Journal of Computer Applications ›› 2026, Vol. 46 ›› Issue (7): 2355-2363.DOI: 10.11772/j.issn.1001-9081.2025060785

• Frontier and comprehensive applications • Previous Articles    

Rock thin section lithology identification model based on improved GhostNet

Miaomiao LIU1,2, Yuhong ZHANG1(), Qiang ZHANG1,2, Ruishan DU1,2   

  1. 1.School of Computer and Information Technology,Northeast Petroleum University,Daqing Heilongjiang 163318,China
    2.Heilongjiang Provincial Key Laboratory of Petroleum Big Data and Intelligent Analysis (Northeast Petroleum University),Daqing Heilongjiang 163318,China
  • Received:2025-07-16 Revised:2025-10-23 Accepted:2025-10-29 Online:2025-11-12 Published:2026-07-10
  • Contact: Yuhong ZHANG
  • About author:LIU Miaomiao, born in 1982, Ph. D., professor. Her research interests include data mining, swarm intelligence algorithm, oil and gas big data.
  • Supported by:
    National Natural Science Foundation of China(42002138);Natural Science Foundation of Hebei Province(D2023107002);Postdoctoral Scientific Research and Development Start Fund of Heilongjiang Province(LBH-Q20073);Key Project of Higher Education Teaching Reform Research in Heilongjiang Province(SJGZY2024088)

基于改进GhostNet的岩石薄片岩性识别模型

刘苗苗1,2, 张郁红1(), 张强1,2, 杜睿山1,2   

  1. 1.东北石油大学 计算机与信息技术学院,黑龙江 大庆 163318
    2.黑龙江省石油大数据与智能分析重点实验室(东北石油大学),黑龙江 大庆 163318
  • 通讯作者: 张郁红
  • 作者简介:刘苗苗(1982—),女,河南洛阳人,教授,博士,CCF高级会员,主要研究方向:数据挖掘、群体智能算法、油气大数据;
  • 基金资助:
    国家自然科学基金资助项目(42002138);河北省自然科学基金资助项目(D2023107002);黑龙江省博士后科研启动金资助项目(LBH-Q20073);黑龙江省高等教育教学改革研究重点项目(SJGZB2024088)

Abstract:

To address the issues of low identification accuracy and poor efficiency in rock thin section lithology identification, a rock thin section lithology identification model based on improved GhostNet was proposed. First, an edge guidance module was constructed using multi-directional Sobel operator to extract edge and texture information from rock thin section images effectively. Second, CBAM (Convolutional Block Attention Module) was embedded at key positions within the GhostNet model to enhance the feature extraction capability and further improve the model's identification performance. Finally, the classifier structure was redesigned by replacing the original classifier with a global average pooling layer, so as to reduce the model's parameters, thereby improving the model training efficiency. A hierarchical classification method was adopted to divide the dataset into three major categories and 108 small categories for coarse-grained and fine-grained identification, respectively. Experimental results showed that the proposed model achieved a first-level classification accuracy of 98.15% and a second-level classification accuracy of 96.39% on the test set, with a model size of 16.3 MB. Compared with EfficientNetV2, the proposed model achieved a 1.31 percentage point improvement in first-level classification accuracy and an 81% reduction in parameters. The proposed model demonstrates superior classification performance and provides an efficient and accurate solution for lithology identification of rock thin sections.

Key words: rock thin section, lithology identification, GhostNet, edge information, CBAM (Convolutional Block Attention Module), lightweight neural network

摘要:

针对岩石薄片岩性识别中存在的识别精度不高和效率低等问题,提出一种基于改进GhostNet的岩石薄片岩性识别模型。首先,采用多方向Sobel算子构建边缘引导模块,有效提取岩石薄片图像中的边缘和纹理信息;其次,在GhostNet模型的关键位置嵌入卷积块注意力模块(CBAM)强化模型的特征提取能力,进一步提高模型的识别效果;最后,重新设计分类器结构,用全局平均池化层替换原始分类器,减少模型的参数量,提高模型训练效率。采用分层分类方法将数据集分为3大类别和108小类,分别进行粗粒度和细粒度识别。实验结果表明,本文模型在测试集上的一级分类准确率为98.15%,二级分类准确率为96.39%,模型大小为16.3 MB。与EfficientNetV2相比,本文模型在一级分类准确率上提高了1.31个百分点,参数量减少了81%,展现出更佳的分类性能,能够为岩石薄片的岩性识别提供高效且准确的解决方案。

关键词: 岩石薄片, 岩性识别, GhostNet, 边缘信息, 卷积块注意力模块, 轻量级神经网络

CLC Number: