Material phase classification by means of Support Vector Machines

The pixel's classification of images obtained from random heterogeneous materials (RHM) is a relevant step for 3D stochastic reconstruction and to compute their physical properties, like Effective Transport Coefficients (ETC). A bad classification will impact on the computed properties. However, the literature on the topic discusses mainly the correlation functions or the properties formulae, giving little or no attention to the classification; authors mention either the use of a threshold or, in few cases, the use of Otsu's method. This paper presents a classification approach based on Support Vector Machines (SVM) and a comparison with the Otsu-based approach, based on accuracy, precision and recall. The data used for the SVM training are the key for a better classification; these data are the grayscale value, the magnitude and direction of pixels gradient. For the validation cases, the recall of the solid phase is significantly better, whilst improving the accuracy for the SVM method. Finally, a discussion about the impact on the correlation functions is presented in order to show the benefits of the proposal. (C) 2018 Elsevier B.V. All rights reserved.