Application of machine learning techniques in mineral phase segmentation for X-ray microcomputed tomography (µCT) data

Abstract X-ray microcomputed tomography (µCT) offers a non-destructive three-dimensional analysis of ores but its application in mineralogical analysis and mineral segmentation is relatively limited. In this study, the application of machine learning techniques for segmenting mineral phases in a µCT dataset is presented. Various techniques were implemented, including unsupervised classification as well as grayscale-based and feature-based supervised classification. A feature matching method was used to register the back-scattered electron (BSE) mineral map to its corresponding µCT slice, allowing automatic annotation of minerals in the µCT slice to create training data for the classifiers. Unsupervised classification produced satisfactory results in terms of segmenting between amphibole, plagioclase, and sulfide phases. However, the technique was not able to differentiate between sulfide phases in the case of chalcopyrite and pyrite. Using supervised classification, around 50–60% of the chalcopyrite and 97–99% of pyrite were correctly identified. Feature based classification was found to have a poorer sensitivity to chalcopyrite, but produced a better result in segmenting between the mineral grains, as it operates based on voxel regions instead of individual voxels. The mineralogical results from the 3D µCT data showed considerable difference compared to the BSE mineral map, indicating stereological error exhibited in the latter analysis. The main limitation of this approach lies in the dataset itself, in which there was a significant overlap in grayscale values between chalcopyrite and pyrite, therefore highly limiting the classifier accuracy.

[1]  Tony Lindeberg,et al.  Scale Selection Properties of Generalized Scale-Space Interest Point Detectors , 2012, Journal of Mathematical Imaging and Vision.

[2]  Purnima Bholowalia,et al.  EBK-Means: A Clustering Technique based on Elbow Method and K-Means in WSN , 2014 .

[3]  M. Becker,et al.  X-ray computed tomography: Practical evaluation of beam hardening in iron ore samples , 2019, Minerals Engineering.

[4]  Wolfram Rühaak,et al.  Phase segmentation of X-ray computer tomography rock images usingmachine learning techniques: an accuracy and performancestudy , 2016 .

[5]  Haibo He,et al.  Learning from Imbalanced Data , 2009, IEEE Transactions on Knowledge and Data Engineering.

[6]  José Augusto Baranauskas,et al.  How Many Trees in a Random Forest? , 2012, MLDM.

[7]  Jan Rosenkranz,et al.  X-ray Microcomputed Tomography (µCT) for Mineral Characterization: A Review of Data Analysis Methods , 2019, Minerals.

[8]  Jan D. Miller,et al.  Quantitative analysis of grain boundary fracture in the breakage of single multiphase particles using X-ray microtomography procedures , 2009 .

[9]  G. Narsilio,et al.  Use of high-resolution X-ray computed tomography and 3D image analysis to quantify mineral dissemination and pore space in oxide copper ore particles , 2017, International Journal of Minerals, Metallurgy, and Materials.

[10]  Peter D. Lee,et al.  Modelling particle scale leach kinetics based on X-ray computed micro-tomography images , 2016 .

[11]  Jianhua Gong,et al.  UAV Remote Sensing for Urban Vegetation Mapping Using Random Forest and Texture Analysis , 2015, Remote. Sens..

[12]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[13]  J. Fitts,et al.  Quantifying fracture geometry with X-ray tomography: Technique of Iterative Local Thresholding (TILT) for 3D image segmentation , 2016, Computational Geosciences.

[14]  Zoran Bosnic,et al.  ROC analysis of classifiers in machine learning: A survey , 2013, Intell. Data Anal..

[15]  J. A. Miller,et al.  Coupled X-ray computed tomography and grey level co-occurrence matrices as a method for quantification of mineralogy and texture in 3D , 2018, Comput. Geosci..

[16]  Shan Suthaharan,et al.  Machine Learning Models and Algorithms for Big Data Classification , 2016 .

[17]  J-P. Franzidis,et al.  Use of X-ray computed tomography to investigate crack distribution and mineral dissemination in sphalerite ore particles , 2011 .

[18]  Johannes E. Schindelin,et al.  Fiji: an open-source platform for biological-image analysis , 2012, Nature Methods.

