Shape Descriptors for Porous Media Analysis Using Computed Tomography Images

Abstract

In this study, we propose a new framework for 3D porous media shape characterization using quantitative data driven shape descriptors. The main conceptual innovations are the introduction of shape descriptors based on geometrical parameters of the shape and empirical mode decomposition (EMD) of the shape skeleton. The EMD yields a decomposition with intrinsic mode functions based on local properties of the skeleton. Efficient methods for computing the defined descriptors from a network of balls representation of the pore space are provided. A multivariate analysis is carried out to describe the relationships between the shape descriptors and justify their use in the context of shape analysis. The proposed descriptors are also used to group together objects by their similarity and perform optimal approximation of the porous media by primitives set. Properties on the approximation are given and discussed. The proposed framework is illustrated with computed tomography images of real soil sample. The results have demonstrated the performance of our methodology for shape characterization, optimal shape decomposition and comparison.