首页 | 本学科首页   官方微博 | 高级检索  
     

基于级联离散小波变换的信号去噪方法研究
引用本文:谢加华,王振力.基于级联离散小波变换的信号去噪方法研究[J].传感器与微系统,2006,25(10):16-18.
作者姓名:谢加华  王振力
作者单位:1. 上海第二工业大学计算机与信息学院网络工程系,上海,201209
2. 南京通信工程学院电子信息工程系,江苏,南京,210007
摘    要:提出了基于级联离散小波变换的信号去噪方法。该方法通过对带噪信号作一层离散小波变换(DWT)后提取的低频部分和高频部分分别作一层DWT和四层DWT,然后,对低频部分提取的低频成分和高频成分均作三层DWT,接着,对所有分解的小波系数进行阈值处理,最后,完成信号重构。实验结果表明:在同样的小波分解层次下,本方法去噪效果好于DWT法和WPD法。

关 键 词:信号去噪  离散小波变换  小波包分解  软限幅函数
文章编号:1000-9787(2006)10-0016-03
收稿时间:2006-07-20
修稿时间:2006年7月20日

Study on signal denoising based on stage-combined discrete wavelet transform
XIE Jia-hua,WANG Zhen-li.Study on signal denoising based on stage-combined discrete wavelet transform[J].Transducer and Microsystem Technology,2006,25(10):16-18.
Authors:XIE Jia-hua  WANG Zhen-li
Affiliation:1. Department of Network, Academy of Computer and Information, Shanghai Second Polytechnic University, Shanghai 201209, China; 2. Department of Electronic Information Engineering, Nanjing Institute of Communications Engineering, Nanjing 210007, China
Abstract:A method for signal denoising is presented based on stage-combined discrete wavelet transform.Firstly,one scale of discrete wavelet transform(DWT) is used to obtain discrete approximation coefficients and discrete detail coefficients to noisy signal.Secondly,one scale of DWT and four scales of DWT are applied to the obtained discrete approximation coefficients and discrete detail coefficients,respectively.Thirdly,three scales of DWT are applied to the obtained discrete approximation coefficients and discrete detail coefficients from above the approximation coefficients,respectively.Finally,signal reconstruction is obtained after thresholds processing is done to all the decomposed wavelet coefficients.Experimental results show that the proposed method performs better than DWT and WPD for signal denoising under the same decomposed wavelet levels.
Keywords:signal denoising  discrete wavelet transform(DWT)  wavelet packet decomposition(WPD)  soft threshold function
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号