基于区域生长的噪声图像细节保护滤波器

Detail-preserving Region-growing-Based Filters for Noisy Image

本文提出了两种同时受脉冲噪声和高斯白噪声污染图像的基于区域生长的细节保护滤波器。本方法由于利用了图像的空间结构信息及像素的幅序信息，因而能较好地解决图像细节保护与噪声滤除的矛盾。在区域生长算法中采用了自适应阈值，能自适应地确定参与滤波运算的像素。文中还给出了模拟实验的结果。

In this paper,two detail-preserving region-growing-based filters is proposed to deal with the noisy image. Because the structural and spatial neighborhood imformation in the image is fully taken into account and combined with the rank-order information of the pixels,the region-growing algorithm can solve the problem between detail-preserving and noise-filtering in the image processing. An adaptive threshold,with which the filters can take proper pixels of the image to do their work,is taken in this algorithm.