Fast Poisson noise removal by biorthogonal Haar domain hypothesis testing

DOI10.1016/J.STAMET.2008.02.004MaRDI QIDQ713874zbMATH OpenOpenAlexFDO

Authors Bo Zhang, S. W. Digel, Jalal Fadili, J.-L. Starck

Publication date 19 October 2012

Published in Statistical Methodology (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/math/0608631

zbMATH Keywords

Fisher approximationbiorthogonal Haar waveletsPoisson intensity estimationwavelet hypothesis testing

Mathematics Subject Classification ID

Nonparametric hypothesis testing (62G10) Nontrigonometric harmonic analysis involving wavelets and other special systems (42C40) Non-Markovian processes: hypothesis testing (62M07)

Abstract: Methods based on hypothesis tests (HTs) in the Haar domain are widely used to denoise Poisson count data. Facing large datasets or real-time applications, Haar-based denoisers have to use the decimated transform to meet limited-memory or computation-time constraints. Unfortunately, for regular underlying intensities, decimation yields discontinuous estimates and strong "staircase" artifacts. In this paper, we propose to combine the HT framework with the decimated biorthogonal Haar (Bi-Haar) transform instead of the classical Haar. The Bi-Haar filter bank is normalized such that the p-values of Bi-Haar coefficients (pBH) provide good approximation to those of Haar (pH) for high-intensity settings or large scales; for low-intensity settings and small scales, we show that pBH are essentially upper-bounded by pH. Thus, we may apply the Haar-based HTs to Bi-Haar coefficients to control a prefixed false positive rate. By doing so, we benefit from the regular Bi-Haar filter bank to gain a smooth estimate while always maintaining a low computational complexity. A Fisher-approximation-based threshold imple- menting the HTs is also established. The efficiency of this method is illustrated on an example of hyperspectral-source-flux estimation.

Recommendations

• A fast algorithm for deconvolution and Poisson noise removal
• Poisson shot noise removal by an oracular non-local algorithm
• Likelihood ratio Haar variance stabilization and normalization for Poisson and other non-Gaussian noise removal
• A modified Chambolle-Pock primal-dual algorithm for Poisson noise removal
• Fast interscale wavelet denoising of Poisson-corrupted images
• A nonlocal low rank model for Poisson noise removal
• Total variation-based phase retrieval for Poisson noise removal
• Efficient gradient projection methods for edge-preserving removal of Poisson noise
• Poisson noise reduction with non-local PCA
• Adaptive total variation regularization based scheme for Poisson noise removal

Cites work

• scientific article; zbMATH DE number 3165877 (Why is no real title available?)
• scientific article; zbMATH DE number 1271137 (Why is no real title available?)
• scientific article; zbMATH DE number 720689 (Why is no real title available?)
• scientific article; zbMATH DE number 3051453 (Why is no real title available?)
• scientific article; zbMATH DE number 3061356 (Why is no real title available?)
• A Comparative Simulation Study of Wavelet Shrinkage Estimators for Poisson Counts
• Image Processing and Data Analysis
• On the distribution of the wavelet coefficient for a Poisson noise
• Simple Regularity Criteria for Subdivision Schemes
• The Frequency Distribution of the Difference Between Two Poisson Variates Belonging to Different Populations
• The control of the false discovery rate in multiple testing under dependency.
• Wavelet denoising of Poisson-distributed data and applications

Cited in

(7)

• Some limit results on the Haar-Fisz transform for inhomogeneous Poisson signals
• Likelihood ratio Haar variance stabilization and normalization for Poisson and other non-Gaussian noise removal
• Mean-square filter design for stochastic polynomial systems with Gaussian and Poisson noises
• Optimal mean-square state and parameter estimation for stochastic linear systems with Poisson noises
• scientific article; zbMATH DE number 2156646 (Why is no real title available?)
• Poisson shot noise removal by an oracular non-local algorithm
• Fast interscale wavelet denoising of Poisson-corrupted images

This page was built for publication: Fast Poisson noise removal by biorthogonal Haar domain hypothesis testing

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q713874)