Deep Learning Based Mineral Image Classification Combined With Visual Attention Mechanism
Mineral image classification technology based on machine vision is an efficient system for ore sorting. With the development of artificial intelligence and computer technology, the deep learning-based mineral image classification system is gradually applied to ore sorting. However, there is a bottle...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9475982/ |
| _version_ | 1831592315207024640 |
|---|---|
| author | Yang Liu Zelin Zhang Xiang Liu Wang Lei Xuhui Xia |
| author_facet | Yang Liu Zelin Zhang Xiang Liu Wang Lei Xuhui Xia |
| author_sort | Yang Liu |
| collection | DOAJ |
| description | Mineral image classification technology based on machine vision is an efficient system for ore sorting. With the development of artificial intelligence and computer technology, the deep learning-based mineral image classification system is gradually applied to ore sorting. However, there is a bottleneck in improving classification accuracy, and the feature extraction ability of the CNNs model is relatively limited for multi-category mineral image classification tasks. Therefore, four visual attention blocks are designed and embedded in the existing CNNs model, and new mineral image classification models based on the visual attention mechanism and CNNs are proposed. Then, referring to the building strategies of the different depth ResNet, we build various CNNs model embedding with attention blocks for mineral image classification and visualize the models by Grad-CAM to observe the change in classification weight distributions and classification weight values. Finally, by using the confusion matrices, this experiment systematically evaluates the classification performance of the proposed models and analyzes the misjudgment rate. |
| first_indexed | 2024-12-18T01:41:05Z |
| format | Article |
| id | doaj.art-67e1d59a007d4a0584c97848548667ee |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-18T01:41:05Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-67e1d59a007d4a0584c97848548667ee2022-12-21T21:25:18ZengIEEEIEEE Access2169-35362021-01-019980919810910.1109/ACCESS.2021.30953689475982Deep Learning Based Mineral Image Classification Combined With Visual Attention MechanismYang Liu0https://orcid.org/0000-0001-9704-8120Zelin Zhang1https://orcid.org/0000-0003-3644-4458Xiang Liu2Wang Lei3https://orcid.org/0000-0002-2377-5736Xuhui Xia4Hubei Key Laboratory for Efficient Utilization and Agglomeration of Metallurgic Mineral Resources, School of Resource and Environmental Engineering, Wuhan University of Science and Technology, Wuhan, ChinaHubei Key Laboratory for Efficient Utilization and Agglomeration of Metallurgic Mineral Resources, School of Resource and Environmental Engineering, Wuhan University of Science and Technology, Wuhan, ChinaKey Laboratory of Metallurgical Equipment and Control Technology, Wuhan University of Science and Technology, Wuhan, ChinaKey Laboratory of Metallurgical Equipment and Control Technology, Wuhan University of Science and Technology, Wuhan, ChinaKey Laboratory of Metallurgical Equipment and Control Technology, Wuhan University of Science and Technology, Wuhan, ChinaMineral image classification technology based on machine vision is an efficient system for ore sorting. With the development of artificial intelligence and computer technology, the deep learning-based mineral image classification system is gradually applied to ore sorting. However, there is a bottleneck in improving classification accuracy, and the feature extraction ability of the CNNs model is relatively limited for multi-category mineral image classification tasks. Therefore, four visual attention blocks are designed and embedded in the existing CNNs model, and new mineral image classification models based on the visual attention mechanism and CNNs are proposed. Then, referring to the building strategies of the different depth ResNet, we build various CNNs model embedding with attention blocks for mineral image classification and visualize the models by Grad-CAM to observe the change in classification weight distributions and classification weight values. Finally, by using the confusion matrices, this experiment systematically evaluates the classification performance of the proposed models and analyzes the misjudgment rate.https://ieeexplore.ieee.org/document/9475982/Deep learningvisual attention mechanismmineral image classificationGrad-CAM |
| spellingShingle | Yang Liu Zelin Zhang Xiang Liu Wang Lei Xuhui Xia Deep Learning Based Mineral Image Classification Combined With Visual Attention Mechanism IEEE Access Deep learning visual attention mechanism mineral image classification Grad-CAM |
| title | Deep Learning Based Mineral Image Classification Combined With Visual Attention Mechanism |
| title_full | Deep Learning Based Mineral Image Classification Combined With Visual Attention Mechanism |
| title_fullStr | Deep Learning Based Mineral Image Classification Combined With Visual Attention Mechanism |
| title_full_unstemmed | Deep Learning Based Mineral Image Classification Combined With Visual Attention Mechanism |
| title_short | Deep Learning Based Mineral Image Classification Combined With Visual Attention Mechanism |
| title_sort | deep learning based mineral image classification combined with visual attention mechanism |
| topic | Deep learning visual attention mechanism mineral image classification Grad-CAM |
| url | https://ieeexplore.ieee.org/document/9475982/ |
| work_keys_str_mv | AT yangliu deeplearningbasedmineralimageclassificationcombinedwithvisualattentionmechanism AT zelinzhang deeplearningbasedmineralimageclassificationcombinedwithvisualattentionmechanism AT xiangliu deeplearningbasedmineralimageclassificationcombinedwithvisualattentionmechanism AT wanglei deeplearningbasedmineralimageclassificationcombinedwithvisualattentionmechanism AT xuhuixia deeplearningbasedmineralimageclassificationcombinedwithvisualattentionmechanism |