Automatic identification of mineral in petrographic thin sections based on images using a deep learning method

• Published in: Zhejiang da xue xue bao. Journal of Zhejiang University. Sciences edition. Li xue ban Vol. 49; no. 6; pp. 743 - 752
• Main Authors: Xu, Shengjia, Su, Cheng, Zhu, Kongyang, Zhang, Xiaocan
• Format: Journal Article
• Language: Chinese
• Published: Hangzhou Zhejiang University 01.11.2022; Zhejiang University Press
• Subjects: Artificial neural networks; Automatic identification; Deep learning; Feature extraction; Image classification; Image segmentation; Machine learning; Object recognition; Optical microscopes; Petrogenesis; Petrology; Photomicrographs; Polarized light; Semantic segmentation; Semantics; 岩石薄片图像; 深度学习; 矿物识别; 语义分割
• ISSN: 1008-9497
• DOI: 10.3785/j.issn.1008-9497.2022.06.013

The identification of minerals in petrographic thin sections is essentially required in petrological research, and is a prerequisite for further understanding of rock classification, petrogenesis, material flow and evolution history.Traditional methods rely on manual identification with optical microscope, which is costly, time-consuming, and subject to expert judgment and personal experience. Following the development of deep learning technology, it is possible for computer to automatically extract more accurate semantic information from images of petrographic thin sections. This paper proposes a deep learning-based method on petrographic thin section images for automatic mineral identification, which not only utilizes the deep convolutional neural network to extract different mineral features in the images for semantic segmentation and recognition, but also takes into account the plane polarized light images and cross polarized light images for comprehensive automatic identification. Our paper used the phot