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

Abstract

Abstract. Performance and accuracy of machine learning techniques to segment rock grains, matrix and pore voxels from a 3-D volume of X-ray tomographic (XCT) grayscale rock images was evaluated. The segmentation and classification capability of unsupervised (k-means, fuzzy c-means, self-organized maps), supervised (artificial neural networks, least-squares support vector machines) and ensemble classifiers (bragging and boosting) were tested using XCT images of andesite volcanic rock, Berea sandstone, Rotliegend sandstone and a synthetic sample. The averaged porosity obtained for andesite (15.8 ± 2.5 %), Berea sandstone (16.3 ± 2.6 %), Rotliegend sandstone (13.4 ± 7.4 %) and the synthetic sample (48.3 ± 13.3 %) is in very good agreement with the respective laboratory measurement data and varies by a factor of 0.2. The k-means algorithm is the fastest of all machine learning algorithms, whereas a least-squares support vector machine is the most computationally expensive. Metrics entropy, purity, mean square root error, receiver operational characteristic curve and 10 K-fold cross-validation were used to determine the accuracy of unsupervised, supervised and ensemble classifier techniques. In general, the accuracy was found to be largely affected by the feature vector selection scheme. As it is always a trade-off between performance and accuracy, it is difficult to isolate one particular machine learning algorithm which is best suited for the complex phase segmentation problem. Therefore, our investigation provides parameters that can help in selecting the appropriate machine learning techniques for phase segmentation.

Emergent Properties of Microbial Activity in Heterogeneous Soil Microenvironments: Different Research Approaches Are Slowly Converging, Yet Major Challenges Remain

“…Machine learning explores the study and construction of algorithms that can learn from data and make data-driven predictions. Machine learning algorithms have started to be employed in soil science, in particular for pattern analysis and image classification to predict material classes in single channel X-ray CT images (Chauhan et al, 2016) and multi-channel nanoSIMS images (Steffens et al, 2017; Schweizer et al, 2018). Deep learning is a class of machine learning algorithms that use a cascade of multiple layers of non-linear processing units for feature extraction and transformation; learn in supervised and/or unsupervised (e.g., pattern analysis) manners; learn multiple levels of representations that correspond to different levels of abstraction; and use some form of gradient descent for training via back-propagation.…”

CobWeb 1.0: Machine Learning Tool Box for Tomographic Imaging

“…In the case of supervised segmentation schemes (LSSVM, Bragging and Boosting) apriori information, also known as feature vector dataset or training dataset, is required to train the model(s) (Chauhan et al, 2016a;Chauhan et al, 2016b), and consequently, the trained model is ready to classify the rest of the dataset. The following five steps accomplish this procedure:  First, the visualization panel displays a single 2D slice of the REV or 3D image stack in a resizable pan-window.…”

“…Once the processing is finished, the segmented data can be visualized in 2D format using Plot button or in 3D rendered stack using VolRender button. The methods used to calculate geometrical parameters and validation schemes are benchmarked in (Chauhan et al, 2016a) (Chauhan et al, 2016b). Therefore, the selection of desired options initialize respective subroutines (uPoreSzVol, uCalVal, uExport) and plot the results as shown in Figure 2.…”

“…CobWeb 1.0 was customized to fill the gap by performing image analysis and accurate greyscale phase segmentation of reconstructed high-resolution XCT and synchrotron tomographic datasets. This software is based on a machine learning approach with great potential for segmentation analysis as introduced previously (Chauhan et al, 2016b;Chauhan et al, 2016a). Further, this software tool package was developed on a MATLAB ® workbench and can be used as Windows stand-alone executable (.exe) files or as a MATLAB ® plugin.…”

Analysis of Impregnation Mechanism of Weft-Knitted Commingled Yarn Composites by Staged Consolidation and Laboratory X-Ray Computed Tomography

“…The algorithm consists of iteratively repeating steps (ii) and (iii) to minimize the intra-cluster variance. More details about this method can be found in the literature (Gonsalves et al, 2015;Chauhan et al, 2016).…”