A bivariate shrinkage function for wavelet-based denoising

Levent Şendur, Ivan W. Selesnick

Research output: Contribution to journalConference article

Abstract

Most simple nonlinear thresholding rules for wavelet-based denoising assume the wavelet coefficients are independent. However, wavelet coefficients of natural images have significant dependency. In this paper, a new heavy-tailed bivariate pdf is proposed to model the statistics of wavelet coefficients, and a simple nonlinear threshold function (shrinkage function) is derived from the pdf using Bayesian estimation theory. The new shrinkage function does not assume the independence of wavelet coefficients.

Original languageEnglish (US)
Pages (from-to)II/1261-II/1264
JournalICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2
DOIs
StatePublished - 2002
Event2002 IEEE International Conference on Acoustic, Speech and Signal Processing - Orlando, FL, United States
Duration: May 13 2002May 17 2002

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'A bivariate shrinkage function for wavelet-based denoising'. Together they form a unique fingerprint.

  • Cite this