Gaussian Mixture Models for Robust Unsupervised Scanning-Electron Microscopy Image Segmentation of North Sea Chalk

Jesper Sören Dramsch; Frédéric Amour; Mikael Lüthje

doi:10.3997/2214-4609.201803014

Gaussian Mixture Models for Robust Unsupervised Scanning-Electron Microscopy Image Segmentation of North Sea Chalk

Jesper Sören Dramsch, Frédéric Amour, Mikael Lüthje

Department of Applied Mathematics and Computer Science

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

430 Downloads (Pure)

Abstract

Scanning-Electron images from North Sea Chalk are studied for important rock properties. To relieve this manual labor, we investigated several standard image processing methods that underperformed on complicated chalk. Due to the lack of manually labeled data, deep neural networks could not be adequately applied. Gaussian Mixture Models learnt a two-fold representation that separated the background well from the rock. Subsequent morphological filtering cleans up the prediction and enables automatic analysis.

Original language	English
Title of host publication	Proceedings of the First EAGE/PESGB Workshop on Machine Learning (London2018)
Publisher	European Association of Geoscientists and Engineers
Publication date	2018
Pages	28-30
ISBN (Print)	978-1-5108-7668-2
DOIs	https://doi.org/10.3997/2214-4609.201803014
Publication status	Published - 2018
Event	First EAGE/PESGB Workshop Machine Learning - Olympia London, London, United Kingdom Duration: 29 Nov 2018 → 30 Nov 2018

Conference

Conference	First EAGE/PESGB Workshop Machine Learning
Location	Olympia London
Country/Territory	United Kingdom
City	London
Period	29/11/2018 → 30/11/2018

Access to Document

10.3997/2214-4609.201803014

Gaussian Mixture Models for Robust Unsupervised Scanning Electron Microscopy Image Segmentation of North Sea Chalk 1 Final published version, 553 KB

OpenUrl availability

Full text

Cite this

@inproceedings{4108cdc5f75e4353bc2f00c9521aee38,

title = "Gaussian Mixture Models for Robust Unsupervised Scanning-Electron Microscopy Image Segmentation of North Sea Chalk",

abstract = "Scanning-Electron images from North Sea Chalk are studied for important rock properties. To relieve this manual labor, we investigated several standard image processing methods that underperformed on complicated chalk. Due to the lack of manually labeled data, deep neural networks could not be adequately applied. Gaussian Mixture Models learnt a two-fold representation that separated the background well from the rock. Subsequent morphological filtering cleans up the prediction and enables automatic analysis. ",

author = "{S{\"o}ren Dramsch}, Jesper and Fr{\'e}d{\'e}ric Amour and Mikael L{\"u}thje",

year = "2018",

doi = "10.3997/2214-4609.201803014",

language = "English",

isbn = "978-1-5108-7668-2",

pages = "28--30",

booktitle = "Proceedings of the First EAGE/PESGB Workshop on Machine Learning (London2018)",

publisher = "European Association of Geoscientists and Engineers",

note = "First EAGE/PESGB Workshop Machine Learning ; Conference date: 29-11-2018 Through 30-11-2018",

}

Sören Dramsch, J, Amour, F & Lüthje, M 2018, Gaussian Mixture Models for Robust Unsupervised Scanning-Electron Microscopy Image Segmentation of North Sea Chalk. in Proceedings of the First EAGE/PESGB Workshop on Machine Learning (London2018). European Association of Geoscientists and Engineers, pp. 28-30, First EAGE/PESGB Workshop Machine Learning , London, United Kingdom, 29/11/2018. https://doi.org/10.3997/2214-4609.201803014

Gaussian Mixture Models for Robust Unsupervised Scanning-Electron Microscopy Image Segmentation of North Sea Chalk. / Sören Dramsch, Jesper; Amour, Frédéric; Lüthje, Mikael.
Proceedings of the First EAGE/PESGB Workshop on Machine Learning (London2018). European Association of Geoscientists and Engineers, 2018. p. 28-30.

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

TY - GEN

T1 - Gaussian Mixture Models for Robust Unsupervised Scanning-Electron Microscopy Image Segmentation of North Sea Chalk

AU - Sören Dramsch, Jesper

AU - Amour, Frédéric

AU - Lüthje, Mikael

PY - 2018

Y1 - 2018

N2 - Scanning-Electron images from North Sea Chalk are studied for important rock properties. To relieve this manual labor, we investigated several standard image processing methods that underperformed on complicated chalk. Due to the lack of manually labeled data, deep neural networks could not be adequately applied. Gaussian Mixture Models learnt a two-fold representation that separated the background well from the rock. Subsequent morphological filtering cleans up the prediction and enables automatic analysis.

AB - Scanning-Electron images from North Sea Chalk are studied for important rock properties. To relieve this manual labor, we investigated several standard image processing methods that underperformed on complicated chalk. Due to the lack of manually labeled data, deep neural networks could not be adequately applied. Gaussian Mixture Models learnt a two-fold representation that separated the background well from the rock. Subsequent morphological filtering cleans up the prediction and enables automatic analysis.

U2 - 10.3997/2214-4609.201803014

DO - 10.3997/2214-4609.201803014

M3 - Article in proceedings

SN - 978-1-5108-7668-2

SP - 28

EP - 30

BT - Proceedings of the First EAGE/PESGB Workshop on Machine Learning (London2018)

PB - European Association of Geoscientists and Engineers

T2 - First EAGE/PESGB Workshop Machine Learning

Y2 - 29 November 2018 through 30 November 2018

ER -

Gaussian Mixture Models for Robust Unsupervised Scanning-Electron Microscopy Image Segmentation of North Sea Chalk

Abstract

Conference

Access to Document

OpenUrl availability

Fingerprint

Cite this