Adaptive wavelet thresholding for image denoising and compression

被引:1885
作者
Chang, SG
Yu, B
Vetterli, M
机构
[1] Univ Calif Berkeley, Dept Elect Engn & Comp Sci, Berkeley, CA 94720 USA
[2] Univ Calif Berkeley, Dept Stat, Berkeley, CA 94720 USA
[3] Swiss Fed Inst Technol, Lab Audiovisual Commun, CH-1015 Lausanne, Switzerland
基金
美国国家科学基金会;
关键词
adaptive method; image compression; image denoising; image restoration; wavelet thresholding;
D O I
10.1109/83.862633
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The first part of this paper proposes an adaptive, data-driven threshold for image denoising via wavelet soft-thresholding, The threshold is derived in a Bayesian framework, and the prior used on the wavelet coefficients is the generalized Gaussian distribution (GGD) widely used in image processing applications, The proposed threshold is simple and closed-form, and it is adaptive to each subband because it depends on data-driven estimates of the parameters. Experimental results show that the proposed method, called BayesShrink, is typically within 5% of the MSE of the best soft-thresholding benchmark with the image assumed known, It also outperforms Donoho and Johnstone's SureShrink most of the time. The second part of the paper attempts to further validate recent claims that lossy compression can be used for denoising, The BayesShrink threshold can aid in the parameter selection of a coder designed with the intention of denoising, and thus achieving simultaneous denoising and compression. Specifically, the zero-zone in the quantization step of compression is analogous to the threshold value in the thresholding function. The remaining coder design parameters are chosen based on a criterion derived from Rissanen's minimum description length (MDL) principle, Experiments show that this compression method does indeed remove noise significantly, especially for large noise power, However, it introduces quantization noise and should he used only if bitrate were an additional concern to denoising.
引用
收藏
页码:1532 / 1546
页数:15
相关论文
共 36 条
  • [1] Wavelet thresholding via a Bayesian approach
    Abramovich, F
    Sapatinas, T
    Silverman, BW
    [J]. JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY, 1998, 60 : 725 - 749
  • [2] [Anonymous], 1995, WAVELETS STAT
  • [3] Image coding using wavelet transform
    Antonini, Marc
    Barlaud, Michel
    Mathieu, Pierre
    Daubechies, Ingrid
    [J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 1992, 1 (02) : 205 - 220
  • [4] BUCKHEIT J, WAVELAB TOOLKIT
  • [5] Nonlinear wavelet image processing: Variational problems, compression, and noise removal through wavelet shrinkage
    Chambolle, A
    DeVore, RA
    Lee, NY
    Lucier, BJ
    [J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 1998, 7 (03) : 319 - 335
  • [6] Chang S. G., 1997, P C INF SCI SYST BAL, P568
  • [7] Spatially adaptive wavelet thresholding with context modeling for image denoising
    Chang, SG
    Yu, B
    Vetterli, M
    [J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 2000, 9 (09) : 1522 - 1531
  • [8] CHANG SG, 1997, P IEEE INT C IM PROC, V1, P604
  • [9] Adaptive Bayesian wavelet shrinkage
    Chipman, HA
    Kolaczyk, ED
    McCullogh, RE
    [J]. JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1997, 92 (440) : 1413 - 1421
  • [10] Multiple shrinkage and subset selection in wavelets
    Clyde, M
    Parmigiani, G
    Vidakovic, B
    [J]. BIOMETRIKA, 1998, 85 (02) : 391 - 401