logo

SCIENCE CHINA Information Sciences, Volume 50 , Issue 1 : 1(2020) https://doi.org/10.1360/N112018-00089

Grain segmentation of sandstone thin section images based on semantic feature extraction

More info
  • ReceivedApr 15, 2018
  • AcceptedAug 4, 2018
  • PublishedJan 2, 2020

Abstract

砂岩薄片鉴定是矿物学和采矿工程中的一个重要步骤, 其基础是将砂岩薄片图像包含的矿物颗粒分割到独立区域. 不同于一般图像分割问题, 砂岩薄片图像中包含大量矿物颗粒, 且相邻颗粒之间边界模糊, 通用的图像分割方法难以适用. 本文利用多角度砂岩薄片图像, 使用卷积神经网络和模糊聚类技术, 提出一种3阶段颗粒分割方法. 第1阶段, 将输入的多角度砂岩图像预分割成超像素集合. 第2阶段, 根据砂岩矿物特点构建卷积神经网络RockNet, 先使用带标签的砂岩矿物颗粒图像库训练RockNet, 然后将之用于提取超像素语义特征. 第3阶段, 提出区域合并方法FCoG, 该方法融合多特征用于聚类和合并超像素, 并生成最终的矿物颗粒. 对采集自多个地区和不同地质年代的砂岩薄片图像数据集进行实验,结果表明本文方法的有效性, 其性能明显优于其他分割方法.


Funded by

国家自然科学基金(批准号: 61373012,61321491,91218302和国家重点研发计划项目(批准号: 2018YFB1003800)


References

[1] Li N, Hao H, Gu Q. A transfer learning method for automatic identification of sandstone microscopic images. Comput Geosci, 2017, 103: 111-121 CrossRef ADS Google Scholar

[2] Zhou Y, Starkey J, Mansinha L. Segmentation of petrographic images by integrating edge detection and region growing. Comput Geosci, 2004, 30: 817-831 CrossRef ADS Google Scholar

[3] Gorsevski P V, Onasch C M, Farver J R. Detecting grain boundaries in deformed rocks using a cellular automata approach. Comput Geosci, 2012, 42: 136-142 CrossRef ADS Google Scholar

[4] Yesiloglu-Gultekin N, Keceli A S, Sezer E A. A computer program (TSecSoft) to determine mineral percentages using photographs obtained from thin sections. Comput Geosci, 2012, 46: 310-316 CrossRef ADS Google Scholar

[5] Izadi H, Sadri J, Mehran N A. A new intelligent method for minerals segmentation in thin sections based on a novel incremental color clustering. Computers & Geosci, 2015, 81: 38-52 DOI:10.1016/j.cageo.2015.04.008. Google Scholar

[6] Lu B, Cui M, liu Q. Automated grain boundary detection using the level set method. Comput Geosci, 2009, 35: 267-275 CrossRef ADS Google Scholar

[7] Jungmann M, Pape H, Wi?kirchen P. Segmentation of thin section images for grain size analysis using region competition and edge-weighted region merging. Comput Geosci, 2014, 72: 33-48 CrossRef ADS Google Scholar

[8] Fueten F, Mason J. An artificial neural net assisted approach to editing edges in petrographic images collected with the rotating polarizer stage. Comput Geosci, 2007, 33: 1176-1188 CrossRef ADS Google Scholar

[9] Dai J, He K, Sun J. Instance-aware semantic segmentation via multi-task network cascades. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, 2016. 3150--3158. Google Scholar

[10] Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks. In: Proceedings of Advances in Neural Information Processing Systems, Lake Tahoe, 2012. 1097--1105. Google Scholar

[11] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. In: Proceedings of the International Conference on Learning Representations, San Diego, 2015. Google Scholar

[12] He K, Zhang X, Ren S, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition. In: Proceedings of the 13rd European Conference on Computer Vision, Zurich, 2014. 346--361. Google Scholar

