Blind Denoising of Mixed Gaussian-impulse Noise by Single CNN

Ryo Abiko, Masaaki Ikehara

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

2 Citations (Scopus)

Abstract

The removal of mixed noise is a stiff problem since the distribution of the noise cannot be predicted accurately. The most common mixed noise is the combination of Additive White Gaussian Noise (AWGN) and Impulse Noise (IN). Many methods first attempt to remove IN but it might collapse the texture of the image. In this paper, we propose a new learning-based method using convolutional neural network (CNN) for removing mixed gaussian-impulse noise. Since our denoising network can remove various level of mixed noise, neither the preprocessing for removing IN nor noise-level estimation is necessary.

Original languageEnglish
Title of host publication2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1717-1721
Number of pages5
ISBN (Electronic)9781479981311
DOIs
Publication statusPublished - 2019 May 1
Event44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Brighton, United Kingdom
Duration: 2019 May 122019 May 17

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2019-May
ISSN (Print)1520-6149

Conference

Conference44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019
CountryUnited Kingdom
CityBrighton
Period19/5/1219/5/17

Fingerprint

Impulse noise
Neural networks
Gaussian noise (electronic)
Textures

Keywords

  • convolutional neural network
  • deep learning
  • Image denoising
  • Mixed noise

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Abiko, R., & Ikehara, M. (2019). Blind Denoising of Mixed Gaussian-impulse Noise by Single CNN. In 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings (pp. 1717-1721). [8683878] (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2019-May). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2019.8683878

Blind Denoising of Mixed Gaussian-impulse Noise by Single CNN. / Abiko, Ryo; Ikehara, Masaaki.

2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. p. 1717-1721 8683878 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2019-May).

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

Abiko, R & Ikehara, M 2019, Blind Denoising of Mixed Gaussian-impulse Noise by Single CNN. in 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings., 8683878, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, vol. 2019-May, Institute of Electrical and Electronics Engineers Inc., pp. 1717-1721, 44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019, Brighton, United Kingdom, 19/5/12. https://doi.org/10.1109/ICASSP.2019.8683878
Abiko R, Ikehara M. Blind Denoising of Mixed Gaussian-impulse Noise by Single CNN. In 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. p. 1717-1721. 8683878. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). https://doi.org/10.1109/ICASSP.2019.8683878
Abiko, Ryo ; Ikehara, Masaaki. / Blind Denoising of Mixed Gaussian-impulse Noise by Single CNN. 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 1717-1721 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).
@inproceedings{11d8397867fe457aac3dc6fc8303b46f,
title = "Blind Denoising of Mixed Gaussian-impulse Noise by Single CNN",
abstract = "The removal of mixed noise is a stiff problem since the distribution of the noise cannot be predicted accurately. The most common mixed noise is the combination of Additive White Gaussian Noise (AWGN) and Impulse Noise (IN). Many methods first attempt to remove IN but it might collapse the texture of the image. In this paper, we propose a new learning-based method using convolutional neural network (CNN) for removing mixed gaussian-impulse noise. Since our denoising network can remove various level of mixed noise, neither the preprocessing for removing IN nor noise-level estimation is necessary.",
keywords = "convolutional neural network, deep learning, Image denoising, Mixed noise",
author = "Ryo Abiko and Masaaki Ikehara",
year = "2019",
month = "5",
day = "1",
doi = "10.1109/ICASSP.2019.8683878",
language = "English",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1717--1721",
booktitle = "2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings",

}

TY - GEN

T1 - Blind Denoising of Mixed Gaussian-impulse Noise by Single CNN

AU - Abiko, Ryo

AU - Ikehara, Masaaki

PY - 2019/5/1

Y1 - 2019/5/1

N2 - The removal of mixed noise is a stiff problem since the distribution of the noise cannot be predicted accurately. The most common mixed noise is the combination of Additive White Gaussian Noise (AWGN) and Impulse Noise (IN). Many methods first attempt to remove IN but it might collapse the texture of the image. In this paper, we propose a new learning-based method using convolutional neural network (CNN) for removing mixed gaussian-impulse noise. Since our denoising network can remove various level of mixed noise, neither the preprocessing for removing IN nor noise-level estimation is necessary.

AB - The removal of mixed noise is a stiff problem since the distribution of the noise cannot be predicted accurately. The most common mixed noise is the combination of Additive White Gaussian Noise (AWGN) and Impulse Noise (IN). Many methods first attempt to remove IN but it might collapse the texture of the image. In this paper, we propose a new learning-based method using convolutional neural network (CNN) for removing mixed gaussian-impulse noise. Since our denoising network can remove various level of mixed noise, neither the preprocessing for removing IN nor noise-level estimation is necessary.

KW - convolutional neural network

KW - deep learning

KW - Image denoising

KW - Mixed noise

UR - http://www.scopus.com/inward/record.url?scp=85069463156&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85069463156&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2019.8683878

DO - 10.1109/ICASSP.2019.8683878

M3 - Conference contribution

AN - SCOPUS:85069463156

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

SP - 1717

EP - 1721

BT - 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -