English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

Rock classification plays an important role in rock mechanics, petrology,mining engineering, magmatic processes, and numerous other fields pertaining togeosciences. This study proposes a concatenated convolutional neural network(Con-CNN) method for classifying the geologic rock type based on petrographicthin sections. Herein, plane polarized light (PPL) and crossed polarized light(XPL) were used to acquire thin section images as the fundamental data. Afterconducting the necessary pre-processing analyses, the PPL and XPL images aswell as their comprehensive image (CI) were incorporated in three convolutionalneural networks (CNNs) comprising the same structure for achieving apreliminary classification; these images were developed by employing the fusedprincipal component analysis (PCA). Subsequently, the results of the CNNs wereconcatenated by using the maximum likelihood detection to obtain acomprehensive classification result. Finally, a statistical revision wasapplied to fix the misclassification due to the proportion difference ofminerals that were similar in appearance. In this study, 13 types of 92 rocksamples, 196 petrographic thin sections, 588 images, and 63504 image patcheswere fabricated for the training and validation of the Con-CNN. The five-foldscross validation shows that the method proposed provides an overall accuracy of89.97%, which facilitates the automation of rock classification in petrographicthin sections.

Rock Classification in Petrographic Thin Section Images Based on Concatenated Convolutional Neural Networks