De-noising of SRµCT Fiber Images by Total Variation Minimization

Joakim Lindblad; Nataša Sladoje; Tibor Lukic

doi:10.1109/ICPR.2010.1116

De-noising of SRµCT Fiber Images by Total Variation Minimization

Joakim Lindblad
, Nataša Sladoje
, Tibor Lukic

Publication: Chapter in Book/Report/Conference proceeding › Conference paper in proceedings › peer-review

Abstract

SRμCT images of paper and pulp fiber materials are characterized by a low signal to noise ratio. De-noising is therefore a common preprocessing step before segmentation into fiber and background components. We suggest a de-noising method based on total variation minimization using a modified Spectral Conjugate Gradient algorithm. Quantitative evaluation performed on synthetic 3D data and qualitative evaluation on real 3D paper fiber data confirm appropriateness of the suggested method for the particular application

Original language	English
Title of host publication	2010 20th International Conference on Pattern Recognition
Publisher	The Institute of Electrical and Electronics Engineers, Inc.
Pages	4621-4624
Number of pages	4
ISBN (Print)	978-1-4244-7542-1
DOIs	https://doi.org/10.1109/ICPR.2010.1116
Publication status	Published - 2010

Publication series

Series	Proceedings - International Conference On Pattern Recognition
ISSN	1051-4651

Access to Document

10.1109/ICPR.2010.1116

Cite this

@inproceedings{6be9d9a8cc47445d9dc87c4c50818928,

title = "De-noising of SRµCT Fiber Images by Total Variation Minimization",

abstract = "SRμCT images of paper and pulp fiber materials are characterized by a low signal to noise ratio. De-noising is therefore a common preprocessing step before segmentation into fiber and background components. We suggest a de-noising method based on total variation minimization using a modified Spectral Conjugate Gradient algorithm. Quantitative evaluation performed on synthetic 3D data and qualitative evaluation on real 3D paper fiber data confirm appropriateness of the suggested method for the particular application",

author = "Joakim Lindblad and Nata{\v s}a Sladoje and Tibor Lukic",

year = "2010",

doi = "10.1109/ICPR.2010.1116",

language = "English",

isbn = "978-1-4244-7542-1",

series = "Proceedings - International Conference On Pattern Recognition",

pages = "4621--4624",

booktitle = "2010 20th International Conference on Pattern Recognition",

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

}

De-noising of SRµCT Fiber Images by Total Variation Minimization. / Lindblad, Joakim; Sladoje, Nataša; Lukic, Tibor.
2010 20th International Conference on Pattern Recognition. The Institute of Electrical and Electronics Engineers, Inc., 2010. p. 4621-4624 (Proceedings - International Conference On Pattern Recognition).

Publication: Chapter in Book/Report/Conference proceeding › Conference paper in proceedings › peer-review

TY - GEN

T1 - De-noising of SRµCT Fiber Images by Total Variation Minimization

AU - Lindblad, Joakim

AU - Sladoje, Nataša

AU - Lukic, Tibor

PY - 2010

Y1 - 2010

N2 - SRμCT images of paper and pulp fiber materials are characterized by a low signal to noise ratio. De-noising is therefore a common preprocessing step before segmentation into fiber and background components. We suggest a de-noising method based on total variation minimization using a modified Spectral Conjugate Gradient algorithm. Quantitative evaluation performed on synthetic 3D data and qualitative evaluation on real 3D paper fiber data confirm appropriateness of the suggested method for the particular application

AB - SRμCT images of paper and pulp fiber materials are characterized by a low signal to noise ratio. De-noising is therefore a common preprocessing step before segmentation into fiber and background components. We suggest a de-noising method based on total variation minimization using a modified Spectral Conjugate Gradient algorithm. Quantitative evaluation performed on synthetic 3D data and qualitative evaluation on real 3D paper fiber data confirm appropriateness of the suggested method for the particular application

UR - https://res.slu.se/id/publ/31861

U2 - 10.1109/ICPR.2010.1116

DO - 10.1109/ICPR.2010.1116

M3 - Conference paper in proceedings

SN - 978-1-4244-7542-1

T3 - Proceedings - International Conference On Pattern Recognition

SP - 4621

EP - 4624

BT - 2010 20th International Conference on Pattern Recognition

PB - The Institute of Electrical and Electronics Engineers, Inc.

ER -

De-noising of SRµCT Fiber Images by Total Variation Minimization

Abstract

Publication series

Access to Document

Other files and links

Cite this