Articles | Volume 7, issue 2
Research article
30 Mar 2016
Research article |  | 30 Mar 2016

Multi-phase classification by a least-squares support vector machine approach in tomography images of geological samples

Faisal Khan, Frieder Enzmann, and Michael Kersten

Abstract. Image processing of X-ray-computed polychromatic cone-beam micro-tomography (μXCT) data of geological samples mainly involves artefact reduction and phase segmentation. For the former, the main beam-hardening (BH) artefact is removed by applying a best-fit quadratic surface algorithm to a given image data set (reconstructed slice), which minimizes the BH offsets of the attenuation data points from that surface. A Matlab code for this approach is provided in the Appendix. The final BH-corrected image is extracted from the residual data or from the difference between the surface elevation values and the original grey-scale values. For the segmentation, we propose a novel least-squares support vector machine (LS-SVM, an algorithm for pixel-based multi-phase classification) approach. A receiver operating characteristic (ROC) analysis was performed on BH-corrected and uncorrected samples to show that BH correction is in fact an important prerequisite for accurate multi-phase classification. The combination of the two approaches was thus used to classify successfully three different more or less complex multi-phase rock core samples.

Short summary
X-ray microtomography image processing involves artefact reduction and image segmentation. The beam-hardening artefact is removed, applying a new algorithm, which minimizes the offsets of the attenuation data points. For the segmentation, we propose using a non-linear classifier algorithm. Statistical analysis was performed to quantify the improvement in multi-phase classification of rock cores using and without using our advanced beam-hardening correction algorithm.