基于最小方差与均值的中值滤波算法  

A New Median Filter Algorithm Based on Minimum Variance and Mean Filter

作　　者：臧恒广[1] 高慧敏[2] 

机构地区：[1]太原科技大学计算机科学与技术学院,山西太原030024 [2]嘉兴学院机电工程学院,浙江嘉兴314001

出　　处：《嘉兴学院学报》2012年第6期34-37,共4页Journal of Jiaxing University

基　　金：山西省自然科学基金(2009011011-3);山西省回国留学人员科研资助项目(2011-078)

摘　　要：中值滤波可有效滤除图像的椒盐噪声,但中值滤波在滤除图像噪声时,破坏了图像的边缘和细节信息.为了在滤除噪声时,保护图像的边缘和细节部分,提出了一种实用且有效的图像滤波算法——基于最小方差与均值的中值滤波算法.新算法结合了基于最小方差的中值滤波和均值滤波两种算法的优点.实验结果表明,该算法在滤除噪声的同时可有效地保护图像的边缘和细节.Median filter can suppress salt and peppers noise effectively, but it damages the image＇s edge and details while suppressing the noise. In order to filter the noise meanwhile protect the edge and detail feature, an effective noise filter algorithm was suggested which is based on minimum variance and mean filter of median filter algorithm. The new algorithm combines the merits of the median filter and mean filter based on minimum variance. The experimental results show that the new algorithm can effectively remove the pepper and salt noise meanwhile can preserve more edge and detail features.

关 键 词：椒盐噪声 中值滤波 边缘保护 最小方差 

分 类 号：O141[理学—数学]