Phase segmentation of X-ray computer tomography rock images using
machine learning techniques: an accuracy and performance
study

Chauhan, Swarup; Rühaak, Wolfram; Anbergen, Hauke; Kabdenov, Alen; Freise, Marcus; Wille, Thorsten; Sass, Ingo

doi:https://doi.org/10.5194/se-7-1125-2016

Articles | Volume 7, issue 4

https://doi.org/10.5194/se-7-1125-2016

© Author(s) 2016. This work is distributed under
the Creative Commons Attribution 3.0 License.

Special issue:

Pore-scale tomography & imaging - applications, techniques...

https://doi.org/10.5194/se-7-1125-2016

© Author(s) 2016. This work is distributed under
the Creative Commons Attribution 3.0 License.

Articles | Volume 7, issue 4

Research article

|

19 Jul 2016

Research article |

| 19 Jul 2016

Phase segmentation of X-ray computer tomography rock images using machine learning techniques: an accuracy and performance study

Swarup Chauhan, Wolfram Rühaak, Hauke Anbergen, Alen Kabdenov, Marcus Freise, Thorsten Wille, and Ingo Sass

Download

Final revised paper (published on 19 Jul 2016)
Preprint (discussion started on 01 Apr 2016)

Interactive discussion

Status: closed

AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment

- Printer-friendly version

- Supplement

RC1: 'Comments on se-2016-44', Anonymous Referee #1, 10 Apr 2016
- AC1: 'Reply Reviewer #1', Wolfram Rühaak, 27 May 2016
RC2: 'Review on "Phase Segmentation of X-Ray Computer Tomography Rock Images using Machine Learning Techniques: An Accuracy and Performance Study"', Anonymous Referee #2, 27 Apr 2016
- AC2: 'Reply Reviewer #2', Wolfram Rühaak, 27 May 2016
EC1: 'Topical editor comment', Steven Henkel, 24 Jun 2016

Short summary

Machine learning techniques are a promising alternative for processing (phase segmentation) of 3-D X-ray computer tomographic rock images. Here the performance and accuracy of different machine learning techniques are tested. The aim is to classify pore space, rock grains and matrix of four distinct rock samples. The porosity obtained based on the segmented XCT images is cross-validated with laboratory measurements. Accuracies of the different methods are discussed and recommendations proposed.