Timur Murtazin, Zufar Kayumov, Vladimir Morozov, Radik Akhmetov, Anton Kolchugin, Dmitrii Tumakov, Danis Nurgaliev, Vladislav Sudakov
{"title":"High-precision algorithm for grain segmentation of thin section by multi-angle optical-microscopic images","authors":"Timur Murtazin, Zufar Kayumov, Vladimir Morozov, Radik Akhmetov, Anton Kolchugin, Dmitrii Tumakov, Danis Nurgaliev, Vladislav Sudakov","doi":"10.2110/jsr.2022.096","DOIUrl":null,"url":null,"abstract":"The present paper introduces an algorithm for automating the analysis of quartz sandstones and siltstones petrographic thin sections images. 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 non-geological images. The results of image segmentation using Mask R-CNN are compared versus 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 Metri c, 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.","PeriodicalId":17044,"journal":{"name":"Journal of Sedimentary Research","volume":null,"pages":null},"PeriodicalIF":2.0000,"publicationDate":"2023-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Sedimentary Research","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.2110/jsr.2022.096","RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"GEOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
The present paper introduces an algorithm for automating the analysis of quartz sandstones and siltstones petrographic thin sections images. 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 non-geological images. The results of image segmentation using Mask R-CNN are compared versus 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 Metri c, 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.
介绍了一种用于石英砂岩和粉砂岩岩石薄片图像自动分析的算法。薄片的图像是在偏振光下获得的,在放大倍率下提供良好的图像质量。此外,每个切片的图像都是在显微镜台的不同旋转角度下获得的。对获得的照片进行增强:由于图像的旋转,移位和重新缩放,图像数量增加。对于Mask R-CNN架构的神经网络的训练,使用迁移学习,初始权值从大量的非地质图像中获得。使用Mask R-CNN的图像分割结果与分水岭算法结果和U-Net网络进行了两个指标的比较。根据标准的Intersection over Union度量,高质量图像的U-Net和模糊图像的Watershed显示出最佳效果,略有优势。然而,根据评估粒度测量精度的Grain Size Metri c, Mask R-CNN的精度最高(超过95%)。对所研究的岩石剖面进行了粒度分析和孔隙度测定。在薄片研究中使用所提出的方法将大大减少获得粒度分布分析和孔隙率测定结果的时间。
期刊介绍:
The journal is broad and international in scope and welcomes contributions that further the fundamental understanding of sedimentary processes, the origin of sedimentary deposits, the workings of sedimentary systems, and the records of earth history contained within sedimentary rocks.