基于改进PCNN模型的对称中值滤波方法  

Symmetric median filtering method based on improved PCNN model

作　　者：吴海龙[1] 柏正尧[1] 张瑜[1] 檀磊[1] 

机构地区：[1]云南大学信息学院,云南昆明650500

出　　处：《云南大学学报（自然科学版）》2018年第1期43-49,共7页Journal of Yunnan University(Natural Sciences Edition)

基　　金：国家自然科学基金(U1231122);云南大学第八届研究生科研创新项目

摘　　要：为滤除灰度图像中椒盐噪声同时保留图像细节,提出了一种椒盐噪声滤波算法.首先利用改进PCNN模型执行一次点火操作从而定位灰度图像中噪声像素点位置,然后利用提出的对称检测中值滤波算法对已定位的噪声点进行滤波而其他位置像素信息保持不变.实验仿真表明,新提出的方法对噪声密度低于60%的椒盐噪声图像较已有的滤波算法有更优异的滤波性能.该算法能有效滤除噪声而且对图像的边缘细节保留完整,实验结果证明了算法的有效性.In order to remove the pepper and salt noise in the gray scale image and keep the image details at the same time, a salt and pepper noise filtering algorithm is proposed.Firstly,the modified PCNN model is used to perform the ignition operation to locate the position of the noise pixel in the gray image.Then,the proposed symmetric detection median filter algorithm is used to filter the located noise point and the other pixel information remains unchanged.The simulation results show that the proposed method has better filtering performance than the existing filtering algorithm for the pepper and salt noise which noise density less than 70%.The algorithm can ef- fectively filter out the noise and keep the edge detail of the image.The experimental results prove the effectiveness of the algorithm.

关 键 词：改进PCNN模型 椒盐噪声 对称检测 中值滤波 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]