摘要
针对椒盐噪声污染图像的降噪,提出一种开关层次中值滤波新算法。该算法由两部分组成:(1)是开关部分,即判定噪声污染图像中的每个像素点是否为噪声像素点,被判定为噪声的像素点的空间位置信息形成噪声定位图像;(2)是层次中值滤波部分,即对噪声定位图像依照某一准则进行分层处理,最后对噪声污染图像执行层次中值滤波。给出该算法的一种实现,并将该实现与标准中值滤波、自适应中值滤波进行仿真对比实验,并与其它中值滤波算法就指标PSNR进行比较,结果均表明该算法降噪效果优良。
A new median filter algorithm,which is named switch layered median filter,is proposed to restore images corrupted by salt-and-pepper noise.This algorithm is composed of two parts:one is the switch part,which the aim is to judge whether every pixel of the corrupted image is noised pixel or not,and the result of this part is the noise pixels position image:the other part is the layered median filter,first segments the noise pixels position image into a serial of layered images which called layered noised pixels position image,then sorts these noised pixels position images according to a kind of criteria,at last,a standard median filters are applied on the salt-and-pepper noise corrupted image, and the result of filtering is got.An implementing method of this algorithm is applied, and extensive simulations are carried out to validate the proposed algorithm.Experimental results show superiorities both visually and quantitatively compared to the standard median filter,adaptive median filter and other median filters to the index of PSNR for the removed of salt-and-pepper noise at different densities,and the proposed algorithm is more valid and advantageous.
出处
《自动化与仪器仪表》
2016年第3期56-58,61,共4页
Automation & Instrumentation
基金
2010年度甘肃省属高校基本科研业务费专项资金资助"往复式压缩机状态监测及RCM技术研究"(甘财教[2010]176)
关键词
椒盐噪声
中值滤波
噪声像素定位图像
开关
层次中值滤波
salt & pepper noise
median filter
noise pixel position image
switch
layered median filter
