Mineral identification in thin sections using a lightweight and attention mechanism

Mineral identification is foundational to geological survey research, mineral resource exploration, and mining engineering. Considering the diversity of mineral types and the challenge of achieving high recognition accuracy for similar features, this study introduces a mineral detection method based...

Full description

Saved in:
Bibliographic Details
Main Authors: Xin Zhang, Wei Dang, Jun Liu, Zijuan Yin, Guichao Du, Yawen He, Yankai Xue
Format: Article
Language:English
Published: KeAi Communications Co., Ltd. 2025-04-01
Series:Natural Gas Industry B
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2352854025000166
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850173660032139264
author Xin Zhang
Wei Dang
Jun Liu
Zijuan Yin
Guichao Du
Yawen He
Yankai Xue
author_facet Xin Zhang
Wei Dang
Jun Liu
Zijuan Yin
Guichao Du
Yawen He
Yankai Xue
author_sort Xin Zhang
collection DOAJ
description Mineral identification is foundational to geological survey research, mineral resource exploration, and mining engineering. Considering the diversity of mineral types and the challenge of achieving high recognition accuracy for similar features, this study introduces a mineral detection method based on YOLOv8-SBI. This work enhances feature extraction by integrating spatial pyramid pooling-fast (SPPF) with the simplified self-attention module (SimAM), significantly improving the precision of mineral feature detection. In the feature fusion network, a weighted bidirectional feature pyramid network is employed for advanced cross-channel feature integration, effectively reducing feature redundancy. Additionally, Inner-Intersection Over Union (InnerIOU) is used as the loss function to improve the average quality localization performance of anchor boxes. Experimental results show that the YOLOv8-SBI model achieves an accuracy of 67.9 %, a recall of 74.3 %, a mAP@0.5 of 75.8 %, and a mAP@0.5:0.95 of 56.7 %, with a real-time detection speed of 244.2 frames per second. Compared to YOLOv8, YOLOv8-SBI demonstrates a significant improvement with 15.4 % increase in accuracy, 28.5 % increase in recall, and increases of 28.1 % and 20.9 % in mAP@0.5 and mAP@0.5:0.95, respectively. Furthermore, relative to other models, such as YOLOv3, YOLOv5, YOLOv6, YOLOv8, YOLOv9, and YOLOv10, YOLOv8-SBI has a smaller parameter size of only 3.01 × 106. This highlights the optimal balance between detection accuracy and speed, thereby offering robust technical support for intelligent mineral classification.
format Article
id doaj-art-bf9f8da9c50a43a0b2ceb5f7fdd9f9d0
institution OA Journals
issn 2352-8540
language English
publishDate 2025-04-01
publisher KeAi Communications Co., Ltd.
record_format Article
series Natural Gas Industry B
spelling doaj-art-bf9f8da9c50a43a0b2ceb5f7fdd9f9d02025-08-20T02:19:48ZengKeAi Communications Co., Ltd.Natural Gas Industry B2352-85402025-04-0112213514610.1016/j.ngib.2025.03.001Mineral identification in thin sections using a lightweight and attention mechanismXin Zhang0Wei Dang1Jun Liu2Zijuan Yin3Guichao Du4Yawen He5Yankai Xue6School of Earth Sciences and Engineering, Xi'an Shiyou University, Xi'an 710065, China; Shaanxi Key Laboratory of Petroleum Accumulation Geology, Xi'an Shiyou University, Xi'an 710065, ChinaSchool of Earth Sciences and Engineering, Xi'an Shiyou University, Xi'an 710065, China; Shaanxi Key Laboratory of Petroleum Accumulation Geology, Xi'an Shiyou University, Xi'an 710065, China; Corresponding author. School of Earth Sciences and Engineering, Xi'an Shiyou University, Xi'an 710065, China.Sulige Gasfield Development Company, PCOC, Xi'an, Shaanxi 710018, ChinaCollege of Materials Science and Engineering, Shanghai University of Engineering Science, Shanghai, 201620, ChinaSchool of Earth Sciences and Engineering, Xi'an Shiyou