Title :
The application of machine learning to the problem of classifying voxels in X-ray microtomographic scans of mineralogical samples
Author :
Shipman, W.J. ; Nel, A.L. ; Chetty, D. ; Miller, Jason D. ; Chen-Luh Lin
Author_Institution :
Dept. of Electr. & Electron. Eng. Sci., Univ. of Johannesburg, Johannesburg, South Africa
Abstract :
Processing X-ray microtomography scans of ore samples to extract quantitative mineralogical information regarding composition, porosity and particle size is complicated by the presence of noise in the tomograms and artefacts resulting from non-ideal scanning conditions. In order to obtain quantitative information, one must first classify voxels into their different mineral classes. This paper presents work done using fuzzy inference systems to learn the classification rules for identifying different mineral classes in the tomogram. The advantages and disadvantages of this method are discussed.
Keywords :
X-ray microscopy; fuzzy reasoning; geophysical image processing; image classification; minerals; particle size; porosity; X-ray microtomographic scans; artefacts; classification rule learning; fuzzy inference systems; machine learning; mineral class identification; mineralogical samples; nonideal scanning conditions; ore composition; ore particle size; ore porosity; ore samples; quantitative mineralogical information extraction; tomograms; voxel classification; Anisotropic magnetoresistance; Attenuation; Histograms; Minerals; Solids; Training; Fuzzy logic; Image classification; Image processing; Machine learning; Pattern analysis; X-ray tomography;
Conference_Titel :
Industrial Technology (ICIT), 2013 IEEE International Conference on
Conference_Location :
Cape Town
Print_ISBN :
978-1-4673-4567-5
Electronic_ISBN :
978-1-4673-4568-2
DOI :
10.1109/ICIT.2013.6505841
