Wavelet shrinkage: unification of basic thresholding functions and thresholds
This work addresses the unification of some basic functions and thresholds used in non-parametric estimation of signals by shrinkage in the wavelet domain. The soft and hard thresholding functions are presented as degenerate smooth sigmoid-based shrinkage functions. The shrinkage achieved by this new family of sigmoid-based functions is then shown to be equivalent to a regularization of wavelet coefficients associated with a class of penalty functions. Some sigmoid-based penalty functions are calculated, and their properties are discussed. The unification also concerns the universal and the minimax thresholds used to calibrate standard soft and hard thresholding functions: these thresholds pertain to a wide class of thresholds, called the detection thresholds. These thresholds depend on two parameters describing the sparsity degree for the wavelet representation of a signal. It is also shown that the non-degenerate sigmoid shrinkage adjusted with the new detection thresholds is as performant as the best up-to-date parametric and computationally expensive method. This justifies the relevance of sigmoid shrinkage for noise reduction in large databases or large size images.
KeywordsNon-parametric estimation Wavelets Shrinkage function Penalty function Detection thresholds
Unable to display preview. Download preview PDF.
- 4.Atto, A.M., Pastor, D., Mercier, G.: Detection threshold for non-parametric estimation. Signal, Image and Video Processing, vol. 2(3). Springer, Heidelberg (2008)Google Scholar
- 5.Simoncelli, E.P., Adelson, E.H.: Noise removal via bayesian wavelet coring. IEEE Int. Conf. Image Proc. (ICIP) 379–382 (1996)Google Scholar
- 7.Şendur L., Selesnick I.V.: Bivariate shrinkage functions for wavelet-based denoising exploiting interscale dependency. IEEE Trans. Signal Process. 11, 2744–2756 (2002)Google Scholar
- 14.Atto, A.M., Pastor, D., Mercier, G.: Smooth sigmoid wavelet shrinkage for non-parametric estimation. IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP, Las Vegas, Nevada, USA, 30 March–4 April (2008)Google Scholar
- 15.Pastor, D., Atto, A.M.: Sparsity from binary hypothesis testing and application to non-parametric estimation. European Signal Processing Conference, EUSIPCO, Lausanne, Switzerland, August 25–29 (2008)Google Scholar
- 16.Benedetto, J.J., Frasier, M.W.: Wavelets : Mathematics and applications. CRC Press, Boca Raton (1994), chap. 9: Wavelets, probability, and statistics: Some bridges, by Christian Houdré, pp. 365–398Google Scholar
- 20.Atto, A.M., Pastor, D.: Limit distributions for wavelet packet coefficients of band-limited stationary random processes. European Signal Processing Conference, EUSIPCO, Lausanne, Switzerland, 25–28 August (2008)Google Scholar
- 29.Coifman, R.R., Donoho, D.L.: Translation invariant de-noising. Lect. Notes Stat. (103), 125–150 (1995)Google Scholar
- 36.Müller J.W.: Possible advantages of a robust evaluation of comparisons. J. Res. Natl. Inst. Stand. Technol. 105(4), 551–555 (2000)Google Scholar