一种基于加权均值滤波噪声点检测的中值滤波算法  

A Median Filter Algorithm Based on Noise Detection by Weighted Average Filtering

作　　者：顾剑锋[1] 陈平[2] 肖轶[2,3] 

机构地区：[1]南通职业大学,南通226007 [2]安徽工业大学,马鞍山243002 [3]南通宝钢钢铁有限公司,南通226002

出　　处：《南通纺织职业技术学院学报》2010年第1期17-21,共5页Journal of Nantong Textile Vocational Technology college

基　　金：国家自然科学基金(编号50874001);南通市应用研究计划(编号K2008037)

摘　　要：针对常规中值滤波在图像去噪过程中会将原图像的有用信息同时滤除的问题,提出了一种基于加权均值滤波噪声点检测的中值滤波算法.该算法通过含噪图像与其经加权均值滤波的图像作差对图像中的噪声点进行判别,从而针对噪声点进行滤波,能在保持图像原始信息的前提下有效地将图像中的噪声滤除.实验结果表明,与常规中值滤波算法相比,该方法既具有较好的去噪特性,也具有较强的细节保护能力.To overcome the drawback that traditional median filter algorithm often gets rid of useful information while filtering the noise in the image,the paper proposes a median filter algorithm based on noise detection by weighted average filtering,which detects and filters the waves of the noise by contrasting the noise image and weighted average filtered image.It filters the noise in the image effectively while keeping the original image information intact.Simulation results demonstrate that this algorithm is better than traditional median-based filters in the performance of noise filtering and detail preservation.

关 键 词：中值滤波 噪声点检测 加权均值滤波 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]