Image Processing Variability in Pore Structural Investigations: Conventional Thresholding vs. Machine Learning Approaches

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Standard

Image Processing Variability in Pore Structural Investigations: Conventional Thresholding vs. Machine Learning Approaches. / Shi, Xiangyun; Misch, David; Vranjes-Wessely, Sanja.
6th International Conference on Fault and Top Seals 2022, FTS 2022. 2022. 01 (6th International Conference on Fault and Top Seals 2022, FTS 2022).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Harvard

Shi, X, Misch, D & Vranjes-Wessely, S 2022, Image Processing Variability in Pore Structural Investigations: Conventional Thresholding vs. Machine Learning Approaches. in 6th International Conference on Fault and Top Seals 2022, FTS 2022., 01, 6th International Conference on Fault and Top Seals 2022, FTS 2022, 6th International Conference on Fault and Top Seals 2022, FTS 2022, Vienna, Austria, 26/09/22. https://doi.org/10.3997/2214-4609.202243001

APA

Shi, X., Misch, D., & Vranjes-Wessely, S. (2022). Image Processing Variability in Pore Structural Investigations: Conventional Thresholding vs. Machine Learning Approaches. In 6th International Conference on Fault and Top Seals 2022, FTS 2022 Article 01 (6th International Conference on Fault and Top Seals 2022, FTS 2022). https://doi.org/10.3997/2214-4609.202243001

Vancouver

Shi X, Misch D, Vranjes-Wessely S. Image Processing Variability in Pore Structural Investigations: Conventional Thresholding vs. Machine Learning Approaches. In 6th International Conference on Fault and Top Seals 2022, FTS 2022. 2022. 01. (6th International Conference on Fault and Top Seals 2022, FTS 2022). doi: https://doi.org/10.3997/2214-4609.202243001

Author

Shi, Xiangyun ; Misch, David ; Vranjes-Wessely, Sanja. / Image Processing Variability in Pore Structural Investigations : Conventional Thresholding vs. Machine Learning Approaches. 6th International Conference on Fault and Top Seals 2022, FTS 2022. 2022. (6th International Conference on Fault and Top Seals 2022, FTS 2022).

Bibtex - Download

@inproceedings{d533aed3d2f84aa388667c88bb91d410,
title = "Image Processing Variability in Pore Structural Investigations: Conventional Thresholding vs. Machine Learning Approaches",
abstract = "Mudstones and shales are of great geoscientific interest given their potential as primary energy carriers (“shale oil/gas”), as well as their importance to numerous other energy-related fields such as hydrogen underground storage, drilling for geothermal energy, or nuclear waste disposal. Electron beam techniques and particularly broad ion beam - scanning electron microscopy (BIB-SEM) have become more and more important in the investigation of such kinds of fine-grained sedimentary rocks, as they can provide porosity quantification and information about the pore space morphology in 2D (Desbois et al., 2009; Klaver et al., 2012; Misch et al., 2018a, 2021). BIB-SEM maps are large digital image files that have to be processed in order to obtain reliable pore characteristics, such as total porosity and pore size distributions (PSDs). Image processing tools like Photoshop, imageJ, and ArcGIS are widely used for image segmentation based on the thresholding principle (Abr{\`a}moff et al., 2004; Desbois et al., 2009; Klaver et al., 2012, 2015; Li et al., 2019; Misch et al., 2018b). However, different image processing approaches may lead to discrepancies in the obtained pore information and generate highly variable results. The effects of different image segmentation approaches on the obtained PSDs and pore geometry factors have not been quantified nor well documented yet.Variability in image processing results is not only caused by the fundamentally different methods, but also inherently linked to i) the physical resolution limit of the respective imaging technique, as well as ii) the inconsistent subjective interpretation of features by the human eye. As shown in Figure 1, boundaries of pore cross-sections in BIB-SEM images can be ambiguous for features approaching the maximum resolution/minimum pixel size of an image. The grey value pattern of pore boundaries is typically gradual rather than sharp and clear, as shown in the grey value profile over a porous domain displayed in Figure 1c. In such cases, a clear boundary determination may be difficult, leading topossible variations in pore quantification data (“boundary effect”).This study addresses the abovementioned variability in image processing by conventional thresholding vs. advanced machine learning methods. The test data set consists of BIB-SEM large-area maps acquired from 12 Middle Miocene mudstone samples within a single stratigraphic interval in the Vienna Basin, Austria. Pore space segmentation of SEM maps was processed using the conventional deterministic thresholding method in the software imageJ (Schindelin et al., 2012, 2015) and the machine learning-based pixel classification in the open-source tool kit ilastik (Berg et al., 2019; Sommer et al., 2011). Total porosity, PSDs and pore morphology were resolved by both methods. The study aims were i) to test the sensitivity of segmentation results to thresholding parameter variations in ImageJ, and ii) to compare the conventional thresholding method with the considerably faster machine learning-based identification by ilastik.",
author = "Xiangyun Shi and David Misch and Sanja Vranjes-Wessely",
note = "Publisher Copyright: {\textcopyright} 2022 International Conference on Fault and Top Seals; 6th International Conference on Fault and Top Seals 2022, FTS 2022 ; Conference date: 26-09-2022 Through 28-09-2022",
year = "2022",
doi = "https://doi.org/10.3997/2214-4609.202243001",
language = "English",
series = "6th International Conference on Fault and Top Seals 2022, FTS 2022",
booktitle = "6th International Conference on Fault and Top Seals 2022, FTS 2022",