[13] Girshick R. Fast r-cnn. In: Proceedings of the 15th IEEE International Conference on Computer Vision, Santiago, 2015. 1440--1448. Google Scholar

[14] Ji Z, Xiong K, Pang Y, et al. Video summarization with attention-based encoder-decoder networks. 2017,. arXiv Google Scholar

[15] Pang Y, Ye L, Li X. Incremental Learning With Saliency Map for Moving Object Detection. IEEE Trans Circuits Syst Video Technol, 2018, 28: 640-651 CrossRef Google Scholar

[16] Pang Y, Sun M, Jiang X. Convolution in Convolution for Network in Network.. IEEE Trans Neural Netw Learning Syst, 2018, 29: 1587-1597 CrossRef PubMed Google Scholar

[17] Cao J, Pang Y, Li X. Randomly translational activation inspired by the input distributions of ReLU. Neurocomputing, 2018, 275: 859-868 CrossRef Google Scholar

[18] Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, 2015. 3431--3440. Google Scholar

[19] Hariharan B, Arbelaez P, Girshick R, et al. Simultaneous detection and segmentation. In: Proceedings of the 13rd European Conference on Computer Vision, Zurich, 2014. 297--312. Google Scholar

[20] Heilbronner R. Automatic grain boundary detection and grain size analysis using polarization micrographs or orientation images. J StructGeol, 2000, 22: 969-981 CrossRef ADS Google Scholar

[21] Roy Choudhury K, Meere P A, Mulchrone K F. Automated grain boundary detection by CASRG. J StructGeol, 2006, 28: 363-375 CrossRef ADS Google Scholar

[22] Jiang F, Gu Q, Hao H Z, et al. Survey on content-based image segmentation methods. Journal of Software. 2017, 28: 160--183. Google Scholar

[23] Wu Z, Leahy R. An optimal graph theoretic approach to data clustering: theory and its application to image segmentation. IEEE Trans Pattern Anal Machine Intell, 1993, 15: 1101-1113 CrossRef Google Scholar

[24] Jianbo Shi , Malik J. Normalized cuts and image segmentation. IEEE Trans Pattern Anal Machine Intell, 2000, 22: 888-905 CrossRef Google Scholar

[25] Ding C, He X, Zha H, et al. A Min-max Cut Algorithm for Graph Partitioning and Data Clustering. In: Proceedings of IEEE International Conference on Data Mining, San Jose, 2001. 107--114. Google Scholar

[26] Boykov Y, Funka-Lea G. Graph Cuts and Efficient N-D Image Segmentation. Int J Comput Vision, 2006, 70: 109-131 CrossRef Google Scholar

[27] Rother C, Kolmogorov V, Blake A. "GrabCut". ACM Trans Graph, 2004, 23: 309-314 CrossRef Google Scholar

[28] Felzenszwalb P F, Huttenlocher D P. Efficient Graph-Based Image Segmentation. Int J Comput Vision, 2004, 59: 167-181 CrossRef Google Scholar

[29] Van den Bergh M, Boix X, Roig G. SEEDS: Superpixels Extracted Via Energy-Driven Sampling. Int J Comput Vis, 2015, 111: 298-314 CrossRef Google Scholar

[30] Comaniciu D, Meer P. Mean shift: a robust approach toward feature space analysis. IEEE Trans Pattern Anal Machine Intell, 2002, 24: 603-619 CrossRef Google Scholar

[31] Sheikh Y A, Khan E A, Kanade T. Mode-seeking by medoidshifts. In: Proceedings of the 11th IEEE International Conference on Computer Vision, Rio de Janeiro, 2007. 1--8. Google Scholar

[32] Vedaldi A, Soatto S. Quick shift and kernel methods for mode seeking. In: Proceedings of the 10th European Conference on Computer Vision, Marseille, 2008. 705--718. Google Scholar

[33] Levinshtein A, Stere A, Kutulakos K N. TurboPixels: fast superpixels using geometric flows.. IEEE Trans Pattern Anal Mach Intell, 2009, 31: 2290-2297 CrossRef PubMed Google Scholar

