BGF-YOLO: Deep Learning for Mineral Classification Using Hyperspectral Imaging

Zhebin Yu; Xiaojun Qi; Ang Li; Jialin Wei; Wei Liu; Wei Su; Zongfa Li

doi:10.54254/2755-2721/2025.24728

Applied and Computational EngineeringOpen access

BGF-YOLO: Deep Learning for Mineral Classification Using Hyperspectral Imaging

Research Article

Open Access

BGF-YOLO: Deep Learning for Mineral Classification Using Hyperspectral Imaging

Zhebin Yu ^1* Xiaojun Qi ², Ang Li ³, Jialin Wei ⁴, Wei Liu ⁵, Wei Su ⁶, Zongfa Li ⁷

¹ China National Gold Group Geology Co., Ltd., Liuyin Park South Street, Dongcheng District, Beijing, China

² China National Gold Group Geology Co., Ltd., Liuyin Park South Street, Dongcheng District, Beijing, China

³ China National Gold Group Geology Co., Ltd., Liuyin Park South Street, Dongcheng District, Beijing, China

⁴ China National Gold Group Geology Co., Ltd., Liuyin Park South Street, Dongcheng District, Beijing, China

⁵ China National Gold Group Geology Co., Ltd., Liuyin Park South Street, Dongcheng District, Beijing, China

⁶ China National Gold Group Geology Co., Ltd., Liuyin Park South Street, Dongcheng District, Beijing, China

⁷ China National Gold Group Geology Co., Ltd., Liuyin Park South Street, Dongcheng District, Beijing, China

^*Corresponding author: slm0718m@163.com

Published on 4 July 2025

ACE Vol.173

ISSN (Print): 2755-273X

ISSN (Online): 2755-2721

ISBN (Print): 978-1-80590-231-7

ISBN (Online): 978-1-80590-232-4

Download Cover

Abstract

The rising resource demands in emerging economies have intensified resource nationalism in mineral-rich countries, necessitating more efficient mineral processing technologies for declining ore grades. This study presents BGF-YOLO, a novel deep learning model enhanced from YOLOv8, designed to optimize mineral beneficiation by accurately identifying mineral species and grain sizes using hyperspectral imaging. The system utilizes hyperspectral data spanning 66 spectral bands (400–1000 nm) and processes large datasets through advanced feature fusion and attention mechanisms. BGF-YOLO integrates a Generalized Feature Pyramid Network (GFPN), Dual-Level Routing Attention (DLRA), and an additional detection head to improve multi-scale feature detection and reduce redundant information. Evaluated on a dataset of 4,975 samples across five mineral classes, the model achieved an overall accuracy of 91.9%, with Galena and Hematite large particles attaining 94.9% and 100.0% accuracy, respectively. Comparative analysis showed that BGF-YOLO outperforms the baseline YOLOv8 by approximately 5% in accuracy. These results demonstrate the potential of combining hyperspectral imaging with advanced deep learning architectures to enhance the precision and efficiency of mineral classification and grain size determination in beneficiation processes.

Keywords:

Hyperspectral Imaging, Deep Learning, BGF-YOLO, Mineral Classification, Grain Size Identification, Feature Pyramid Network, Attention Mechanism

View PDF

References

[1]. Sun Y, Ortiz J. An ai-based system utilizing iot-enabled ambient sensors and llms for complex activity tracking [J]. arXiv preprint arXiv: 2407.02606, 2024.

[2]. Kang M, Ting C M, Ting F F, et al. Bgf-yolo: Enhanced yolov8 with multiscale attentional feature fusion for brain tumor detection [C]//International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer Nature Switzerland, 2024: 35-45.

[3]. Dumont J A, Lemos Gazire M, Robben C. Sensor-based ore sorting methodology investigation applied to gold ores [J]. Procemin Geomet, 2017.

[4]. Liu C, Li M, Zhang Y, et al. An enhanced rock mineral recognition method integrating a deep learning model and clustering algorithm [J]. Minerals, 2019, 9(9): 516.

[5]. Zhang W, Sun W, Hu Y, et al. Selective flotation of pyrite from galena using chitosan with different molecular weights [J]. Minerals, 2019, 9(9): 549.

[6]. Y. Liu, Z. Zhang, X. Liu, L. Wang, and X. Xia, ‘‘Ore image classification based on small deep learning model: Evaluation and optimization of model depth, model structure and data size, ’’ Minerals Eng., 2021, Art. no. 107020, doi: 10.1016/j.mineng.2021.107020.

[7]. Wu B, Cai Z, Wu W, et al. AoI-aware resource management for smart health via deep reinforcement learning [J]. IEEE Access, 2023.

References

[1]. Sun Y, Ortiz J. An ai-based system utilizing iot-enabled ambient sensors and llms for complex activity tracking [J]. arXiv preprint arXiv: 2407.02606, 2024.

[3]. Dumont J A, Lemos Gazire M, Robben C. Sensor-based ore sorting methodology investigation applied to gold ores [J]. Procemin Geomet, 2017.

[4]. Liu C, Li M, Zhang Y, et al. An enhanced rock mineral recognition method integrating a deep learning model and clustering algorithm [J]. Minerals, 2019, 9(9): 516.

[5]. Zhang W, Sun W, Hu Y, et al. Selective flotation of pyrite from galena using chitosan with different molecular weights [J]. Minerals, 2019, 9(9): 549.

[7]. Wu B, Cai Z, Wu W, et al. AoI-aware resource management for smart health via deep reinforcement learning [J]. IEEE Access, 2023.

Cite this article

Yu,Z.;Qi,X.;Li,A.;Wei,J.;Liu,W.;Su,W.;Li,Z. (2025). BGF-YOLO: Deep Learning for Mineral Classification Using Hyperspectral Imaging. Applied and Computational Engineering,173,1-7.

Data availability

The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.

About volume

Volume title: Proceedings of the 7th International Conference on Computing and Data Science

ISBN: 978-1-80590-231-7(Print) / 978-1-80590-232-4(Online)

Editor: Marwan Omar

Conference website: https://2025.confcds.org/

Conference date: 25 September 2025

Series: Applied and Computational Engineering

Volume number: Vol.173

ISSN: 2755-2721(Print) / 2755-273X(Online)

© 2024 by the author(s). Licensee EWA Publishing, Oxford, UK. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license. Authors who publish this series agree to the following terms:

1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this series.

2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this series.

3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See Open access policy for details).