CobWeb 1.0: machine learning toolbox for tomographic imaging
<p>Despite the availability of both commercial and open-source software, an ideal tool for digital rock physics analysis for accurate automatic image analysis at ambient computational performance is difficult to pinpoint. More often, image segmentation is driven manually, where the performance...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2020-01-01
|
| Series: | Geoscientific Model Development |
| Online Access: | https://www.geosci-model-dev.net/13/315/2020/gmd-13-315-2020.pdf |
| _version_ | 1819002020268343296 |
|---|---|
| author | S. Chauhan S. Chauhan K. Sell K. Sell K. Sell W. Rühaak T. Wille I. Sass |
| author_facet | S. Chauhan S. Chauhan K. Sell K. Sell K. Sell W. Rühaak T. Wille I. Sass |
| author_sort | S. Chauhan |
| collection | DOAJ |
| description | <p>Despite the availability of both commercial and open-source software, an
ideal tool for digital rock physics analysis for accurate automatic image
analysis at ambient computational performance is difficult to pinpoint. More
often, image segmentation is driven manually, where the performance remains
limited to two phases. Discrepancies due to artefacts cause inaccuracies in
image analysis. To overcome these problems, we have developed CobWeb 1.0, which is automated and explicitly tailored for accurate
greyscale (multiphase) image segmentation using unsupervised and supervised
machine learning techniques. In this study, we demonstrate image
segmentation using unsupervised machine learning techniques. The simple and
intuitive layout of the graphical user interface enables easy access to
perform image enhancement and image segmentation, and further to obtain the
accuracy of different segmented classes. The graphical user interface
enables not only processing of a full 3-D digital rock dataset but also
provides a quick and easy region-of-interest selection, where a
representative elementary volume can be extracted and processed. The CobWeb
software package covers image processing and machine learning libraries of
MATLAB<sup>®</sup> used for image enhancement and image
segmentation operations, which are compiled into series of Windows-executable binaries. Segmentation can be performed using unsupervised,
supervised and ensemble classification tools. Additionally, based on the
segmented phases, geometrical parameters such as pore size distribution,
relative porosity trends and volume fraction can be calculated and
visualized. The CobWeb software allows the export of data to various formats
such as ParaView (.vtk), DSI Studio (.fib) for visualization and animation,
and Microsoft<sup>®</sup> Excel and
MATLAB<sup>®</sup> for numerical calculation and
simulations. The capability of this new software is verified using
high-resolution synchrotron tomography datasets, as well as lab-based
(cone-beam) X-ray microtomography datasets. Regardless of the high spatial
resolution (submicrometre), the synchrotron dataset contained edge
enhancement artefacts which were eliminated using a novel dual filtering and
dual segmentation procedure.</p> |
| first_indexed | 2024-12-20T22:58:28Z |
| format | Article |
| id | doaj.art-1e3f268d7c3c4f3fbf07710cb2035a54 |
| institution | Directory Open Access Journal |
| issn | 1991-959X 1991-9603 |
| language | English |
| last_indexed | 2024-12-20T22:58:28Z |
| publishDate | 2020-01-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | Geoscientific Model Development |
| spelling | doaj.art-1e3f268d7c3c4f3fbf07710cb2035a542022-12-21T19:24:04ZengCopernicus PublicationsGeoscientific Model Development1991-959X1991-96032020-01-011331533410.5194/gmd-13-315-2020CobWeb 1.0: machine learning toolbox for tomographic imagingS. Chauhan0S. Chauhan1K. Sell2K. Sell3K. Sell4W. Rühaak5T. Wille6I. Sass7Institute for Geosciences, Johannes Gutenberg-University, 55099 Mainz, GermanyInstitute of Applied Geosciences, University of Technology, 64287 Darmstadt, GermanyInstitute for Geosciences, Johannes Gutenberg-University, 55099 Mainz, Germanyigem – Institute for Geothermal Resource Management, Berlinstr. 107a, 55411 Bingen, Germanynow at: Ministry of Economic Affairs Rhineland Palatine, Stiftsstrasse 9, 55116 Mainz, GermanyBundesgesellschaft für Endlagerung mbH (BGE), 38226 Peine, GermanyAPS Antriebs-, Prüf- und Steuertechnik GmbH, Götzenbreite 12, 37124 Rosdorf, GermanyInstitute of Applied Geosciences, University of Technology, 64287 Darmstadt, Germany<p>Despite the availability of both commercial and open-source software, an ideal tool for digital rock physics analysis for accurate automatic image analysis at ambient computational performance is difficult to pinpoint. More often, image segmentation is driven manually, where the performance remains limited to two phases. Discrepancies due to artefacts cause inaccuracies in image analysis. To overcome these problems, we have developed CobWeb 1.0, which is automated and explicitly tailored for accurate greyscale (multiphase) image segmentation using unsupervised and supervised machine learning techniques. In this study, we demonstrate image segmentation using unsupervised machine learning techniques. The simple and intuitive layout of the graphical user interface enables easy access to perform image enhancement and image segmentation, and further to obtain the accuracy of different segmented classes. The graphical user interface enables not only processing of a full 3-D digital rock dataset but also provides a quick and easy region-of-interest selection, where a representative elementary volume can be extracted and processed. The CobWeb software package covers image processing and machine learning libraries of MATLAB<sup>®</sup> used for image enhancement and image segmentation operations, which are compiled into series of Windows-executable binaries. Segmentation can be performed using unsupervised, supervised and ensemble classification tools. Additionally, based on the segmented phases, geometrical parameters such as pore size distribution, relative porosity trends and volume fraction can be calculated and visualized. The CobWeb software allows the export of data to various formats such as ParaView (.vtk), DSI Studio (.fib) for visualization and animation, and Microsoft<sup>®</sup> Excel and MATLAB<sup>®</sup> for numerical calculation and simulations. The capability of this new software is verified using high-resolution synchrotron tomography datasets, as well as lab-based (cone-beam) X-ray microtomography datasets. Regardless of the high spatial resolution (submicrometre), the synchrotron dataset contained edge enhancement artefacts which were eliminated using a novel dual filtering and dual segmentation procedure.</p>https://www.geosci-model-dev.net/13/315/2020/gmd-13-315-2020.pdf |
| spellingShingle | S. Chauhan S. Chauhan K. Sell K. Sell K. Sell W. Rühaak T. Wille I. Sass CobWeb 1.0: machine learning toolbox for tomographic imaging Geoscientific Model Development |
| title | CobWeb 1.0: machine learning toolbox for tomographic imaging |
| title_full | CobWeb 1.0: machine learning toolbox for tomographic imaging |
| title_fullStr | CobWeb 1.0: machine learning toolbox for tomographic imaging |
| title_full_unstemmed | CobWeb 1.0: machine learning toolbox for tomographic imaging |
| title_short | CobWeb 1.0: machine learning toolbox for tomographic imaging |
| title_sort | cobweb 1 0 machine learning toolbox for tomographic imaging |
| url | https://www.geosci-model-dev.net/13/315/2020/gmd-13-315-2020.pdf |
| work_keys_str_mv | AT schauhan cobweb10machinelearningtoolboxfortomographicimaging AT schauhan cobweb10machinelearningtoolboxfortomographicimaging AT ksell cobweb10machinelearningtoolboxfortomographicimaging AT ksell cobweb10machinelearningtoolboxfortomographicimaging AT ksell cobweb10machinelearningtoolboxfortomographicimaging AT wruhaak cobweb10machinelearningtoolboxfortomographicimaging AT twille cobweb10machinelearningtoolboxfortomographicimaging AT isass cobweb10machinelearningtoolboxfortomographicimaging |