Deep neural networks for automatic grain-matrix segmentation in plane and cross-polarized sandstone photomicrographs

• Published in: Applied intelligence (Dordrecht, Netherlands) Vol. 52; no. 3; pp. 2332 - 2345
• Main Authors: Das, Rajdeep, Mondal, Ajoy, Chakraborty, Tapan, Ghosh, Kuntal
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.02.2022; Springer Nature B.V
• Subjects: Artificial Intelligence; Artificial neural networks; Computer Science; Grains; Image segmentation; Machine learning; Machines; Manufacturing; Mechanical Engineering; Neural networks; Petrography; Photomicrographs; Processes; Sandstone; Semantic segmentation; Semantics; Grain segmentation; Sandstone photomicrograph; Data-driven; Semantic segmentation
• ISSN: 0924-669X; 1573-7497
• DOI: 10.1007/s10489-021-02530-z

Grain segmentation of sandstone that is partitioning the grain from its surrounding matrix/cement in the thin section is the primary step for computer-aided mineral identification and sandstone classification. The photomicrograph of sandstone contain many mineral grains and their surrounding matrix/cement. The distinction between adjacent grains and the matrix is often ambiguous, making grain segmentation difficult. Various solutions exist in literature to handle these problems; however, they are not robust against sandstone petrography’s varied pattern. In this paper, we formulate grain segmentation as a pixel-wise two-class (i.e., grain and background) semantic segmentation task. We develop a deep learning-based end-to-end trainable framework named Deep Semantic Grain Segmentation network ( dsgsn ), a data-driven method, and provide a generic solution. As per the authors’ knowledge, this is the first work where the deep neural network is explored to solve the grain segmentation problem. Extensive experiments on the images highlight that our method obtains better segmentation accuracy than various segmentation architectures with more parameters.