Comparison of Micro X-ray Computer Tomography Image Segmentation Methods: Artificial Neural Networks Versus Least Square Support Vector Machine

Micro X-ray computer tomography (XCT) is a powerful non-destructive method for obtaining information about rock structures and mineralogy. A new methodology to obtain porosity from 2D XCT digital images using artificial neural network and least square support vector machine is demonstrated following these steps: the XCT image was first preprocessed, thereafter clustering algorithms such as K-means, Fuzzy c-means and self-organized maps was used for image segmentation. Then artificial neural network was applied for image classification. For comparison, least square support vector machine approach was used for classification labeling of the scan images. The methodology shows how artificial neural network and least square support vector machine deals with outliers and artifact which are caused by beam hardening artifact and the curse of dimensionality problem. Furthermore, the percentages of correctness it classifies pore-space and the uncertainties within which porosity can be estimated.