Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Optical Technique》 2009-03
Add to Favorite Get Latest Update

New algorithm for image de-noising using node threshold wavelet packet transform

ZHENG De-zhong,CUI Fa-yi(Measurement Technology and Instrumentation Key Lab of Hebei Province,Yanshan University,Qinhuangdao 066004,China)  
Wavelet packet transform,which is derived from wavelet transform,can be considered as a linear combination of general wavelet functions and has flexible time-frequency analysis ability.With decomposition level increases,wavelet packet decomposition can focus in range of all frequency.A new algorithm is proposed for image de-noising using node threshold wavelet packet transform.Wavelet packet transform is used for noisy image decomposition.This method operates threshold at sub-band of image signal,uses soft threshold to deal with wavelet packet transform coefficients with different thresholds,and spectral entropy method is applied to estimate the node noise.Finally,the quality of image after de-noising is evaluated using PSNR(Point Signal Noise Ratio).Experiments show that this algorithm has better image de-noising performance,compared with algorithms for wavelet packet image de-noising using other threshold methods.
【Fund】: 国家教育部博士点基金(200602600)
【CateGory Index】: TP391.41
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved