一种基于改进脊波变换的激光图像滤波算法

针对激光图像中的斑点噪声,提出了一种基于改进脊波变换的滤波算法.该算法首先对含有噪声的激光图像进行二维连续脊波变换,获得高频和低频分解系数;然后根据高频系数中噪声分布特征设计出一种能够根据脊波分解层数的变化而自适应调整的阈值函数模型;提出一种修正硬阈值函数对于低频脊波分解系数进行处理;最后进行系数重构.采用自适应维纳滤波对重构图像出现的“卷绕”现象进行处理.仿真结果表明,该滤波算法对于激光图像中的斑点噪声的抑制效果优于经典中值滤波(MF)、自适应中值滤波(AMF),对于激光图像处理具有一定的参考价值.

A new laser image filtering algorithm based on improved Ridgelet transform

A new filtering algorithm is presented so as to deal with the salt & pepper in laser images.Firstly,the noise laser image is conducted two-dimension continuous Ridgelet transform,obtaining high frequency Ridgelet coefficient and low frequency coefficient.Secondly,according to the the distribution characteristics of the high frequency,a new adaptive threshold function is put forward that can be adjusted by the change of the Ridgelet decomposition layers.a new improved hard threshold function is presented to filter the nois in the low frequency Ridgelet coefficient.Finally,the filtering coefficient are reconstructed.The adaptive wiener filter is used to deal with the winding phenomenon.The experimental results show that the performance of the introduced algorithm in this paper is batter than the classical median filter(MF)and adaptive median filter(AMF) and can provide a reference for the research of laser image processing.