小波阈值消噪算法中自适应确定分解层数研究  

A Study of Adaptive Optimal Decomposition Level in Threshold De-noising Algorithm Based on Wavelet Transform

作　　者：李炜[1] 陈晓辉[1] 毛海杰[1] 

机构地区：[1]兰州理工大学电气与信息工程学院,甘肃兰州730050

出　　处：《计算机仿真》2009年第3期311-313,336,共4页Computer Simulation

基　　金：教育部"春晖计划"(Z2005-1-62001);兰州理工大学重点特色梯队建设项目(0915)

摘　　要：小波多尺度分解的阈值算法是一种有效的信号去噪方法,但实际应用中去噪效果易受到分解层数、门限阈值以及阈值函数选取的影响。分析了有用信号和白噪声的小波系数特点,提出了一种分解层数的自适应确定方法。基于自相关函数的白噪声检验,提出通过去除白噪声小波变换细节系数中的相关成分来增加白噪声的显著性检验,提高了自适应确定最优分解层数的准确性。仿真结果表明,确定最优分解层数是重要的。较之传统的基于白化检验确定最优分解层数的方法,该方法具有更好的去噪效果,尤其适用于强噪声背景下弱信号检测。It is an effective method to reduce the noise in signals based on wavelet multiscale decomposition. There are a lot of factors which will affect the de - noising efficacy, such as threshold, threshold strategy, decomposition level and so on. Based on analyzing the characteristics of the wavelet coefficients of useful signal and white noise, a novel method is presented in this paper. The method is based on white noise verification using the self - correlation function, and it dispels the correlation of the details wavelet coefficient of white noise to increase white noise verification of decomposition level. The simulations indicate that selecting optimal decomposition level is important, and the method can effectively improve the de - noising efficacy than traditional methods. It is suitable for the detection of weak signal with strong noise.

关 键 词：小波多尺度分解 阈值消噪 分解层数 白噪声检验 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]