Rock image classification using deep residual neural network with transfer learning

被引:26
作者
Chen, Weihao [1 ]
Su, Lumei [1 ,2 ]
Chen, Xinqiang [1 ]
Huang, Zhihao [1 ]
机构
[1] Xiamen Univ Technol, Sch Elect Engn & Automat, Xiamen, Peoples R China
[2] Xialong Inst Engn & Technol, Longyan, Peoples R China
基金
中国国家自然科学基金;
关键词
deep learning; image recognition; rock classification; transfer learning; convolutional neural network;
D O I
10.3389/feart.2022.1079447
中图分类号
P [天文学、地球科学];
学科分类号
07 ;
摘要
Rock image classification is a significant part of geological research. Compared with traditional image classification methods, rock image classification methods based on deep learning models have the great advantage in terms of automatic image features extraction. However, the rock classification accuracies of existing deep learning models are unsatisfied due to the weak feature extraction ability of the network model. In this study, a deep residual neural network (ResNet) model with the transfer learning method is proposed to establish the corresponding rock automatic classification model for seven kinds of rock images. ResNet34 introduces the residual structure to make it have an excellent effect in the field of image classification, which extracts high-quality rock image features and avoids information loss. The transfer learning method abstracts the deep features from the shallow features, and better express the rock texture features for classification in the case of fewer rock images. To improve the generalization of the model, a total of 3,82,536 rock images were generated for training via image slicing and data augmentation. The network parameters trained on the Texture Library dataset which contains 47 types of texture images and reflect the characteristics of rocks are used for transfer learning. This pre-trained weight is loaded when training the ResNet34 model with the rock dataset. Then the model parameters are fine-tuned to transfer the model to the rock classification problem. The experimental results show that the accuracy of the model without transfer learning reached 88.1%, while the model using transfer learning achieved an accuracy of 99.1%. Aiming at geological engineering field investigation, this paper studies the embedded deployment application of the rock classification network. The proposed rock classification network model is transplanted to an embedded platform. By designing a rock classification system, the off-line rock classification is realized, which provides a new solution for the rock classification problem in the geological survey. The deep residual neural network and transfer learning method used in this paper can automatically classify rock features without manually extracting. These methods reduce the influence of subjective factors and make the rock classification process more automatic and intelligent.
引用
收藏
页数:19
相关论文
共 47 条
[1]  
Ali S. B., 2020, 2020 IEEE 17 INDIA C, P1
[2]   Deep learning discrimination of quartz and resin in optical microscopy images of minerals [J].
Alvarez Iglesias, Julio Cesar ;
Magalhaes Santos, Richard Bryan ;
Paciornik, Sidnei .
MINERALS ENGINEERING, 2019, 138 :79-85
[3]  
Bai L., 2019, Geol. Bull. China, V38, P2053
[4]  
Bai L., 2018, China Mining Magazine, V27, P178
[5]   A framework for scheduling dependent programs on GPU architectures [J].
Chang, Yuan-Ming ;
Liao, Wei-Cheng ;
Wang, Shao-Chung ;
Yang, Chun-Chieh ;
Hwang, Yuan-Shin .
JOURNAL OF SYSTEMS ARCHITECTURE, 2020, 106
[6]   Deep learning based classification of rock structure of tunnel face [J].
Chen, Jiayao ;
Yang, Tongjun ;
Zhang, Dongming ;
Huang, Hongwei ;
Tian, Yu .
GEOSCIENCE FRONTIERS, 2021, 12 (01) :395-404
[7]  
Cheng G., 2017, Journal of Xian Shiyou University, V32, P116
[8]  
Dabrowski M., 2017, P C COMPUTER SCI INF, P3, DOI [10.15439/2017F526, DOI 10.15439/2017F526]
[9]   Instance-aware Semantic Segmentation via Multi-task Network Cascades [J].
Dai, Jifeng ;
He, Kaiming ;
Sun, Jian .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :3150-3158
[10]  
Falivene O., 2022, AAPG B