基于模糊方法的随机值脉冲噪声去除算法  

Random Value Impulse Denoising Agorithm based on Fuzzy Method

作　　者：董晶[1] 刘云龙[2] DONG Jing LIU Yun-long(China Academy of Electronics and Information Technology ,Beijing 100041 ,China Information System Reliability Testing Center, Research Center for Computer and Microelectronic Industry Development, Beijing 100048, China)

机构地区：[1]中国电子科学研究院,北京100041 [2]工业和信息化部计算机与微电子发展研究中心信息系统可靠性测试中心,北京100048

出　　处：《中国电子科学研究院学报》2017年第4期378-382,共5页Journal of China Academy of Electronics and Information Technology

基　　金：国家863高技术研究项目

摘　　要：随机值脉冲噪声脉冲强度的动态范围为整个灰度空间,通常为均匀随机分布,因此通常不知道它的先验分布。一般算法很难区分对比度差的信号与噪声。本文针对随机值脉冲噪声的特征,构建了噪声描述描述模型,利用模糊系统理论描述随机值脉冲噪声的存在特征,通过像素多邻域、自适应窗口检测噪声,运用最小化价值函数滤除噪声,实验证明本文提出的算法是一种有效的随机脉冲噪声检测与去除方法。The intense of random value impulse noise is covered whole grayscale space,which obeys the uniform distribution. The general algorithm is difficult to distinguish contrast difference between signal and noise. In this paper,a noise model was built,which utilized the fuzzy systems theory to describe noise characteristics. Noise was detected by using pixel multiple neighbor and adaptive windows. Finally,the denoising was done with minimizing the cost function. Experiments show that the proposed algorithm is an effective methods for removing the random value impulse noise.

关 键 词：随机值脉冲噪声 模糊方法 噪声检测 隶属度 噪声去除 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]