Frequentist and Bayesian inference for Gaussian-log-Gaussian wavelet trees and statistical signal processing applications

Research output: Contribution to journalJournal articleResearchpeer-review

Abstract

We introduce new estimation methods for a subclass of the Gaussian scale mixture models for wavelet trees by Wainwright, Simoncelli and Willsky that rely on modern results for composite likelihoods and approximate Bayesian inference. Our methodology is illustrated for denoising and edge detection problems in two-dimensional images.
Original languageEnglish
JournalStat
Volume6
Issue number1
Pages (from-to)248-256
Number of pages9
ISSN2049-1573
DOIs
Publication statusPublished - 2017

Fingerprint

Edge detection
Signal processing
Composite materials

Cite this

@article{99905bf9ab554d77bb57ac05c2b79fa9,
title = "Frequentist and Bayesian inference for Gaussian-log-Gaussian wavelet trees and statistical signal processing applications",
abstract = "We introduce new estimation methods for a subclass of the Gaussian scale mixture models for wavelet trees by Wainwright, Simoncelli and Willsky that rely on modern results for composite likelihoods and approximate Bayesian inference. Our methodology is illustrated for denoising and edge detection problems in two-dimensional images.",
author = "Jacobsen, {Christian Robert Dahl} and Jesper M{\o}ller",
year = "2017",
doi = "10.1002/sta4.156",
language = "English",
volume = "6",
pages = "248--256",
journal = "Stat",
issn = "2049-1573",
publisher = "Wiley",
number = "1",

}

Frequentist and Bayesian inference for Gaussian-log-Gaussian wavelet trees and statistical signal processing applications. / Jacobsen, Christian Robert Dahl; Møller, Jesper.

In: Stat, Vol. 6, No. 1, 2017, p. 248-256.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - Frequentist and Bayesian inference for Gaussian-log-Gaussian wavelet trees and statistical signal processing applications

AU - Jacobsen, Christian Robert Dahl

AU - Møller, Jesper

PY - 2017

Y1 - 2017

N2 - We introduce new estimation methods for a subclass of the Gaussian scale mixture models for wavelet trees by Wainwright, Simoncelli and Willsky that rely on modern results for composite likelihoods and approximate Bayesian inference. Our methodology is illustrated for denoising and edge detection problems in two-dimensional images.

AB - We introduce new estimation methods for a subclass of the Gaussian scale mixture models for wavelet trees by Wainwright, Simoncelli and Willsky that rely on modern results for composite likelihoods and approximate Bayesian inference. Our methodology is illustrated for denoising and edge detection problems in two-dimensional images.

U2 - 10.1002/sta4.156

DO - 10.1002/sta4.156

M3 - Journal article

VL - 6

SP - 248

EP - 256

JO - Stat

JF - Stat

SN - 2049-1573

IS - 1

ER -