Abstract
Intelligent ore mineral identification is one of the basic technologies of intelligent geology and intelligent ore deposit science. Computer vision technology and deep learning theory make the intelligent identification of ore and mineral possible. Based on tensorflow, a deep learning system, this study takes pyrite, chalcopyrite, galena, sphalerite and other sulfide minerals in Jiapigou gold mine and Shihu gold mine in Hebei Province as examples,The experimental results show that the accuracy of the model increases and the loss function decreases with the increase of training times; after 3000 batch processing, the model accuracy and loss function tend to be stable. The recognition success rate of the training model for the microscopic ore and mineral photos in the test set is higher than 90%.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Bianco, S., Buzzelli, M., Mazzini, D., Schettini, R.: Deep learning for logo recognition. Neurocomputing 245, 23–30 (2017)
Do, K.D.: Formation tracking control of unicycle-type mobile robots with limited sensing ranges. Rob. Auton. Syst. 16(3), 527–538 (2008)
Guo, X.J.: Image quasi dense matching and cosegmentation. Ph.D. Dissertation. Tianjin University, Tianjin (2013) ( in Chinese with English summary)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Han, L. (2021). Experimental Study on Intelligent Mineral Recognition Under Microscope Based on Deep Learning. In: Xu, Z., Parizi, R.M., Loyola-González, O., Zhang, X. (eds) Cyber Security Intelligence and Analytics. CSIA 2021. Advances in Intelligent Systems and Computing, vol 1342. Springer, Cham. https://doi.org/10.1007/978-3-030-70042-3_58
Download citation
DOI: https://doi.org/10.1007/978-3-030-70042-3_58
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-70041-6
Online ISBN: 978-3-030-70042-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)