一种基于噪声迭代检测的中值滤波改进算法  

AN IMPROVED MEDIAN FILTERING ALGORITHM BASED ON NOISE ITERATIVE DETECTION

作　　者：王金凤[1] 侯德文[1] 庞乐[1] 

机构地区：[1]山东师范大学信息科学与工程学院,济南250014

出　　处：《山东师范大学学报（自然科学版）》2015年第2期31-34,38,共5页Journal of Shandong Normal University(Natural Science)

摘　　要：针对传统中值滤波算法对于图像噪声密度过高时处理能力较差的问题,提出一种基于噪声迭代检测的改进型中值滤波算法.首先该算法对噪声图像进行迭代的噪声检测,提高噪声点检测的准确率,其次根据检测到的噪声点逐步改变滤波窗口的大小,对噪声图像进行渐进中值滤波.最后,如果图像中存在较大的噪声块,则噪声用邻域中的非噪声点的灰度均值来代替.实验结果表明,新方法对噪声密度较高图像的滤波效果优于传统中值滤波方法.该算法的迭代噪声检测机制能够既检测出噪声又较好地保留了图像的非噪声点的信息,渐进滤波的策略能够对噪声图像进行适度平滑的滤波同时较好地保留了图像的细节点.To deal with the poor processing ability of the traditional median filter algorithm for image with high density of noisy, we puts forward an improved median filtering algorithm based on iterative method of noise detection. At first, in order to improve the accuracy of noise detection, noise detection iteration is applied to the noise image. Secondly, the size of the filtering window is gradually changed by the noise point which is detected to restore image with progressive median filtering. Finally, if the image consists of larger noise cluster, the noise would be replaced with the mean of signals near it. The experiments show that the filtering effect of new method applied to high -density noise image is better than other traditional filtering method. Iterative noise detection mechanism of this algorithm can not only detect the noise, but also has a better effect on preserving the non - noise points of the image information. At the same time, and reserve the detail of the image nicely. gradual filtering strategy can moderately filter the noise image

关 键 词：噪声检测 迭代 中值滤波 渐进滤波 

分 类 号：TP311.52[自动化与计算机技术—计算机软件与理论]