摘要
传统的小波域信号降噪算法往往仅对平稳噪声有效,降噪效果有待进一步提高。论文在相关降噪算法的基础上,提出了一种改进的区域相关降噪算法。该方法对一个区域内的小波系数进行相关性度量,克服了传统方法对小波系数的偏移引起误判的不足。通过对两组非平稳信号降噪进行对比实验,结果表明,该方法对比传统小波方法具有更好的降噪效果,无论是主观视觉效果和客观评价指标都更有优势。
The traditional signal denoising algorithm based on wavelet domain is often only effective under stationary noise environment,in order to improve the noise reduction effect,an improved region correlation denoising algorithm is proposed based on the related denoising method in this paper. The wavelet coefficients are evaluated in a region which overcomes the shortcomings of misclassifying the wavelet coefficients with the traditional method. By comparing the two groups of non-stationary signal noise reduction experiments,the results show that the proposed method has better noise reduction effect than traditional wavelet method,both subjective visual effect and objective evaluation index are more advantageous.
作者
王益艳
WANG Yiyan(School of Intelligent Manufacturing,Sichuan University of Arts and Science,Dazhou 635000;Dazhou Industrial Technology Institute of Intelligent Manufacturing,Dazhou 635000)
出处
《计算机与数字工程》
2020年第2期285-289,共5页
Computer & Digital Engineering
基金
达州市科技计划应用基础研究项目(编号:KJJ2015001)
四川文理学院校级重点科研项目(编号:2017KZ003Z)资助。
关键词
非平稳信号
信号降噪
小波变换
相关性度量
non-stationary signal
signal denoising
wavelet transform
correlation measure
