改进的基于平稳小波变换的散斑去噪方法  

Improved speckle denoising method based on stationary wavelet transform

作　　者：刘益菲 刘吉[1] 武锦辉[1] 刘贵香 牛天利 于丽霞[1] Liu Yifei;Liu Ji;Wu Jinhui;Liu Guixiang;Niu Tianli;Yu Lixia(School of Information and Communication Engineering,North University of China,Taiyuan 030051,China)

机构地区：[1]中北大学信息与通信工程学院,太原030051

出　　处：《国外电子测量技术》2023年第7期16-21,共6页Foreign Electronic Measurement Technology

基　　金：山西省基础研究计划项目(202103021224188,202203021221101)资助。

摘　　要：针对剪切散斑干涉相位条纹图去噪过程中存在的噪声残留和边缘模糊问题,提出一种将正余弦分解和平稳小波变换相结合的散斑去噪方法,使用平稳小波变换对图像的正余弦分量进行小波分解,利用改进的小波阈值函数和阈值选取规则对分解后的高频图像进行处理,最后进行小波重构和反正切运算得到去噪后的相位条纹图。通过实验对各方法去噪后的效果进行分析,该方法能够保留边缘信息,改善相位图的质量,对比现有传统算法均方差分别降低了0.05、0.03,信噪比分别提高了3.1、1.1 dB。In order to solve the problem of noise residue and edge blur in the process of phase fringe image denoising in the shear speckle interference,this paper proposes a speckle denoising method which combines the sine and cosine decomposition and stationary wavelet transform.The stationary wavelet transform is used to decompose the sine and cosine components of the image.The improved wavelet threshold function and threshold selection rule are used to process the decomposed high frequency image.Finally,wavelet reconstruction and arctangent operation are carried out to obtain the denoised phase fringe diagram.Experiments were conducted to analyze the effect of each method after denoising.The method in this paper can retain the edge information and improve the quality of phase diagram.Compared with the existing traditional algorithm,the mean square error is reduced by O.05 and 0.03 respectively,and the signalto-noise ratio is increased by 3.1 and 1.1 dB respectively.

关 键 词：正余弦分解 平稳小波变换 阈值函数 散斑干涉 散斑去噪 

分 类 号：TN247[电子电信—物理电子学]