Abstract: This paper analyses the theory and effects of Total Variation(TV) model for noise removal and proposes a new fourth-order Partial Differential Equations(PDE) de-nosing model to avoid the blocky effects of second-order PDE model, while preserving edges. A symmetric discrete algorithm based on four-neighbor system is developed to solve the new model. Median filtering is applied to alleviate the speckle effects in the processed image at last. Experimental results show that the new algorithm is better, compared with traditional methods.

Key words: image de-noising, Total Variation(TV) model, fourth-order Partial Differential Equations(PDE) model

摘要： 通过分析整体变分模型的去噪原理和效果，提出一个新的四阶偏微分方程去噪模型，用于克服二阶偏微分方程去噪后使图像分块的缺点，同时保持去噪后图像的高保真性，并发展一个基于四邻域系统的对称离散化算法用于求解新模型，应用中值滤波去除四阶偏微分方程去噪所引起的亮点。实验结果表明，与传统方法相比，以该算法去噪后的图像具有更好的质量和视觉效果。

关键词: 图像去噪, 整体变分模型, 四阶偏微分方程模型

CLC Number: 

• TP301.6