一种图像去噪模型的数值解法

A Numerical Computational Method to a Diffusion Model

用偏微分方程数值解中常用的交替方向隐格式对Wang Qiang等提出的图像去噪中的一种基于时滞正则的扩散模型进行离散化,构造出此模型的数值计算方法,并进行了数值实验.从实验结果来看,该扩散模型能有效地去除噪声并能比较好的保持图像的一些细节特征,而本文中构造出的模型的数值解法也是非常有效的.

In this paper, we choose the Peaceman-Rachford（PR） method to construct a numerical computational method for Wang Qiang＇s time-delay regularization based on anisotropic diffusion model which is proposed for image denoising. The numerical examples are presented to show that this method can not only remove the noise efficiently but can preserve the details in the image such as edges and comers. All these can prove that the numerical computational method we have been constructed is very efficient.