University, Xi'an 710065, China; Shaanxi Key Laboratory of Petroleum Accumulation Geology, Xi'an Shiyou University, Xi'an 710065, ChinaDepartment of Geology, Northwest University, Xi'an 710069, China; State Key Laboratory of Continental Dynamics, Northwest University, Xi'an 710069, ChinaSchool of Earth Sciences and Engineering, Xi'an Shiyou University, Xi'an 710065, China; Shaanxi Key Laboratory of Petroleum Accumulation Geology, Xi'an Shiyou University, Xi'an 710065, ChinaMineral identification is foundational to geological survey research, mineral resource exploration, and mining engineering. Considering the diversity of mineral types and the challenge of achieving high recognition accuracy for similar features, this study introduces a mineral detection method based on YOLOv8-SBI. This work enhances feature extraction by integrating spatial pyramid pooling-fast (SPPF) with the simplified self-attention module (SimAM), significantly improving the precision of mineral feature detection. In the feature fusion network, a weighted bidirectional feature pyramid network is employed for advanced cross-channel feature integration, effectively reducing feature redundancy. Additionally, Inner-Intersection Over Union (InnerIOU) is used as the loss function to improve the average quality localization performance of anchor boxes. Experimental results show that the YOLOv8-SBI model achieves an accuracy of 67.9 %, a recall of 74.3 %, a mAP@0.5 of 75.8 %, and a mAP@0.5:0.95 of 56.7 %, with a real-time detection speed of 244.2 frames per second. Compared to YOLOv8, YOLOv8-SBI demonstrates a significant improvement with 15.4 % increase in accuracy, 28.5 % increase in recall, and increases of 28.1 % and 20.9 % in mAP@0.5 and mAP@0.5:0.95, respectively. Furthermore, relative to other models, such as YOLOv3, YOLOv5, YOLOv6, YOLOv8, YOLOv9, and YOLOv10, YOLOv8-SBI has a smaller parameter size of only 3.01 × 106. This highlights the optimal balance between detection accuracy and speed, thereby offering robust technical support for intelligent mineral classification.http://www.sciencedirect.com/science/article/pii/S2352854025000166Deep learningNeural networksLightweight modelsAttention mechanismsMineral identification
spellingShingle Xin Zhang
Wei Dang
Jun Liu
Zijuan Yin
Guichao Du
Yawen He
Yankai Xue
Mineral identification in thin sections using a lightweight and attention mechanism
Natural Gas Industry B
Deep learning
Neural networks
Lightweight models
Attention mechanisms
Mineral identification
title Mineral identification in thin sections using a lightweight and attention mechanism
title_full Mineral identification in thin sections using a lightweight and attention mechanism
title_fullStr Mineral identification in thin sections using a lightweight and attention mechanism
title_full_unstemmed Mineral identification in thin sections using a lightweight and attention mechanism
title_short Mineral identification in thin sections using a lightweight and attention mechanism
title_sort mineral identification in thin sections using a lightweight and attention mechanism
topic Deep learning
Neural networks
Lightweight models
Attention mechanisms
Mineral identification
url http://www.sciencedirect.com/science/article/pii/S2352854025000166
work_keys_str_mv AT xinzhang mineralidentificationinthinsectionsusingalightweightandattentionmechanism
AT weidang mineralidentificationinthinsectionsusingalightweightandattentionmechanism
AT junliu mineralidentificationinthinsectionsusingalightweightandattentionmechanism
AT zijuanyin mineralidentificationinthinsectionsusingalightweightandattentionmechanism
AT guichaodu mineralidentificationinthinsectionsusingalightweightandattentionmechanism
AT yawenhe mineralidentificationinthinsectionsusingalightweightandattentionmechanism
AT yankaixue mineralidentificationinthinsectionsusingalightweightandattentionmechanism