Abstract: In order to remove noise while having image fidelity, based on anisotropic diffusion model, this paper proposes the anisotropic diffusion model combined with adaptive fidelity term. The model can suppress noise on the edge and strong noise. Experimental results show that the model can effectively remove the noise, and the details and edges of the image can be a good fidelity.

Key words: ROF model, selective fidelity term, anisotropic diffusion, image denoising, P-M model

摘要： 为了在去除噪声的同时，对图像更好的保真，在各向异性扩散模型的基础上，提出了结合自适应保真项的各向异性扩散模型。该模型能够很好地抑制边缘上的噪声和强噪声。实验结果表明，该模型不仅能有效去除噪声，而且对图像细节、边缘也能很好的保真。

关键词: ROF模型, 自适应保真, 各向异性扩散, 图像去噪, P-M模型