基于双边滤波与非局部均值的图像去噪研究

提出了一种基于双边滤波与非局部均值的图像去 噪算法,近年来提出的非局部均值算法是去噪效果非常 出色的算法之一,双边滤波去噪算法采用空间邻近度和灰度相似性构造新的权重系数,其取 得了良好的去噪效果,本文 据此改进非局部均值算法的权重部分,把空间邻近度因子与非局部均值的权重系数相结合, 构造新的权重系数。实验表 明,本文改进权重的非局部均值算法与已有的去噪方法相比,能得到更好的峰值信噪比,能 更好的保护图像细节以及结构信息。

Image denoising based on bilateral filtering and non-local means

This paper presents an image denoising method based on bilat eral filtering and non-local means.Non-local means method which was proposed in recent years is one of the great performing methods.And co mpared with the classical denoising methods,bilateral filtering method has a better performance in denoising for the reason that the weight include the geometric closeness and the intensity similarity.And accordingly this paper improve the we ight of the non-local means method.This paper combines the geometric closeness factor with the weight of Non-local means and constructs a new weight.Experiment shows that the modified algorithm can achieve better performance.And it can protect the image d etail and structure information better.