一种基于峰谷滤波的改进算法  

An Improved Algorithm Based on the Peak-and-Valley Filtering

作　　者：朱建明[1] 吕振肃[1] 马榕[1] 夏春水[1] 

机构地区：[1]兰州大学信息科学与工程学院,甘肃兰州730000

出　　处：《甘肃科学学报》2006年第4期64-66,共3页Journal of Gansu Sciences

摘　　要：在峰谷滤波的基础上提出了一种新的改进算法,首先在噪声污染图像的滤波窗口中去除除中心象素外的最大最小灰度值象素,然后利用中心象素与修改后的邻域进行比较以判断其是否为噪声点.理论分析和图像处理仿真实验表明,改进后的滤波器性能得到较大改善,在有效去除噪声的同时能充分保留原图像细节信息.A new improved algorithm is proposed based on the peak-and-vally filter. Firstly, except the central pixel, pixels with maximum and minimum gray values in the filtering window are excluded. Then, the central pixel is compared with the neighbors to decide whether it is a noised pixel or not. The theoretical analysis and simulation experiments of the image processing indicate that this improved filter can not only remove noises effectively but also keep the details of the image sufficiently.

关 键 词：非线性滤渡 中值滤波器 峰谷滤波器 图像处理 

分 类 号：TN911.73[电子电信—通信与信息系统]