一种改进的n维空间递归滤波算法

THE IMPROVED N-DIMENSIONAL RECURSIVE NONLINEAR FILTERING ALGORITHM

基于递归运算准则 ,本文提出了一种n维空间非线性滤波器的改进算法。该算法利用像素点的周边信息完成对噪声点的识别与修复。此n维空间滤波器可以递归地分解到更低一维空间 ,本文主要分析了这种改进的滤波算法在二维空间信号消噪处理中的性能。仿真结果表明 ,与中值滤波和Peak-and-Valley滤波算法比较 ,该算法在信噪比和图像细节保留方面具有更大的优势 。

An improved n-dimensional nonlinear filter is presented in this paper based on recursive operation.This recursive nonlinear filter identifies noisy items by inspection of their surrounding neighborhood,and afterwards using the information around the noise pixel restore the noise pixel.This n-dimensional filter can be decomposed recursively to a lower dimensional space,this study,which focuses on the case of two-dimensional signals,explores one possible implementation of this improved filter.Simulation results demonstrate that the proposed algorithm is better than traditional median-based filters and Peak-and-Valley filter and is particularly effective for the cases where the images are highly corrupted.