}

RIS (suitable for import to EndNote) - Download

TY - GEN

T1 - Image Processing Variability in Pore Structural Investigations

T2 - 6th International Conference on Fault and Top Seals 2022, FTS 2022

AU - Shi, Xiangyun

AU - Misch, David

AU - Vranjes-Wessely, Sanja

N1 - Publisher Copyright: © 2022 International Conference on Fault and Top Seals

PY - 2022

Y1 - 2022

N2 - Mudstones and shales are of great geoscientific interest given their potential as primary energy carriers (“shale oil/gas”), as well as their importance to numerous other energy-related fields such as hydrogen underground storage, drilling for geothermal energy, or nuclear waste disposal. Electron beam techniques and particularly broad ion beam - scanning electron microscopy (BIB-SEM) have become more and more important in the investigation of such kinds of fine-grained sedimentary rocks, as they can provide porosity quantification and information about the pore space morphology in 2D (Desbois et al., 2009; Klaver et al., 2012; Misch et al., 2018a, 2021). BIB-SEM maps are large digital image files that have to be processed in order to obtain reliable pore characteristics, such as total porosity and pore size distributions (PSDs). Image processing tools like Photoshop, imageJ, and ArcGIS are widely used for image segmentation based on the thresholding principle (Abràmoff et al., 2004; Desbois et al., 2009; Klaver et al., 2012, 2015; Li et al., 2019; Misch et al., 2018b). However, different image processing approaches may lead to discrepancies in the obtained pore information and generate highly variable results. The effects of different image segmentation approaches on the obtained PSDs and pore geometry factors have not been quantified nor well documented yet.Variability in image processing results is not only caused by the fundamentally different methods, but also inherently linked to i) the physical resolution limit of the respective imaging technique, as well as ii) the inconsistent subjective interpretation of features by the human eye. As shown in Figure 1, boundaries of pore cross-sections in BIB-SEM images can be ambiguous for features approaching the maximum resolution/minimum pixel size of an image. The grey value pattern of pore boundaries is typically gradual rather than sharp and clear, as shown in the grey value profile over a porous domain displayed in Figure 1c. In such cases, a clear boundary determination may be difficult, leading topossible variations in pore quantification data (“boundary effect”).This study addresses the abovementioned variability in image processing by conventional thresholding vs. advanced machine learning methods. The test data set consists of BIB-SEM large-area maps acquired from 12 Middle Miocene mudstone samples within a single stratigraphic interval in the Vienna Basin, Austria. Pore space segmentation of SEM maps was processed using the conventional deterministic thresholding method in the software imageJ (Schindelin et al., 2012, 2015) and the machine learning-based pixel classification in the open-source tool kit ilastik (Berg et al., 2019; Sommer et al., 2011). Total porosity, PSDs and pore morphology were resolved by both methods. The study aims were i) to test the sensitivity of segmentation results to thresholding parameter variations in ImageJ, and ii) to compare the conventional thresholding method with the considerably faster machine learning-based identification by ilastik.

