一种新的基于噪声点检测的脉冲噪声去噪算法  

A New De-noising Algorithm for Removal Impulse Noise Based on Detection of Noise Points

作　　者：刘祝华[1] 邹道文[2] 邓承志[1] 汪胜前[2] 

机构地区：[1]江西省光电子与通信重点实验室江西师范大学,南昌330027 [2]江西科技师范学院应用物理系,南昌330013

出　　处：《计算机工程与应用》2005年第15期41-43,78,共4页Computer Engineering and Applications

摘　　要：中值滤波是广泛应用于去除脉冲噪声的一种非线性去噪方法,但是单一地使用中值滤波方法去除脉冲噪声会造成图像细节信息的丢失,从而使图像变得模糊。基于噪声点检测的脉冲噪声滤波方法可以在滤除噪声的同时有效地保持图像的细节信息。该文在此基础上提出了一种新的基于噪声点检测的脉冲噪声滤波算法,该算法在检测噪声点时用被检测点的中值滤波结果作为判定该点是否为噪声点的依据。而在滤除被检测到的噪声点时,采用的是迭代的中值滤波算法。从实验结果中可以看到,与其它中值滤波算法相比,该文的算法在去除脉冲噪声时能取得较好的效果。Median filter is a nonlinear filtering technique widely used for removal of impulse noise.Despite its effectiveness in smoothing noise,the median filter tends to remove fine details when it is applied to an image uniformly.The filtering algorithm for removal impulse noise based on detection of noise points can maintain details as well as smooth noise.Therefore,a new algorithm for detection of noise points based on the value of median filtering is presented in the article.The new algorithm determines a pixel point as noise point according to its value of median filtering.And the iterative median filtering algorithm is used when smoothing noise points.Experiment results show that the new algorithm is more effective than other median-based filters in removing impulse noise.

关 键 词：噪声点检测 脉冲噪声 中值滤波 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]