for a Novel Denoising Model

该文在研究两步模型的基础上,提出了一种新的变分去噪模型。通过分析新模型的性质,给出一种高效且快速的数值算法。由于新模型耦合了两个变量,因此新算法首先利用交替极小化方法化原模型为两个简单的子模型,然后再对两个子模型分别利用分裂Bregman方法进行数值求解。实验结果表明,新算法不但收敛速度较快,而且在去噪过程中能够减缓阶梯效应并能较好地保持图像的边缘信息。

A novel variational denoising model is proposed based on the study of two-step model.By analysing the properties of new model,an efficient and fast numerical algorithm is introduced.There are two variables in the new model,so it is firstly turned into two simple submodels by using alternative minimization method in the new algorithm,and then the two submodels are solved using split Bregman method respectively.Experimental results show new algorithm not only has faster convergence rate,but also can alleviate the staircase effect and preserve the edge information better while removing noises.