Author(s)

He Ma

Affiliation(s)

Yellow River Engineering Consulting Co., Ltd., Zhengzhou 450003, Henan, China.

Corresponding Author

He Ma

ABSTRACT

Lithology identification is a fundamental task in resource exploration and engineering geology, yet traditional methods face bottlenecks such as low efficiency and high subjectivity. In recent years, intelligent rock image recognition techniques based on convolutional neural network (CNN) have demonstrated remarkable advantages. This paper systematically reviews the research progress of CNN in intelligent rock image recognition and explores their application potential and technical challenges in this field. First, the basic architecture and working principles of CNN are introduced, including the synergistic interactions among convolutional layers, pooling layers, and fully connected layers. Subsequently, the criteria for model selection and optimization pathways in rock image recognition are analyzed, covering task-specific model adaptation strategies and multi-model comparative evaluation and selection strategies. Additionally, the roles of data augmentation strategies, resolution enhancement techniques, and model architecture innovations in improving model performance are discussed. Finally, this paper summarizes the limitations of current research and proposes future research directions, aiming to provide theoretical support and practical guidance for overcoming existing technical bottlenecks.

KEYWORDS

Convolutional neural network; Rock image; Lithology identification; Identification mode; Optimization path

CITE THIS PAPER

He Ma. Advances in intelligent rock image recognition based on Convolutional Neural Networks. Journal of Computer Science and Electrical Engineering. 2025, 7(7): 71-79. DOI: https://doi.org/10.61784/jcsee3104.

REFERENCES

[1] Liu X, Wang H, Jing H, et al. Research on intelligent identification of rock types based on Faster R-CNN method. IEEE Access, 2020, 8: 21804-21812.

[2] Zhang Y, Ye Y L, Guo D J, et al. PCA-VGG16 model for classification of rock types. Earth Science Informatics, 2024, 17(2): 1553-1567.

[3] Wu Lei, Zhai Xinwei, Wang Erteng, et al. Geochemical characteristics and formation environment of Jijitaizi ophiolite in Beishan area. Northwestern Geology, 2025, 58(1): 27-42.

[4] Meng Wuyi, Zhang Zhen, Gao Yongbao, et al. Mineral composition and geological significance of the newly discovered Wangzhuang gold deposit in Southern Qinling. Northwestern Geology, 2024, 57(4): 157-169.

[5] Liu Hao, Cui Junping, Jin Wei, et al. Geochemical characteristics and geological significance of granites in the eastern Songliao Basin. Northwestern Geology, 2024, 57(2): 46-58.

[6] Dai Xinyu, Zhou Bin, Li Xinlin, et al. Geochronology, geochemistry and tectonic significance of Miocene quartz monzonite intrusions in the north of Qitaidaban, West Kunlun. Northwestern Geology, 2024, 57(4): 191-205.

[7] Chen Yangyang, Duan Jun, Xu Gang, et al. Geochemical characteristics and tectonic significance of Late Triassic lamprophyres in Beishan area, Gansu Province. Northwestern Geology, 2024, 57(6): 78-94.

[8] Bai Lin, Yao Yu, Li Shuangtao, et al. Mineral composition analysis of rock images based on deep learning feature extraction. China Mining Magazine, 2018, 27(7): 178-182.

[9] Li Yan. Rock image recognition based on deep learning. Beijing: Beijing Forestry University, 2020.

[10] Tan Yongjian, Tian Miao, Xu Dexin, et al. Research on rock image classification and recognition based on Xception network. Geography and Geo-Information Science, 2022, 38(3): 17-22.

[11] Liu X, Wang H, Jing H, et al. Research on intelligent identification of rock types based on Faster R-CNN method. IEEE Access, 2020, 8: 21804-21812.

[12] Yuan Hang. Research on intelligent lithology identification method based on rock image feature learning. 2023.

[13] Marmo R, Amodio S, Tagllaferri R, et al. Textural identification of carbonate rocks by image processing and neural network: methodology proposal and examples. Computers & Geosciences, 2005, 31(5): 649-659.

[14] Chatterjee S. Vision-based rock-type classification of limestone using multi-class support vector machine. Applied Intelligence, 2013, 39: 14-27.

[15] Cheng Guojian, Yin Juanjuan. Rock thin section image classification based on SVM. Technology Innovation and Application, 2015, 5(1): 38.

[16] Izadi H, Sadri J, Bayati M. An intelligent system for mineral identification in thin sections based on a cascade approach. Computers & Geosciences, 2017, 99: 37-49.

[17] Chai H, Li N, Xiao C, et al. Automatic discrimination of sedimentary facies and lithologies in reef-bank reservoirs using borehole image logs. Applied Geophysics, 2009, 6: 17-29.

[18] Zhang F, Liu J, Lu X, et al. Spatial weighted graph-driven fault diagnosis of complex process industry considering technological process flow. Measurement Science and Technology, 2023, 34(12): 125143.

[19] Hinton G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networks. Science, 2006, 313(5786): 504-507.

[20] Zhang Ye, Li Mingchao, Han Shuai. Automatic identification and classification method of lithology based on deep learning of rock images. Acta Petrologica Sinica, 2018, 34(2): 333-342.

[21] Xu Zhenhao, Ma Wen, Lin Peng, et al. Intelligent lithology identification based on transfer learning of rock images. Journal of Basic Science and Engineering, 2021, 29(5): 1075-1092.

[22] Feng Yaxing, Gong Xi, Xu Yongyang, et al. Lithology identification method based on fresh rock surface images and Siamese convolutional neural networks. Geography and Geo-Information Science, 2019, 35(5): 89-94.

[23] Ran X, Xue L, Zhang Y, et al. Rock classification from field image patches analyzed using a deep convolutional neural network. Mathematics, 2019, 7: 755.

