Automatic parameter tuning for image denoising with learned sparsifying transforms

Luke Pfister, Yoram Bresler

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

Abstract

Data-driven and learning-based sparse signal models outperform analytical models (e.g, wavelets), for image denoising, but require careful parameter tuning to reach peak performance. In this work, we provide a solution to the problem of parameter tuning for image denoising with transform sparsity regularization. We show that by viewing a learned sparsifying transform as a filter bank we can utilize the SURELET denoising algorithm to automatically tune parameters for an image denoising task. Numerical experiments show that combining SURELET with a learned sparsifying transform provides the best of both worlds. Our approach requires no parameter tuning for image denoising, yet outperforms SURELET with analytic transforms and matches the performance of transform learning denoising with hand-tuned parameters.

Original languageEnglish (US)
Title of host publication2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages6040-6044
Number of pages5
ISBN (Electronic)9781509041176
DOIs
StatePublished - Jun 16 2017
Event2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - New Orleans, United States
Duration: Mar 5 2017Mar 9 2017

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN (Print)1520-6149

Other

Other2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017
CountryUnited States
CityNew Orleans
Period3/5/173/9/17

Fingerprint

Image denoising
Tuning
Filter banks
Analytical models
Experiments

Keywords

  • Sparse representations
  • Sparsifying transform learning
  • Stein unbiased risk estimator
  • image denoising
  • linear expansion of thresholds (LET)

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Pfister, L., & Bresler, Y. (2017). Automatic parameter tuning for image denoising with learned sparsifying transforms. In 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings (pp. 6040-6044). [7953316] (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2017.7953316

Automatic parameter tuning for image denoising with learned sparsifying transforms. / Pfister, Luke; Bresler, Yoram.

2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. p. 6040-6044 7953316 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

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

Pfister, L & Bresler, Y 2017, Automatic parameter tuning for image denoising with learned sparsifying transforms. in 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings., 7953316, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 6040-6044, 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017, New Orleans, United States, 3/5/17. https://doi.org/10.1109/ICASSP.2017.7953316
Pfister L, Bresler Y. Automatic parameter tuning for image denoising with learned sparsifying transforms. In 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2017. p. 6040-6044. 7953316. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). https://doi.org/10.1109/ICASSP.2017.7953316
Pfister, Luke ; Bresler, Yoram. / Automatic parameter tuning for image denoising with learned sparsifying transforms. 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 6040-6044 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).
@inproceedings{ef5b01b975f6404b998a8d331d3ccb72,
title = "Automatic parameter tuning for image denoising with learned sparsifying transforms",
abstract = "Data-driven and learning-based sparse signal models outperform analytical models (e.g, wavelets), for image denoising, but require careful parameter tuning to reach peak performance. In this work, we provide a solution to the problem of parameter tuning for image denoising with transform sparsity regularization. We show that by viewing a learned sparsifying transform as a filter bank we can utilize the SURELET denoising algorithm to automatically tune parameters for an image denoising task. Numerical experiments show that combining SURELET with a learned sparsifying transform provides the best of both worlds. Our approach requires no parameter tuning for image denoising, yet outperforms SURELET with analytic transforms and matches the performance of transform learning denoising with hand-tuned parameters.",
keywords = "Sparse representations, Sparsifying transform learning, Stein unbiased risk estimator, image denoising, linear expansion of thresholds (LET)",
author = "Luke Pfister and Yoram Bresler",
year = "2017",
month = "6",
day = "16",
doi = "10.1109/ICASSP.2017.7953316",
language = "English (US)",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "6040--6044",
booktitle = "2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings",
address = "United States",

}

TY - GEN

T1 - Automatic parameter tuning for image denoising with learned sparsifying transforms

AU - Pfister, Luke

AU - Bresler, Yoram

PY - 2017/6/16

Y1 - 2017/6/16

N2 - Data-driven and learning-based sparse signal models outperform analytical models (e.g, wavelets), for image denoising, but require careful parameter tuning to reach peak performance. In this work, we provide a solution to the problem of parameter tuning for image denoising with transform sparsity regularization. We show that by viewing a learned sparsifying transform as a filter bank we can utilize the SURELET denoising algorithm to automatically tune parameters for an image denoising task. Numerical experiments show that combining SURELET with a learned sparsifying transform provides the best of both worlds. Our approach requires no parameter tuning for image denoising, yet outperforms SURELET with analytic transforms and matches the performance of transform learning denoising with hand-tuned parameters.

AB - Data-driven and learning-based sparse signal models outperform analytical models (e.g, wavelets), for image denoising, but require careful parameter tuning to reach peak performance. In this work, we provide a solution to the problem of parameter tuning for image denoising with transform sparsity regularization. We show that by viewing a learned sparsifying transform as a filter bank we can utilize the SURELET denoising algorithm to automatically tune parameters for an image denoising task. Numerical experiments show that combining SURELET with a learned sparsifying transform provides the best of both worlds. Our approach requires no parameter tuning for image denoising, yet outperforms SURELET with analytic transforms and matches the performance of transform learning denoising with hand-tuned parameters.

KW - Sparse representations

KW - Sparsifying transform learning

KW - Stein unbiased risk estimator

KW - image denoising

KW - linear expansion of thresholds (LET)

UR - http://www.scopus.com/inward/record.url?scp=85023755207&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85023755207&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2017.7953316

DO - 10.1109/ICASSP.2017.7953316

M3 - Conference contribution

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 6040

EP - 6044

BT - 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -