Rock thin section image recognition and classification based on VGG model
-
摘要:
岩石薄片图像的复杂性和多解性，导致岩石薄片分类难度较大。尝试将深度学习方法应用于岩石薄片图像分类。实验选取了安山岩、白云岩、花岗岩等6种常见岩石种类的薄片图像，每类1000张图像作为实验数据，建立了岩石薄片分类的VGG模型，经过9万次训练后，测试集识别准确率达到了82%。对实验结果进行了分析，发现相似组成成分的岩石图像容易混淆，如白云岩与鲕粒灰岩均属于碳酸盐岩，容易相互误判。在安山岩特征图中提取出了斜长石斑晶和微晶及隐晶质或玻璃质基质，在鲕粒灰岩特征图中提取了鲕粒及填隙物中的亮晶方解石，也验证了方法的可靠性。
Abstract:The complexity and multiple solutions of rock thin section images lead to the difficulty in classification of rock thin sections. This paper attempts to apply the deep learning method to the classification of rock thin images. Thin section images of 6 common rock types, such as andesite, dolomite and granite, were selected in the experiment, and 1000 images of each type were used as experimental data. The VGG model was established, and the identification accuracy of the verification set reached 82% after 90, 000 iterations. Based on the analysis of the experimental data, the authors found that the rock images with similar compositions are easy to be confused; for example, dolomite and oolitic limestone are both carbonate rocks and it is easy to misjudge each other. Plagioclase porphyry, microcrystalline and cryptocrystalline or vitreous matrix were extracted from the andesite characteristic diagram, and oolitic and interstitial materials were extracted from the oolitic limestone characteristic diagram. The result obtained by the authors proves that the VGG model is effective in the classification of rock thin section.
-
Key words:
- rock thin section images /
- deep learning /
- VGG /
- feature extraction
-
-
表 2 薄片图像分类混淆矩阵
Table 2. Confusion matrix of rock thin section images classification
准确率 安山岩 白云岩 鲕粒灰岩 花岗岩 岩屑砂岩 石英砂岩 安山岩 0.76 0.07 0.04 0.07 0.04 0.03 白云岩 0.12 0.74 0.10 0.00 0.01 0.00 鲕粒灰岩 0.05 0.11 0.80 0.03 0.01 0.01 花岗岩 0.05 0.01 0.01 0.79 0.05 0.09 岩屑砂岩 0.00 0.01 0.00 0.00 0.98 0.01 石英砂岩 0.03 0.03 0.00 0.05 0.00 0.89 
下载: 导出CSV
-
[1] 赵鹏大.大数据时代数字找矿与定量评价[J].地质通报, 2015, 34(7):1255-1259. doi: 10.3969/j.issn.1671-2552.2015.07.001 http://dzhtb.cgs.cn/gbc/ch/reader/view_abstract.aspx?file_no=20150701&flag=1
[2] 严光生, 薛群威, 肖克炎, 等.地质调查大数据研究的主要问题分析[J].地质通报, 2015, 34(7):1273-1279. doi: 10.3969/j.issn.1671-2552.2015.07.004 http://dzhtb.cgs.cn/gbc/ch/reader/view_abstract.aspx?file_no=20150704&flag=1
[3] 陈建平, 李婧, 崔宁, 等.大数据背景下地质云的构建与应用[J].地质通报, 2015, 34(7):1260-1265. doi: 10.3969/j.issn.1671-2552.2015.07.002 http://dzhtb.cgs.cn/gbc/ch/reader/view_abstract.aspx?file_no=20150702&flag=1
[4] 肖克炎, 孙莉, 李楠, 等.大数据思维下的矿产资源评价[J].地质通报, 2015, 34(7):1266-1272. doi: 10.3969/j.issn.1671-2552.2015.07.003 http://dzhtb.cgs.cn/gbc/ch/reader/view_abstract.aspx?file_no=20150703&flag=1
[5] 刘延保, 曹树刚, 刘玉成.基于LS-SVM的岩石细观图像分析方法探讨[J].岩石力学与工程学报, 2008, 27(5):1059-1059. doi: 10.3321/j.issn:1000-6915.2008.05.023
[6] Singh N, Singh T, Tiwary A, et al. Textural identification of basaltic rock mass using image processing and neural network[J]. Computers & Geosciences, 2010, 14(2):301-310. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=e5bbc337a064438c325901c36779c007
[7] Ghiasi-Freez J, Soleimanpour I, Kadkhodaie-Ilkhchi A, et al. Semiautomated porosity identification from thin section images using image analysis and intelligent discriminant classifiers[J]. Computers & Geosciences, 2012, 45:36-45. http://cn.bing.com/academic/profile?id=82b283e13aca9119ad91ea694b948afa&encoded=0&v=paper_preview&mkt=zh-cn
[8] Mlynarczuk M, Górszczyk A, 's ipek B. The application of pattern recognition in the automatic classification of microscopicrock images[J]. Computers & Geosciences, 2013, 60(10):126-133. https://www.sciencedirect.com/science/article/pii/S0098300413002112
[9] 程国建, 杨静, 黄全舟, 等.基于概率神经网络的岩石薄片图像分类识别研究[J].科学技术与工程, 2013, 13(31):9231-9235. doi: 10.3969/j.issn.1671-1815.2013.31.014
[10] Marmo R, Amodio S, Tagllaferri R, et al. Textural identification of carbonate rocks by image processing and neural network:Methodology proposal and examples[J]. Computers & Geosciences, 2014, 31(5):649-659. http://cn.bing.com/academic/profile?id=60d02dc69c877935dbe0f7e5d3369c14&encoded=0&v=paper_preview&mkt=zh-cn
[11] 郭超, 刘烨.多色彩空间下的岩石图像识别研究[J].科学技术与工程, 2014, 14(18):247-251. doi: 10.3969/j.issn.1671-1815.2014.18.048
[12] 刘烨, 程国建, 马微, 等.基于铸体薄片图像颜色空间与形态学梯度的岩石分类[J].中南大学学报(自然科学版), 2016, 47(7):2375-2382. http://d.old.wanfangdata.com.cn/Periodical/zngydxxb201607027
[13] Li N, Hao H, Gu Q, et al. A transfer learning method for automatic identification of sandstone microscopic images[J]. Computers & Geosciences, 2017, 103:111-121. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=4f089a754e0740883b9f130f730af2f3
[14] 白林, 姚钰, 李双涛, 等.基于深度学习特征提取的岩石图像矿物成分分析[J].中国矿业, 2018, 27(7):178-182. http://d.old.wanfangdata.com.cn/Periodical/zgky201807038
[15] Hinton G E, Osindero S, Teh Y W. A Fast Learning Algorithm for Deep Belief Nets[J]. Neural Computation, 2006, 18(7):1527-1554. doi: 10.1162/neco.2006.18.7.1527
[16] Krizhevsky A, Sutskever I, Hinton G. ImageNet Classification with Deep Convolutional Neural Networks[C]//NIPS. Curran Associates Inc., 2012.
[17] Lecun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11):2278-2324. doi: 10.1109/5.726791
[18] Zhu Y, Bai L, Peng W, et al. Depthwise Separable Convolution Feature Learning for Ihomogeneous Rock Image Classification[C]//ICCSIP, 2018, 1005: 165-176.
-
图(3)
表(3)
计量
- 文章访问数: 1241
- PDF下载数: 13
- 施引文献: 0