Multi-phase classification by a least-squares support vector machine approach  in tomography images of geological samples

Khan, Faisal; Enzmann, Frieder; Kersten, Michael

doi:https://doi.org/10.5194/se-7-481-2016

Articles | Volume 7, issue 2

https://doi.org/10.5194/se-7-481-2016

© 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-7-481-2016

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

Articles | Volume 7, issue 2

Research article

|

30 Mar 2016

Research article |

| 30 Mar 2016

Multi-phase classification by a least-squares support vector machine approach in tomography images of geological samples

Faisal Khan, Frieder Enzmann, and Michael Kersten

Download

Final revised paper (published on 30 Mar 2016)
Preprint (discussion started on 03 Dec 2015)

Interactive discussion

Status: closed

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

- Printer-friendly version

- Supplement

RC C1863: 'Comments on sed-7-3383-2015', Anonymous Referee #1, 17 Jan 2016
- RC C1919: 'Review on "Beam-hardening correction by a surface fitting and phase classification by a least square support vector machine approach for tomography images of geological samples"', Anonymous Referee #2, 03 Feb 2016
  - AC C1999: 'Rebuttal letter to reviewer #2', Michael Kersten, 09 Mar 2016
- AC C1994: 'Rebuttal to reviewer #1', Michael Kersten, 09 Mar 2016

Short summary

X-ray microtomography image processing involves artefact reduction and image segmentation. The beam-hardening artefact is removed, applying a new algorithm, which minimizes the offsets of the attenuation data points. For the segmentation, we propose using a non-linear classifier algorithm. Statistical analysis was performed to quantify the improvement in multi-phase classification of rock cores using and without using our advanced beam-hardening correction algorithm.