Deep Neural Networks for Automatic Grain-matrix Segmentation in Plane and Cross-polarized Sandstone Photomicrographs
This work provides a generic solution for computer-aided mineral identification and sandstone classification in petrography, but it is incremental as it applies deep learning to a domain-specific task.
The authors tackled the problem of grain segmentation in sandstone photomicrographs, which is challenging due to ambiguous distinctions between grains and matrix, and developed a deep learning-based method that achieved better segmentation accuracy than existing architectures with more parameters.
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 microscopic images 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 microscopic images highlight that our method obtains better segmentation accuracy than various segmentation architectures with more parameters.