The application of machine learning to the problem of classifying voxels in X-ray microtomographic scans of mineralogical samples

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.