摘要
在D.L.Dohono和I.M.Johnstone提出的多分辨分析小波阈值去噪算法的基础上,提出了一种新的阈值函数。与传统的硬阈值和软阈值比,此函数不仅易计算,且具有优越的数学特性和清晰的物理意义。试验结果表明,该方法可有效地去除白噪声干扰,无论在视觉效果还是在信噪比和均方误差定量指标上均明显优于常用的软、硬阈值及改进的软硬阈值折中算法,充分体现出小波阈值去噪方法的优越性。
Based on the Multi-analysis wavelet threshold denosing method which put forward by D. L. Dohono and I. M. Johnstone,a new threshold function is proposed. This new thresholding function has many advantages over the classical soft and hard thresholdding function. It is clear in physics meaning and simple in expression. The results show that this improved method is effective in removing white noise . and gives better RMSE performance and SNR gains than the soft and hard thmsholding methods and embadies the advantages of the wavelet threshold denoising method more fully.
出处
《压电与声光》
CSCD
北大核心
2008年第1期93-95,共3页
Piezoelectrics & Acoustooptics
基金
重庆市自然科学基金资助项目(CSTC2007BA2023)
重庆市教育委员会科学技术研究项目(KJ060613)
关键词
小波变换
硬阈值去噪
软阈值去噪
阈值函数
wavelet transform
hard-thresholding
soft-thresholding
threshold function
