摘要

The anisotropic diffusion equation model proposed by the Perona and Malik is sometimes unstable. In this paper, we introduce an anisotropic diffusion model based-on the Lattice Boltzmann method, and apply it to the fast anisotropic smoothing for medical images. Furthermore, we show that the LBM-based model is stable if the relaxation parameter is equal to or larger than one but smaller than two. To quantitatively evaluate and validate the model in medical image smoothing, we compared the model with Perona and Malik's method by calculating the signal to noise ratio. The experimental results show that our method outperforms over Perona and Malik's method in image denoising.