Denoising via nonorthogonal wavelet transforms
In most applications in signal analysis and image processing the observed data sets are contami\-nated by noise. An important issue in the context of the signal decontamination issue is how to estimate the underlying clear signal from the set of noisy observations. A method proposed earlier [\textit{D. L. Donoho} and \textit{I. M. Johnstone}, Biometrika 81, 425--455 (1994; Zbl 0815.62019); \textit{D. L. Donoho}, IEEE Trans. Inf. Theory 41, 613--627 (1995; Zbl 0820.62002)], which is concerned with the situation of detecting a signal in additive Gaussian white noise, provides a step forward in solving the denoising problem via thresholding of orthogonal wavelet coefficients. The present paper contains the stochastic noise model and reexamines the three main results of this denoising procedure, namely results on the threshold-selection, the quality of the \(L^2\)-approximation, and the smoothness characterization of the denoised function. These three topics are investigated with respect to biorthogonal and redundant wavelet transforms. Specifically, the authors study whether the original denoising procedure proposed by Donoho and Johnstone for orthogonal discrete wavelet transforms can be transfered to the case of using non-orthogonal wavelet transforms. Of course, the application of non-orthogonal wavelet transforms leads to the appearance of non-zero cross-correlation functions. The analysis demonstrates that a generalization of the denoising scheme to non-orthogonal wavelet transforms requires some modifications of the original decontamination scheme. It is evident that non-zero cross-correlations require a larger scale-wavelet dependent threshold than the uniform threshold for orthogonal discrete wavelet transforms. For the entire collection see [Zbl 0996.00017].
- Wavelet thresholding for non-(necessarily) Gaussian noise: A preliminary report
- Multiple wavelet threshold estimation by generalized cross validation for images with correlated noise
- A comparative study of several methods in kernel density estimation
- Statistical analysis of wavelet spectrum thresholding rules in order to suppress noise in signal
- Wavelet thresholding for non-necessarily Gaussian noise: idealism
- Nonlinear wavelet thresholding: a recursive method to determine the optimal denoising threshold
- Noise reduction by wavelet thresholding
- The asymptotic behavior of the optimal threshold minimizing the probability-of-error criterion
- Second-generation wavelet denoising methods for irregularly spaced data in two dimensions
- Smoothness estimates for soft-threshold denoising via translation-invariant wavelet transforms
- An on-line orthogonal wavelet denoising algorithm for high-resolution surface scans
- Statistically based multiwavelet denoising
- Signal and image denoising via wavelet thresholding: Orthogonal and biorthogonal, scalar and multiple wavelet transforms
- IMAGE AND AUDIO-SPEECH DENOISING BASED ON HIGHER-ORDER STATISTICAL MODELING OF WAVELET COEFFICIENTS AND LOCAL VARIANCE ESTIMATION
- scientific article; zbMATH DE number 6001074 (Why is no real title available?)
- Redundant wavelet processing on the half-axis with applications to signal denoising with small delays: theory and experiments
- scientific article; zbMATH DE number 5151401 (Why is no real title available?)
- SUBBAND VARIANCE COMPUTATION OF HOMOSCEDASTIC ADDITIVE NOISE IN DISCRETE DYADIC WAVELET TRANSFORM
- scientific article; zbMATH DE number 5525419 (Why is no real title available?)
- scientific article; zbMATH DE number 1271140 (Why is no real title available?)
- scientific article; zbMATH DE number 724718 (Why is no real title available?)
- Denoising via block Wiener filtering in wavelet domain
- NOISY SIGNAL COMPRESSION BY WAVELET TRANSFORM WITH OPTIMAL DOWNSAMPLING
- Data-Driven and Optimal Denoising of a Signal and Recovery of Its Derivative Using Multiwavelets
- Estimation of nonlinear autoregressive models using design-adapted wavelets
- Lifting scheme of symmetric tight wavelets frames
This page was built for publication: Denoising via nonorthogonal wavelet transforms
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4424419)
