Spatially adaptive wavelet denoising using the minimum description length principle

Author

Xie, Jiecheng ; Zhang, Dali ; Xu, Wenli

Author_Institution

Tsinghua Univ., Beijing, China

Volume

13

Issue

2

fYear

2004

Firstpage

179

Lastpage

187

Abstract

This paper presents a new spatially adaptive wavelet denoising method. Based on a doubly stochastic process model of wavelet coefficients, the method gives a new threshold, which varies spatially according to the variances of the coefficients, using the minimum description length (MDL) principle. The new threshold is not only easier to analyze since it is in a closed form, but also provides more facility for future compression than several other methods, almost without deteriorating mean square error risk.

Keywords

data compression; image coding; image denoising; stochastic processes; wavelet transforms; doubly stochastic process model; future compression; mean square error disk; minimum description length; minimum description length principle; spatially adaptive wavelet denoising; wavelet coefficients; Discrete wavelet transforms; Image coding; Mean square error methods; Noise reduction; Partial differential equations; Risk analysis; Statistics; Stochastic processes; Wavelet coefficients; Wavelet transforms; Algorithms; Computer Simulation; Image Enhancement; Image Interpretation, Computer-Assisted; Information Storage and Retrieval; Models, Statistical; Reproducibility of Results; Sensitivity and Specificity; Signal Processing, Computer-Assisted; Stochastic Processes;

fLanguage

English

Journal_Title

Image Processing, IEEE Transactions on

Publisher

ieee

ISSN

1057-7149

Type

jour

DOI

10.1109/TIP.2004.823828

Filename

1278333