Denoising based on non local means for ultrasound images with simultaneous multiple noise distributions

Denis H.P. Salvadeo; Isabelle Bloch; Florence Tupin; Nelson D.A. Mascarenhas; Alexandre L.M. Levada; Charles Alban Deledalle; Sonia Dahdouh

doi:10.1109/ICIP.2014.7025546

Denoising based on non local means for ultrasound images with simultaneous multiple noise distributions

Denis H.P. Salvadeo, Isabelle Bloch, Florence Tupin, Nelson D.A. Mascarenhas, Alexandre L.M. Levada, Charles Alban Deledalle, Sonia Dahdouh

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

In this paper, an extension of the framework proposed by Deledalle et al. [1] for Non Local Means (NLM) method is proposed. This extension is a general adaptive method to denoise images containing multiple noises. It takes into account a segmentation stage that indicates the noise type of a given pixel in order to select the similarity measure and suitable parameters to perform the denoising task, considering a certain patch on the image. For instance, it has been experimentally observed that fetal 3D ultrasound images are corrupted by different types of noise, depending on the tissue. Finally, the proposed method is applied to denoise these images, showing very good results.

Original language	English
Title of host publication	2014 IEEE International Conference on Image Processing, ICIP 2014
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	2699-2703
Number of pages	5
ISBN (Electronic)	9781479957514
DOIs	https://doi.org/10.1109/ICIP.2014.7025546
Publication status	Published - 28 Jan 2014
Externally published	Yes

Publication series

Name	2014 IEEE International Conference on Image Processing, ICIP 2014

Keywords

image denoising
multiple noises
non local means
ultrasound image
ultrasound segmentation

Access to Document

10.1109/ICIP.2014.7025546

Cite this

Salvadeo, D. H. P., Bloch, I., Tupin, F., Mascarenhas, N. D. A., Levada, A. L. M., Deledalle, C. A., & Dahdouh, S. (2014). Denoising based on non local means for ultrasound images with simultaneous multiple noise distributions. In 2014 IEEE International Conference on Image Processing, ICIP 2014 (pp. 2699-2703). Article 7025546 (2014 IEEE International Conference on Image Processing, ICIP 2014). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICIP.2014.7025546

Salvadeo, Denis H.P. ; Bloch, Isabelle ; Tupin, Florence et al. / Denoising based on non local means for ultrasound images with simultaneous multiple noise distributions. 2014 IEEE International Conference on Image Processing, ICIP 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 2699-2703 (2014 IEEE International Conference on Image Processing, ICIP 2014).

@inproceedings{5d302695acd645a2a2558a0bd7253ab7,

title = "Denoising based on non local means for ultrasound images with simultaneous multiple noise distributions",

abstract = "In this paper, an extension of the framework proposed by Deledalle et al. [1] for Non Local Means (NLM) method is proposed. This extension is a general adaptive method to denoise images containing multiple noises. It takes into account a segmentation stage that indicates the noise type of a given pixel in order to select the similarity measure and suitable parameters to perform the denoising task, considering a certain patch on the image. For instance, it has been experimentally observed that fetal 3D ultrasound images are corrupted by different types of noise, depending on the tissue. Finally, the proposed method is applied to denoise these images, showing very good results.",

keywords = "image denoising, multiple noises, non local means, ultrasound image, ultrasound segmentation",

author = "Salvadeo, \{Denis H.P.\} and Isabelle Bloch and Florence Tupin and Mascarenhas, \{Nelson D.A.\} and Levada, \{Alexandre L.M.\} and Deledalle, \{Charles Alban\} and Sonia Dahdouh",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.",

year = "2014",

month = jan,

day = "28",

doi = "10.1109/ICIP.2014.7025546",

language = "English",

series = "2014 IEEE International Conference on Image Processing, ICIP 2014",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "2699--2703",

booktitle = "2014 IEEE International Conference on Image Processing, ICIP 2014",

}

Salvadeo, DHP, Bloch, I, Tupin, F, Mascarenhas, NDA, Levada, ALM, Deledalle, CA & Dahdouh, S 2014, Denoising based on non local means for ultrasound images with simultaneous multiple noise distributions. in 2014 IEEE International Conference on Image Processing, ICIP 2014., 7025546, 2014 IEEE International Conference on Image Processing, ICIP 2014, Institute of Electrical and Electronics Engineers Inc., pp. 2699-2703. https://doi.org/10.1109/ICIP.2014.7025546

Denoising based on non local means for ultrasound images with simultaneous multiple noise distributions. / Salvadeo, Denis H.P.; Bloch, Isabelle; Tupin, Florence et al.
2014 IEEE International Conference on Image Processing, ICIP 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 2699-2703 7025546 (2014 IEEE International Conference on Image Processing, ICIP 2014).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Denoising based on non local means for ultrasound images with simultaneous multiple noise distributions

AU - Salvadeo, Denis H.P.

AU - Bloch, Isabelle

AU - Tupin, Florence

AU - Mascarenhas, Nelson D.A.

AU - Levada, Alexandre L.M.

AU - Deledalle, Charles Alban

AU - Dahdouh, Sonia

PY - 2014/1/28

Y1 - 2014/1/28

N2 - In this paper, an extension of the framework proposed by Deledalle et al. [1] for Non Local Means (NLM) method is proposed. This extension is a general adaptive method to denoise images containing multiple noises. It takes into account a segmentation stage that indicates the noise type of a given pixel in order to select the similarity measure and suitable parameters to perform the denoising task, considering a certain patch on the image. For instance, it has been experimentally observed that fetal 3D ultrasound images are corrupted by different types of noise, depending on the tissue. Finally, the proposed method is applied to denoise these images, showing very good results.

AB - In this paper, an extension of the framework proposed by Deledalle et al. [1] for Non Local Means (NLM) method is proposed. This extension is a general adaptive method to denoise images containing multiple noises. It takes into account a segmentation stage that indicates the noise type of a given pixel in order to select the similarity measure and suitable parameters to perform the denoising task, considering a certain patch on the image. For instance, it has been experimentally observed that fetal 3D ultrasound images are corrupted by different types of noise, depending on the tissue. Finally, the proposed method is applied to denoise these images, showing very good results.

KW - image denoising

KW - multiple noises

KW - non local means

KW - ultrasound image

KW - ultrasound segmentation

U2 - 10.1109/ICIP.2014.7025546

DO - 10.1109/ICIP.2014.7025546

M3 - Conference contribution

AN - SCOPUS:84949929075

T3 - 2014 IEEE International Conference on Image Processing, ICIP 2014

SP - 2699

EP - 2703

BT - 2014 IEEE International Conference on Image Processing, ICIP 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Salvadeo DHP, Bloch I, Tupin F, Mascarenhas NDA, Levada ALM, Deledalle CA et al. Denoising based on non local means for ultrasound images with simultaneous multiple noise distributions. In 2014 IEEE International Conference on Image Processing, ICIP 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 2699-2703. 7025546. (2014 IEEE International Conference on Image Processing, ICIP 2014). doi: 10.1109/ICIP.2014.7025546

Denoising based on non local means for ultrasound images with simultaneous multiple noise distributions

Abstract

Publication series

Keywords

Access to Document

Fingerprint

Cite this