KFU. Card publication. HIGH-PRECISION ALGORITHM FOR GRAIN SEGMENTATION OF THIN SECTIONS BY MULTI-ANGLE OPTICAL-MICROSCOPIC IMAGES.

KAZAN
FEDERAL UNIVERSITY

- RUS
- 中文
- ES

HIGH-PRECISION ALGORITHM FOR GRAIN SEGMENTATION OF THIN SECTIONS BY MULTI-ANGLE OPTICAL-MICROSCOPIC IMAGES.

Form of presentation

Articles in international journals and collections

Year of publication

2023

��

��

Authors, employees of KFU

Akhmetov Radik Fanusovich, author

Kayumov Zufar Damirovich, author

Kolchugin Anton Nikolaevich, author

Morozov Vladimir Petrovich, author

Murtazin Timur Aleksandrovich, author

Nurgaliev Danis Karlovich, author

Sudakov Vladislav Anatolevich, author

Tumakov Dmitriy Nikolaevich, author

Bibliographic description in the original language

Timur Murtazin, Zufar Kayumov, Vladimir Morozov, Radik Akhmetov, Anton Kolchugin, Dmitrii Tumakov, Danis Nurgaliev, Vladislav Sudakov; HIGH-PRECISION ALGORITHM FOR GRAIN SEGMENTATION OF THIN SECTIONS BY MULTI-ANGLE OPTICAL-MICROSCOPIC IMAGES. Journal of Sedimentary Research 2023;; 93 (12): 932–944. doi: https://doi.org/10.2110/jsr.2022.096

Annotation

This paper introduces an algorithm for automating the analysis of petrographic thin-section images of sandstones and siltstones. The images of thin sections are obtained in polarized light at magnifications providing good image quality. In addition, the images for each section are obtained at different angles of rotation of the microscope stage. Augmentation is applied to the obtained photographs: the number of images increases due to rotations, shifts, and rescaling of the image. For training the neural network of the Mask R-CNN architecture, transfer learning is used, with initial weights obtained from a huge variety of nongeological images. The results of image segmentation using Mask R-CNN are compared to the Watershed algorithm results and the U-Net network for two metrics. According to the standard Intersection over Union metric, U-Net for high-quality images and Watershed for blurry images show the best results with a slight superiority. However, according to the Grain Size Metric, which evaluates the accuracy of grain-size measurement, the best accuracy (over 95%) is shown by Mask R-CNN. The grain-size analysis is done, and the porosity of the studied petrographic sections is determined. The use of the proposed approaches in the study of thin sections will significantly reduce the time for obtaining the results of grain-size-distribution analysis and porosity determination. This article is the result of multidisciplinary collaboration between geologists and programmers. This has allowed for the merging of profound knowledge in the field of geology with cutting-edge data processing technologies. By employing the presented methodology, geologists can devote more time to interpreting results rather than obtaining them, which in turn enhances the efficiency of research work. The benefits of using this methodology are not limited to just speeding up the process: it also allows for increased accuracy and reliability of the analysis, minimizing human error.

Keywords

Grain segmentation, Thin section, Petrographic microscopic images, Deep learning Mask R-CNN

The name of the journal

Journal of Sedimentary Research

URL

https://pubs.geoscienceworld.org/sepm/jsedres/article-abstract/93/12/932/628766/HIGH-PRECISION-ALGORITHM-FOR-GRAIN-SEGMENTATION-OF?redirectedFrom=fulltext

Please use this ID to quote from or refer to the card

https://repository.kpfu.ru/eng/?p_id=294544&p_lang=2

Full metadata record

Field DC	Value	Language
dc.contributor.author	Akhmetov Radik Fanusovich	ru_RU
dc.contributor.author	Kayumov Zufar Damirovich	ru_RU
dc.contributor.author	Kolchugin Anton Nikolaevich	ru_RU
dc.contributor.author	Morozov Vladimir Petrovich	ru_RU
dc.contributor.author	Murtazin Timur Aleksandrovich	ru_RU
dc.contributor.author	Nurgaliev Danis Karlovich	ru_RU
dc.contributor.author	Sudakov Vladislav Anatolevich	ru_RU
dc.contributor.author	Tumakov Dmitriy Nikolaevich	ru_RU
dc.date.accessioned	2023-01-01T00:00:00Z	ru_RU
dc.date.available	2023-01-01T00:00:00Z	ru_RU
dc.date.issued	2023	ru_RU
dc.identifier.citation	Timur Murtazin, Zufar Kayumov, Vladimir Morozov, Radik Akhmetov, Anton Kolchugin, Dmitrii Tumakov, Danis Nurgaliev, Vladislav Sudakov; HIGH-PRECISION ALGORITHM FOR GRAIN SEGMENTATION OF THIN SECTIONS BY MULTI-ANGLE OPTICAL-MICROSCOPIC IMAGES. Journal of Sedimentary Research 2023;; 93 (12): 932–944. doi: https://doi.org/10.2110/jsr.2022.096	ru_RU
dc.identifier.uri	https://repository.kpfu.ru/eng/?p_id=294544&p_lang=2	ru_RU
dc.description.abstract	Journal of Sedimentary Research	ru_RU
dc.description.abstract	This paper introduces an algorithm for automating the analysis of petrographic thin-section images of sandstones and siltstones. The images of thin sections are obtained in polarized light at magnifications providing good image quality. In addition, the images for each section are obtained at different angles of rotation of the microscope stage. Augmentation is applied to the obtained photographs: the number of images increases due to rotations, shifts, and rescaling of the image. For training the neural network of the Mask R-CNN architecture, transfer learning is used, with initial weights obtained from a huge variety of nongeological images. The results of image segmentation using Mask R-CNN are compared to the Watershed algorithm results and the U-Net network for two metrics. According to the standard Intersection over Union metric, U-Net for high-quality images and Watershed for blurry images show the best results with a slight superiority. However, according to the Grain Size Metric, which evaluates the accuracy of grain-size measurement, the best accuracy (over 95%) is shown by Mask R-CNN. The grain-size analysis is done, and the porosity of the studied petrographic sections is determined. The use of the proposed approaches in the study of thin sections will significantly reduce the time for obtaining the results of grain-size-distribution analysis and porosity determination. This article is the result of multidisciplinary collaboration between geologists and programmers. This has allowed for the merging of profound knowledge in the field of geology with cutting-edge data processing technologies. By employing the presented methodology, geologists can devote more time to interpreting results rather than obtaining them, which in turn enhances the efficiency of research work. The benefits of using this methodology are not limited to just speeding up the process: it also allows for increased accuracy and reliability of the analysis, minimizing human error.	ru_RU
dc.language.iso	ru	ru_RU
dc.subject	Grain segmentation	ru_RU
dc.subject	Thin section	ru_RU
dc.subject	Petrographic microscopic images	ru_RU
dc.subject	Deep learning Mask R-CNN	ru_RU
dc.title	HIGH-PRECISION ALGORITHM FOR GRAIN SEGMENTATION OF THIN SECTIONS BY MULTI-ANGLE OPTICAL-MICROSCOPIC IMAGES.	ru_RU
dc.type	Articles in international journals and collections	ru_RU