[24] Fan G, Chen F, Chen D, et al. Recognizing multiple types of rocks quickly and accurately based on lightweight CNNs model. IEEE Access, 2020, 8: 55269-55278.

[25] Wang C, Li Y, Fan G, et al. Quick recognition of rock images for mobile applications. Journal of Engineering Science and Technology Review, 2018, 11(4): 111-117.

[26] Fan G, Chen F, Chen D, et al. A deep learning model for quick and accurate rock recognition with smartphones. Mobile Information Systems, 2020, 2020: 1-14.

[27] Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks. Communications of the ACM, 2017, 60(6): 84-90.

[28] Chollet F. Xception: deep learning with depthwise separable convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017.

[29] Szegedy C, Vanhoucke V, Ioffe S, et al. Rethinking the Inception architecture for computer vision. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.

[30] He K M, Zhang X Y, Ren S Q, et al. Deep residual learning for image recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.

[31] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv, 2015.

[32] Zhang Z, Tang J, Fan B, et al. An intelligent lithology recognition system for continental shale by using digital coring images and convolutional neural networks. Geoenergy Science and Engineering, 2024, 239: 212909.

[33] Dong Wenhao, Zhang Huai. Lithology identification of cuttings based on transfer learning. Journal of University of Chinese Academy of Sciences, 2023, 40(6): 743-750.

[34] Alzubaidi F, Mostaghimi P, Swietojanski P, et al. Automated lithology classification from drill core images using convolutional neural networks. Journal of Petroleum Science and Engineering, 2021, 197: 107933.

[35] Zhang W, Zhang W, Zhang G, et al. Hard-rock tunnel lithology identification using multi-scale dilated convolutional attention network based on tunnel face images. Frontiers of Structural and Civil Engineering, 2024, 17(12): 1796-1812.

[36] Wang Xiaobing, Liu Lin, Wang Junqing, et al. Research on lithology identification of rock images based on convolutional neural network ResNet50 residual network. Geotechnical Engineering Technique, 2024, 38(3): 294-302.

[37] Xiong Feng, Liao Yifan, Cao Weiteng, et al. Automatic lithology identification based on convolutional neural network-deep transfer learning. Safety and Environmental Engineering, 2023, 30(4): 26-34.

[38] Ma Zedong, Ma Lei, Li Ke, et al. Multi-scale lithology identification based on deep learning of rock images. Bulletin of Geological Science and Technology, 2022, 41(6): 316-322.

[39] Xiong Yuehan, Liu Dongyan, Liu Dongsheng, et al. Automatic lithology classification method based on deep learning of mesoscopic images of rock samples. Journal of Jilin University (Earth Science Edition), 2021, 51(5): 1597-1604.

[40] Hu Qicheng, Ye Weimin, Wang Qiong, et al. Research on lithology identification based on big data of geological images. Journal of Engineering Geology, 2020, 28(6): 1433-1440.

[41] Chen Zhongliang, Yuan Feng, Li Xiaohui, et al. Interpretability study of deep transfer learning for images of plutonic intrusive rocks from Dabie Mountain. Geological Review, 2023, 69(6): 2263-2273.

[42] Xu Z, Ma W, Lin P, et al. Deep learning of rock microscopic images for intelligent lithology identification: neural network comparison and selection. Journal of Rock Mechanics and Geotechnical Engineering, 2022, 14(4): 1140-1152.

[43] Yang Lei, Xiong Chang, Liu Wenchao, et al. Research on lithology identification of cuttings based on improved ResNet deep residual network. Journal of Yangtze University (Natural Science Edition), 2023, 20(2): 11-19.

[44] Ren Wei, Zhang Sheng, Qiao Jihua, et al. Intelligent identification of rock and minerals based on deep learning. Geological Review, 2021, 67(S1): 1281-1282.

[45] Han Xinhao, He Yueshun, Chen Jie, et al. Research on intelligent identification of rock lithology based on Swin Transformer. Modern Electronics Technique, 2024, 47(7): 37-44.

[46] Zhang Chaoqun, Yi Yunheng, Zhou Wenjuan, et al. Small sample rock classification based on deep learning and data augmentation technology. Science Technology and Engineering, 2022, 22(33): 14786-14794.

[47] Liu Xiaobo, Wang Huaiyuan, Wang Liancheng. Faster R-CNN method for intelligent identification of rock types. Modern Mining, 2019, 35(5): 60-64.

[48] Xu Shuteng, Zhou Yongzhang. Experimental research on intelligent identification of microscopic ore minerals based on deep learning. Acta Petrologica Sinica, 2018, 34(11): 3244-3252.

[49] Theodoridis S. Machine learning: a Bayesian and optimization perspective. Academic Press, 2015.

[50] Bai Lin, Wei Xin, Liu Yu, et al. Rock thin section image recognition based on VGG model. Geological Bulletin of China, 2019, 38(12): 2053-2058.

[51] Xiao Chengyong, Li Qing, Li Hui, et al. Ore type detection algorithm based on improved Mask R-CNN. Sintering and Pelletizing, 2024, 49(2): 65-73, 106.

[52] Yang Z, He B N, Liu Y, et al. Classification of rock fragments produced by tunnel boring machine using convolutional neural networks. Automation in Construction, 2021, 125: 103612.

[53] Xu Z, Ma W, Lin P, et al. Deep learning of rock images for intelligent lithology identification. Computers & Geosciences, 2021, 154: 104799.

[54] Xu Z, Shi H, Lin P, et al. Intelligent on-site lithology identification based on deep learning of rock images and elemental data. IEEE Geoscience and Remote Sensing Letters, 2022, 19: 1-5.