AB - Mudstones and shales are of great geoscientific interest given their potential as primary energy carriers (“shale oil/gas”), as well as their importance to numerous other energy-related fields such as hydrogen underground storage, drilling for geothermal energy, or nuclear waste disposal. Electron beam techniques and particularly broad ion beam - scanning electron microscopy (BIB-SEM) have become more and more important in the investigation of such kinds of fine-grained sedimentary rocks, as they can provide porosity quantification and information about the pore space morphology in 2D (Desbois et al., 2009; Klaver et al., 2012; Misch et al., 2018a, 2021). BIB-SEM maps are large digital image files that have to be processed in order to obtain reliable pore characteristics, such as total porosity and pore size distributions (PSDs). Image processing tools like Photoshop, imageJ, and ArcGIS are widely used for image segmentation based on the thresholding principle (Abràmoff et al., 2004; Desbois et al., 2009; Klaver et al., 2012, 2015; Li et al., 2019; Misch et al., 2018b). However, different image processing approaches may lead to discrepancies in the obtained pore information and generate highly variable results. The effects of different image segmentation approaches on the obtained PSDs and pore geometry factors have not been quantified nor well documented yet.Variability in image processing results is not only caused by the fundamentally different methods, but also inherently linked to i) the physical resolution limit of the respective imaging technique, as well as ii) the inconsistent subjective interpretation of features by the human eye. As shown in Figure 1, boundaries of pore cross-sections in BIB-SEM images can be ambiguous for features approaching the maximum resolution/minimum pixel size of an image. The grey value pattern of pore boundaries is typically gradual rather than sharp and clear, as shown in the grey value profile over a porous domain displayed in Figure 1c. In such cases, a clear boundary determination may be difficult, leading topossible variations in pore quantification data (“boundary effect”).This study addresses the abovementioned variability in image processing by conventional thresholding vs. advanced machine learning methods. The test data set consists of BIB-SEM large-area maps acquired from 12 Middle Miocene mudstone samples within a single stratigraphic interval in the Vienna Basin, Austria. Pore space segmentation of SEM maps was processed using the conventional deterministic thresholding method in the software imageJ (Schindelin et al., 2012, 2015) and the machine learning-based pixel classification in the open-source tool kit ilastik (Berg et al., 2019; Sommer et al., 2011). Total porosity, PSDs and pore morphology were resolved by both methods. The study aims were i) to test the sensitivity of segmentation results to thresholding parameter variations in ImageJ, and ii) to compare the conventional thresholding method with the considerably faster machine learning-based identification by ilastik.

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-85145591851&origin=resultslist&sort=plf-f&src=s&sid=a3d817d0b00f5fe559607abb33f4dbd5&sot=aut&sdt=a&sl=18&s=AU-ID%2857812373200%29&relpos=2&citeCnt=0&searchTerm=

U2 - https://doi.org/10.3997/2214-4609.202243001

DO - https://doi.org/10.3997/2214-4609.202243001

M3 - Conference contribution

T3 - 6th International Conference on Fault and Top Seals 2022, FTS 2022

BT - 6th International Conference on Fault and Top Seals 2022, FTS 2022

Y2 - 26 September 2022 through 28 September 2022

ER -