[19]  P. Withers,et al.  Quantitative X-ray tomography , 2014 .

[20]  Veerle Cnudde,et al.  High-resolution X-ray computed tomography in geosciences: A review of the current technology and applications , 2013 .

[21]  Jan D. Miller,et al.  3D characterization and analysis of particle shape using X-ray microtomography (XMT) , 2005 .

[22]  Haitao Lu,et al.  Morphological Background Detection and Illumination Normalization of Text Image with Poor Lighting , 2014, PloS one.

[23]  R. Ketcham,et al.  Application of high resolution X-ray computed tomography to mineral deposit origin, evaluation, and processing , 2015 .

[24]  Stephen J. Neethling,et al.  Multi-scale quantification of leaching performance using X-ray tomography , 2016 .

[25]  B. S. Duran,et al.  Cluster Analysis: A Survey , 1974 .

[26]  Henning Osholm Sørensen,et al.  Improved segmentation of X-ray tomography data from porous rocks using a dual filtering approach , 2012, Comput. Geosci..

[27]  H. Sebastian Seung,et al.  Trainable Weka Segmentation: a machine learning tool for microscopy pixel classification , 2017, Bioinform..

[28]  Martin Kappas,et al.  Comparison of Random Forest, k-Nearest Neighbor, and Support Vector Machine Classifiers for Land Cover Classification Using Sentinel-2 Imagery , 2017, Sensors.

[29]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[30]  B. Park,et al.  Choice of neighbor order in nearest-neighbor classification , 2008, 0810.5276.

[31]  C. L. Lin,et al.  Improved 3D image segmentation for X-ray tomographic analysis of packed particle beds , 2015 .

[32]  Tony Lindeberg,et al.  Image Matching Using Generalized Scale-Space Interest Points , 2013, Journal of Mathematical Imaging and Vision.

[33]  C. L. Lin,et al.  A Review of X-Ray Computed Tomography and Its Applications in Mineral Processing , 1990 .

[34]  C. Wanhainen,et al.  The Aitik Cu–Au–Ag deposit in northern Sweden: a product of high salinity fluids , 2003 .

[35]  Wolfram Rühaak,et al.  Processing of rock core microtomography images: Using seven different machine learning algorithms , 2016, Comput. Geosci..

[36]  Luc Van Gool,et al.  Speeded-Up Robust Features (SURF) , 2008, Comput. Vis. Image Underst..

[37]  Stephen J. Neethling,et al.  Calibrated X-ray micro-tomography for mineral ore quantification , 2017 .

[38]  Musbah J. Aqel,et al.  Survey on Image Segmentation Techniques , 2015 .

[39]  M. Cho,et al.  Classification of savanna tree species, in the Greater Kruger National Park region, by integrating hyperspectral and LiDAR data in a Random Forest data mining environment , 2012 .

[40]  C. L. Evans,et al.  Quantifying mineral grain size distributions for process modelling using X-ray micro-tomography , 2015 .

[41]  Shie Mannor,et al.  Robustness and generalization , 2010, Machine Learning.

[42]  Tapan Mukerji,et al.  Digital rock physics benchmarks - Part I: Imaging and segmentation , 2013, Comput. Geosci..

[43]  P. Jacobs,et al.  Applications of X-ray computed tomography in the geosciences , 2003, Geological Society, London, Special Publications.

[44]  Jan D. Miller,et al.  Cone beam X-ray microtomography for three-dimensional liberation analysis in the 21st century , 1996 .

[45]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[46]  Peter D. Lee,et al.  Quantifying and minimising systematic and random errors in X-ray micro-tomography based volume measurements , 2015, Comput. Geosci..

[47]  Andrew P. Bradley,et al.  The use of the area under the ROC curve in the evaluation of machine learning algorithms , 1997, Pattern Recognit..

[48]  Lisa M. Brown,et al.  A survey of image registration techniques , 1992, CSUR.

[49]  Richard A. Ketcham,et al.  High resolution X-ray computed tomography studies of Grasberg porphyry Cu-Au ores, Papua, Indonesia , 2008 .