Home Journals Articles Updates About
CN
image
收藏切换
Research on Intelligent Incremental Method for Image Samples in Intelligent Recognition of Rock and Mineral
收藏切换
Feixue SONG1, 2, Lin SUN1, 2, 3, Yanbo ZHANG2, 3, Xulong YAO2, 3, Zhigang TAO4, 5, Youbang LAI6, Chong CAO7
Mining Research and Development | 2025, 45(12) : 271 - 282
Less
收藏切换
Mining Research and Development | 2025, 45(12): 271-282
Research on Intelligent Incremental Method for Image Samples in Intelligent Recognition of Rock and Mineral
Full
Feixue SONG1, 2, Lin SUN1, 2, 3, Yanbo ZHANG2, 3, Xulong YAO2, 3, Zhigang TAO4, 5, Youbang LAI6, Chong CAO7
Affiliations
  • 1.College of Artificial Intelligence, North China University of Science and Technology, Tangshan, Hebei 063210, China
  • 2.Green Intelligent Mining Technology Innovation Center of Hebei Province, Tangshan, Hebei 063210, China
  • 3.College of Mining Engineering, North China University of Science and Technology, Tangshan, Hebei 063210, China
  • 4.State Key Laboratory for Geomechanics and Deep Underground Engineering, Beijing 100083, China
  • 5.School of Mechanics and Civil Engineering, China University of Mining and Technology-Beijing, Beijing 100083, China
  • 6.Sijaying Yanshan Iron Mine Co., Ltd., Hebei Iron and Steel Group, Tangshan, Hebei 063210, China
  • 7.School of Emergency Management and Safety Engineering, North China University of Science and Technology, Tangshan, Hebei 063210, China
Published: 2025-12-25
Outline
收藏切换

The scarcity of samples seriously restricts the promotion and application of deep learning technology in the field of intelligent recognition of rock and mineral. Therefore, an intelligent incremental method for image samples of rock and mineral based on an improved deep convolutional generative adversarial network (DCGAN) was proposed. By introducing self-attention mechanism to enhance the details and authenticity of generated images, using loss function with gradient penalty mechanism (WGAN-GP) to improve training stability, expanding network structure to enhance model performance, and combining various data augmentation techniques to expand sample diversity and quality, the problem of sample scarcity has been effectively alleviated. The experimental results show that the proposed method outperforms comparative models in evaluation indicators such as peak signal-to-noise ratio, Fréchet initial distance, and structural similarity index. The loss function curves show that the model training process is stable and has a good convergence performance. The clustering analysis results indicate that images generated by the model are superior to the original images in terms of complexity and diversity. The survey results show that the model can generate high-quality and highly realistic images of rock and mineral. The research effectively alleviated the problem of scarcity of rock and mineral image samples, laying the foundation for the intelligent development and practical application of rock and mineral image generation.

Intelligent identification of minerals  /  Deep learning  /  Generative adversarial network  /  Image generation  /  Data enhancement
宋飞雪, 孙林, 张艳博, 姚旭龙, 陶志刚, 来有邦, 曹冲. 岩石矿物智能识别中图像样本的智能增量方法研究. 矿业研究与开发, 2025 , 45 (12) : 271 -282 .
Feixue SONG, Lin SUN, Yanbo ZHANG, Xulong YAO, Zhigang TAO, Youbang LAI, Chong CAO. Research on Intelligent Incremental Method for Image Samples in Intelligent Recognition of Rock and Mineral[J]. Mining Research and Development, 2025 , 45 (12) : 271 -282 .
Appendix
Less
Year 2025 volume 45 Issue 12
83
36
Cite this Article
BibTeX
Article Info
  • Receive Date：2024-11-09
  • Online Date：2026-10-28
  • Published：2025-12-25
Article Data
Affiliations
History
  • Received：2024-11-09
Funding
Affiliations
    1.College of Artificial Intelligence, North China University of Science and Technology, Tangshan, Hebei 063210, China
    2.Green Intelligent Mining Technology Innovation Center of Hebei Province, Tangshan, Hebei 063210, China
    3.College of Mining Engineering, North China University of Science and Technology, Tangshan, Hebei 063210, China
    4.State Key Laboratory for Geomechanics and Deep Underground Engineering, Beijing 100083, China
    5.School of Mechanics and Civil Engineering, China University of Mining and Technology-Beijing, Beijing 100083, China
    6.Sijaying Yanshan Iron Mine Co., Ltd., Hebei Iron and Steel Group, Tangshan, Hebei 063210, China
    7.School of Emergency Management and Safety Engineering, North China University of Science and Technology, Tangshan, Hebei 063210, China
References
Share
https://castjournals.cast.org.cn/joweb/kyyjykf/EN/
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family		 属数
Number of
genus		 种数
Number of
species		 占总种数比例
Percentage of
total species (%)		 属
Genus		 种数
Number of
species		 占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT
Links
Articles
Latest Articles
Most Read
Collections
Updates
Events
News
Multimedia
About
About Us
Contact
No. 86 Xueyuan South Road, Haidian District, Beijing
100081
010-62662699(Operation and Technical Support)
qkjq@cast.org.cn

Copyright © 2025 China Association for Science and Technology. All rights reserved. For all open access content, the relevant licensing terms apply.
Sponsored by the Office of the Leading Group for Cybersecurity and Informatization of CAST, and supported by Science and Technology Review Publishing House