A machine learning framework for adaptive combination of signal denoising methods

David K. Hammond, Eero Simoncelli

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

Abstract

We present a general framework for combination of two distinct local denoising methods. Interpolation between the two methods is controlled by a spatially varying decision function. Assuming the availability of clean training data, we formulate a learning problem for determining the decision function. As an example application we use Weighted Kernel Ridge Regression to solve this learning problem for a pair of wavelet-based image denoising algorithms, yielding a "hybrid" denoising algorithm whose performance surpasses that of either initial method.

Original languageEnglish (US)
Title of host publication2007 IEEE International Conference on Image Processing, ICIP 2007 Proceedings
Volume6
DOIs
StatePublished - 2006
Event14th IEEE International Conference on Image Processing, ICIP 2007 - San Antonio, TX, United States
Duration: Sep 16 2007Sep 19 2007

Other

Other14th IEEE International Conference on Image Processing, ICIP 2007
CountryUnited States
CitySan Antonio, TX
Period9/16/079/19/07

Fingerprint

Signal denoising
Learning systems
Image denoising
Interpolation
Availability

Keywords

  • Image denoising
  • Image processing
  • Kernel Ridge Regression
  • Machine learning

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Hammond, D. K., & Simoncelli, E. (2006). A machine learning framework for adaptive combination of signal denoising methods. In 2007 IEEE International Conference on Image Processing, ICIP 2007 Proceedings (Vol. 6). [4379513] https://doi.org/10.1109/ICIP.2007.4379513

A machine learning framework for adaptive combination of signal denoising methods. / Hammond, David K.; Simoncelli, Eero.

2007 IEEE International Conference on Image Processing, ICIP 2007 Proceedings. Vol. 6 2006. 4379513.

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

Hammond, DK & Simoncelli, E 2006, A machine learning framework for adaptive combination of signal denoising methods. in 2007 IEEE International Conference on Image Processing, ICIP 2007 Proceedings. vol. 6, 4379513, 14th IEEE International Conference on Image Processing, ICIP 2007, San Antonio, TX, United States, 9/16/07. https://doi.org/10.1109/ICIP.2007.4379513
Hammond DK, Simoncelli E. A machine learning framework for adaptive combination of signal denoising methods. In 2007 IEEE International Conference on Image Processing, ICIP 2007 Proceedings. Vol. 6. 2006. 4379513 https://doi.org/10.1109/ICIP.2007.4379513
Hammond, David K. ; Simoncelli, Eero. / A machine learning framework for adaptive combination of signal denoising methods. 2007 IEEE International Conference on Image Processing, ICIP 2007 Proceedings. Vol. 6 2006.
@inproceedings{2818e141418b4972858d79f054e81a1a,
title = "A machine learning framework for adaptive combination of signal denoising methods",
abstract = "We present a general framework for combination of two distinct local denoising methods. Interpolation between the two methods is controlled by a spatially varying decision function. Assuming the availability of clean training data, we formulate a learning problem for determining the decision function. As an example application we use Weighted Kernel Ridge Regression to solve this learning problem for a pair of wavelet-based image denoising algorithms, yielding a {"}hybrid{"} denoising algorithm whose performance surpasses that of either initial method.",
keywords = "Image denoising, Image processing, Kernel Ridge Regression, Machine learning",
author = "Hammond, {David K.} and Eero Simoncelli",
year = "2006",
doi = "10.1109/ICIP.2007.4379513",
language = "English (US)",
isbn = "1424414377",
volume = "6",
booktitle = "2007 IEEE International Conference on Image Processing, ICIP 2007 Proceedings",

}

TY - GEN

T1 - A machine learning framework for adaptive combination of signal denoising methods

AU - Hammond, David K.

AU - Simoncelli, Eero

PY - 2006

Y1 - 2006

N2 - We present a general framework for combination of two distinct local denoising methods. Interpolation between the two methods is controlled by a spatially varying decision function. Assuming the availability of clean training data, we formulate a learning problem for determining the decision function. As an example application we use Weighted Kernel Ridge Regression to solve this learning problem for a pair of wavelet-based image denoising algorithms, yielding a "hybrid" denoising algorithm whose performance surpasses that of either initial method.

AB - We present a general framework for combination of two distinct local denoising methods. Interpolation between the two methods is controlled by a spatially varying decision function. Assuming the availability of clean training data, we formulate a learning problem for determining the decision function. As an example application we use Weighted Kernel Ridge Regression to solve this learning problem for a pair of wavelet-based image denoising algorithms, yielding a "hybrid" denoising algorithm whose performance surpasses that of either initial method.

KW - Image denoising

KW - Image processing

KW - Kernel Ridge Regression

KW - Machine learning

UR - http://www.scopus.com/inward/record.url?scp=48149087583&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=48149087583&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2007.4379513

DO - 10.1109/ICIP.2007.4379513

M3 - Conference contribution

AN - SCOPUS:48149087583

SN - 1424414377

SN - 9781424414376

VL - 6

BT - 2007 IEEE International Conference on Image Processing, ICIP 2007 Proceedings

ER -