Noise Reduction by Wavelet Thresholding

By Maarten Jansen. 2001

459 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/539fc4735f52e6acc7549142b12d29a2759ad8b8

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Image Denoising Via Sparse and Redundant Representations Over Learned Dictionaries (2006, background): “At first, sparsity of the unitary wavelet coefficients was considered, leading to the celebrated shrinkage algorithm [1]–[9].”
From Sparse Solutions of Systems of Equations to Sparse Modeling of Signals and Images (2009, methodology): “Transform sparsity is also a driving factor for other important signal and image processing problems, including image denoising [50, 51, 27, 43, 53, 52, 144, 124, 96] and image deblurring [76, 75, 74, 41].”
The Harvard Automated Processing Pipeline for Electroencephalography (HAPPE): Standardized Processing Software for Developmental and High-Artifact Data (2018, background): “The coeﬃcients are then subjected to thresholding, such that coeﬃcients with values smaller than the threshold have their contribution to the data substantially suppressed (similar to Rong-Yi and Zhong, 2005; Jansen, 2012).”
Image Denoising Via Learned Dictionaries and Sparse representation (2006, background): “Indeed, at first, sparsity of the unitary wavelet coefficients has been considered, leading to the celebrated shrinkage algorithm [1] [2] [3] [4] [5] [6].”
Adapting to Unknown Smoothness by Aggregation of Thresholded Wavelet Estimators (2006, methodology): “…instance, the RiskShrink and SureShrink methods (see Donoho and Johnstone (1995)), the cross-validation methods (see, for instance, Nason (1995) and Jansen (2001)), the methods based on hypothesis tests (see, for instance, Abramovich, Benjamini, Donoho and Johnstone (2006)), the Lepski methods…”
Why Simple Shrinkage Is Still Relevant for Redundant Representations? (2006, methodology): “Later work in [11]–[13] simplified these ideas and related them to the MAP formulation as presented above, using the prior Prfx x xg = kW W Wx x xk p, with a unitary wavelet transform matrix 3 W W W 2 IR N2N , and 0 p 1.”
Deflecting Adversarial Attacks with Pixel Deflection (2018, background): “[19] observed that hard thresholding results in over-blurring of the input image, while soft thresholding maintains better PSNR.”