计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (12): 141-145.

• 数据库、信号与信息处理 • 上一篇    下一篇

小波阈值去噪算法的新改进

叶重元,黄永东   

  1. 北方民族大学 信息与系统科学研究所,银川 750021
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-04-21 发布日期:2011-04-21

New improvement of wavelet threshold denoising algorithm

YE Chongyuan,HUANG Yongdong   

  1. Institute of Information and System Science,North University for Nationalities,Yinchuan 750021,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-04-21 Published:2011-04-21

摘要: 在D.L.Donoho和I.M.Johnstone提出的多分辨分析小波阈值去噪方法的基础上,提出了一种新的阈值函数。与传统的硬阈值、软阈值、半软阈值以及已有的改进阈值函数相比,该函数不仅易于计算,而且具有优越的数学特性。通过Heavisine和Droppler信号的仿真实验表明,新的阈值函数可以有效地去除白噪声干扰,无论在视觉效果上还是在信噪比和均方误差定量指标上,均优于上述几种去噪方法,具有较高的实用价值。

关键词: 小波变换, 去噪, 阈值函数

Abstract: A new threshold function is put forward,which is based on the multiresolution analysis wavelet threshold denoising method introduced by D.L.Donoho and I.M.Johnstone.The new threshold function is not only easy to compute but also has perfect mathematical properties by contrast to the classical hard,soft,semisoft threshold function and several existing improved threshold functions.The simulation experiments for Heavisine and Droppler signals show that the new threshold function can suppress the white noise effectively,it is better than above mentioned denoising methods in the visual effect and Signal Noise Ratio(SNR) and Mean Square Error(MSE).Thus,it has high practical value.

Key words: wavelet transform, denoising, threshold function