Image denoising via adjustment of wavelet coefficient magnitude correlation

J. Portilla, Eero Simoncelli

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We describe a novel method of removing additive white noise of known variance from photographic images. The method is based on a characterization of statistical properties of natural images represented in a complex wavelet decomposition. Specifically, we decompose the noisy image into wavelet subbands, estimate the autocorrelation of both the noise-free raw coefficients and their magnitudes within each subband, impose these statistics by projecting onto the space of images having the desired autocorrelations, and reconstruct an image from the modified wavelet coefficients. This process is applied repeatedly, and can be accelerated to produce optimal results in only a few iterations. Denoising results compare favorably to three reference methods, both perceptually and in terms of mean squared error.

Original languageEnglish (US)
Title of host publicationIEEE International Conference on Image Processing
Volume3
StatePublished - 2000
EventInternational Conference on Image Processing (ICIP 2000) - Vancouver, BC, Canada
Duration: Sep 10 2000Sep 13 2000

Other

OtherInternational Conference on Image Processing (ICIP 2000)
CountryCanada
CityVancouver, BC
Period9/10/009/13/00

Fingerprint

Image denoising
Autocorrelation
Wavelet decomposition
White noise
Statistics

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Hardware and Architecture
  • Electrical and Electronic Engineering

Cite this

Portilla, J., & Simoncelli, E. (2000). Image denoising via adjustment of wavelet coefficient magnitude correlation. In IEEE International Conference on Image Processing (Vol. 3)

Image denoising via adjustment of wavelet coefficient magnitude correlation. / Portilla, J.; Simoncelli, Eero.

IEEE International Conference on Image Processing. Vol. 3 2000.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Portilla, J & Simoncelli, E 2000, Image denoising via adjustment of wavelet coefficient magnitude correlation. in IEEE International Conference on Image Processing. vol. 3, International Conference on Image Processing (ICIP 2000), Vancouver, BC, Canada, 9/10/00.
Portilla J, Simoncelli E. Image denoising via adjustment of wavelet coefficient magnitude correlation. In IEEE International Conference on Image Processing. Vol. 3. 2000
Portilla, J. ; Simoncelli, Eero. / Image denoising via adjustment of wavelet coefficient magnitude correlation. IEEE International Conference on Image Processing. Vol. 3 2000.
@inproceedings{287fe8c7349a4664a1fa868fdb99a66e,
title = "Image denoising via adjustment of wavelet coefficient magnitude correlation",
abstract = "We describe a novel method of removing additive white noise of known variance from photographic images. The method is based on a characterization of statistical properties of natural images represented in a complex wavelet decomposition. Specifically, we decompose the noisy image into wavelet subbands, estimate the autocorrelation of both the noise-free raw coefficients and their magnitudes within each subband, impose these statistics by projecting onto the space of images having the desired autocorrelations, and reconstruct an image from the modified wavelet coefficients. This process is applied repeatedly, and can be accelerated to produce optimal results in only a few iterations. Denoising results compare favorably to three reference methods, both perceptually and in terms of mean squared error.",
author = "J. Portilla and Eero Simoncelli",
year = "2000",
language = "English (US)",
volume = "3",
booktitle = "IEEE International Conference on Image Processing",

}

TY - GEN

T1 - Image denoising via adjustment of wavelet coefficient magnitude correlation

AU - Portilla, J.

AU - Simoncelli, Eero

PY - 2000

Y1 - 2000

N2 - We describe a novel method of removing additive white noise of known variance from photographic images. The method is based on a characterization of statistical properties of natural images represented in a complex wavelet decomposition. Specifically, we decompose the noisy image into wavelet subbands, estimate the autocorrelation of both the noise-free raw coefficients and their magnitudes within each subband, impose these statistics by projecting onto the space of images having the desired autocorrelations, and reconstruct an image from the modified wavelet coefficients. This process is applied repeatedly, and can be accelerated to produce optimal results in only a few iterations. Denoising results compare favorably to three reference methods, both perceptually and in terms of mean squared error.

AB - We describe a novel method of removing additive white noise of known variance from photographic images. The method is based on a characterization of statistical properties of natural images represented in a complex wavelet decomposition. Specifically, we decompose the noisy image into wavelet subbands, estimate the autocorrelation of both the noise-free raw coefficients and their magnitudes within each subband, impose these statistics by projecting onto the space of images having the desired autocorrelations, and reconstruct an image from the modified wavelet coefficients. This process is applied repeatedly, and can be accelerated to produce optimal results in only a few iterations. Denoising results compare favorably to three reference methods, both perceptually and in terms of mean squared error.

UR - http://www.scopus.com/inward/record.url?scp=0034442998&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034442998&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0034442998

VL - 3

BT - IEEE International Conference on Image Processing

ER -