| 基于VGG模型的岩石薄片图像识别 |
| |
| 引用本文： | 白林,魏昕,刘禹,吴崇阳,陈立辉.基于VGG模型的岩石薄片图像识别[J].地质通报,2019,38(12):2053-2058. |
| |
| 作者姓名： | 白林 魏昕 刘禹 吴崇阳 陈立辉 |
| |
| 作者单位： | 成都理工大学数学地质四川省重点实验室, 四川 成都 610059;成都理工大学管理科学学院, 四川 成都 610059;自然资源部地质信息技术重点实验室, 北京 100037,成都理工大学地球科学学院, 四川 成都 610059,成都理工大学管理科学学院, 四川 成都 610059,成都理工大学管理科学学院, 四川 成都 610059,成都理工大学地球科学学院, 四川 成都 610059 |
| |
| 基金项目： | 国家重点研发计划《基于“地质云”平台的深部找矿知识挖掘》（编号：2016YFC0600510）、四川省应用基础研究项目《基于人工智能方法的岩石和矿物自动识别技术研究》（编号：2018JY0112）、自然资源部地质信息技术重点实验室开放课题《基于深度学习的野外岩石识别技术研究及应用》（编号：2018433） |
| |
| 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。
|
| 关 键 词： | 岩石薄片图像 深度学习 VGG 特征提取 |
| 收稿时间： | 2019/4/17 0:00:00 |
| 修稿时间： | 2019/7/16 0:00:00 |
Rock thin section image recognition and classification based on VGG model |
| |
| BAI Lin,WEI Xin,LIU Yu,WU Chongyang and CHEN Lihui.Rock thin section image recognition and classification based on VGG model[J].Geologcal Bulletin OF China,2019,38(12):2053-2058. |
| |
| Authors: | BAI Lin WEI Xin LIU Yu WU Chongyang and CHEN Lihui |
| |
| Affiliation: | Geomathematics Key Laboratory of Sichuan Province, Chengdu University of Technology, Chengdu 610059, Sichuan, China;College of Management Science, Chengdu University of Technology, Chengdu 610059, Sichuan, China;Key Laboratory of Geological Information Technology, Ministry of Natural Resources, Beijing 100037, China,College of Earth Sciences, Chengdu University of Technology, Chengdu 610059, Sichuan, China,College of Management Science, Chengdu University of Technology, Chengdu 610059, Sichuan, China,College of Management Science, Chengdu University of Technology, Chengdu 610059, Sichuan, China and College of Earth Sciences, Chengdu University of Technology, Chengdu 610059, Sichuan, China |
| |
| 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. |
| |
| Keywords: | rock thin section images deep learning VGG feature extraction |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《地质通报》浏览原始摘要信息 |
|
点击此处可从《地质通报》下载全文 |
|
