基于噪声检测的彩色图象脉冲噪声滤波

文章提出了具有细节保持能力的自适应彩色图像脉冲噪声滤波器，称为细节保持滤波器。新方法对图像中噪声像素进行检测，仅对噪声像素进行有序滤波而对非噪声像素则保持其原值不变，并根据图像噪声情况自适应地选择滤波窗口。从而，有效地滤除随机彩色脉冲噪声、保持图像边缘与细节，其性能优于经典的矢量中值滤波器（ＶＭＦ）、方向一距离滤波器（ＤＤＦ）、距离一幅度矢量滤波器（ＤＭＶＦ）等非线性滤波器。

Noise Detection-Based Color Filters for Impulse Noise Removal

In this paper,new filters for impulse noise removal in color image are proposed based on noise detection, called as detail-preserving filters(DPF).In the new method, impulse noise in color image is first preperly detected,and the detected noisy pixels are filtered out with adaptive selection of filter window,while the noise-free pixels are kept without any change.Experimental results show that the proposed detail-preserving filters remove impulse noise and preserve edges and details very well,that perform better than the classical vector median filter (VMF),direction-directance filter(DDF), and distance-magnitude vector filter(DMVF).