Semiautomatic classification of cementitious materials using scanning electron microscope images

Segmentation and classification are prolific research topics in the image processing community, which have been more and more used in the context of analysis of cementitious materials, on images acquired with Scanning Electron Microscopes (SEM) . Indeed, there is a need to be able to detect and to quantify the materials present in a cement paste in order to follow the chemical reactions occurring in the material even days after the solidification. In this paper, we propose a new approach for segmentation and classification of cementitious materials based on the denoising of the data with the Block Matching 3D (BM3D) algorithm, Binary Partition Tree (BPT) segmentation, Support Vector Machines (SVM) classification, and the interactivity with the user. The BPT provides a hierarchical representation of the spatial regions of the data, allowing a segmentation to be selected among the admissible partitions of the image. SVMs are used to obtain a classification map of the image. This approach combines state-of-the-art image processing tools with the interactivity with the user to allow a better segmentation to be performed, or to help the classifier discriminate the classes better. We show that the proposed approach outperforms a previous method on synthetic data and several real datasets coming from cement samples, both qualitatively with visual examination and quantitatively with the comparison of experimental results with theoretical ones.