[34] Achanta R, Shaji A, Smith K. SLIC superpixels compared to state-of-the-art superpixel methods.. IEEE Trans Pattern Anal Mach Intell, 2012, 34: 2274-2282 CrossRef PubMed Google Scholar

[35] Jiang F, Gu Q, Hao H, et al. Grain segmentation of multi-angle petrographic thin section microscopic images. In: Proceedings of the IEEE International Conference on Image Processing, Beijing, 2017. 3879--3883. Google Scholar

[36] Jie Wang , Lili Ju , Xiaoqiang Wang . An Edge-Weighted Centroidal Voronoi Tessellation Model for Image Segmentation. IEEE Trans Image Process, 2009, 18: 1844-1858 CrossRef PubMed ADS Google Scholar

[37] Russakovsky O, Deng J, Su H. ImageNet Large Scale Visual Recognition Challenge. Int J Comput Vis, 2015, 115: 211-252 CrossRef Google Scholar

[38] Liu Z, Li X, Luo P, et al. Semantic Image Segmentation via Deep Parsing Network. In: Proceedings of the 15th IEEE International Conference on Computer Vision, Santiago, 2015. 1377--1385. Google Scholar

[39] LeCun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition. In: Proceedings of the IEEE, New York, 1998. 2278--2324. Google Scholar

[40] Zhang X D. Matrix Analysis and Applications. Beijing: Tsinghua University Press, 2013. Google Scholar

[41] Loan C F V. The ubiquitous Kronecker product. J Comput Appl Math, 2000, 123: 85-100 CrossRef ADS Google Scholar

[42] Bouvrie J. Notes on Convolutional Neural Networks. Neural Nets, 2006. https://www.mendeley.com/research-papers/notes-convolutional-neural-networks/. Google Scholar

[43] Dunn J C. A Fuzzy Relative of the ISODATA Process and Its Use in Detecting Compact Well-Separated Clusters. J Cybernetics, 1973, 3: 32-57 CrossRef Google Scholar

[44] Gong M, Liang Y, Shi J. Fuzzy C-Means Clustering With Local Information and Kernel Metric for Image Segmentation. IEEE Trans Image Process, 2013, 22: 573-584 CrossRef PubMed ADS Google Scholar

[45] Jahne B, Geissler P, Haussecker H. Handbook of Computer Vision and Applications. New York: Academic Press, 1999. Google Scholar

[46] Hu X, Garzanti E, Wang J. The timing of India-Asia collision onset - Facts, theories, controversies. Earth-Sci Rev, 2016, 160: 264-299 CrossRef Google Scholar

[47] Achanta R, Susstrunk S. Superpixels and Polygons Using Simple Non-iterative Clustering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Hawaii, 2017. 4895--4904. Google Scholar

[48] Monteiro F C, Campilho A C. Performance Evaluation of Image Segmentation. In: Proceedings of the International Conference on Image Analysis and Recognition, Povoa de Varzim, 2006. 248--259. Google Scholar

[49] Chen J, Li Z, Huang B. Linear Spectral Clustering Superpixel. IEEE Trans Image Process, 2017, 26: 3317-3330 CrossRef PubMed ADS Google Scholar

[50] Jiang F, Gu Q, Hao H. A method for automatic grain segmentation of multi-angle cross-polarized microscopic images of sandstone. Comput Geosci, 2018, 115: 143-153 CrossRef ADS Google Scholar

[51] Gao W, Zhang X, Yang L, et al. An improved Sobel edge detection. In: Proceedings of the 3rd IEEE International Conference on Computer Science and Information Technology, Beijing, 2010. 67--71. Google Scholar

Copyright 2020  CHINA SCIENCE PUBLISHING & MEDIA LTD.  中国科技出版传媒股份有限公司  版权所有

京ICP备14028887号-23       京公网安备11010102003388号