LE-YOLOv5: A Lightweight and Efficient Neural Network for Steel Surface Defect Detection
Due to the influence of manufacturing process and external factors, there will be some undesired defects on the steel surface, which seriously affects the lifetime of steel, and the traditional surface defect detection efficiency and speed are not satisfactory. Therefore, based on the industrial sce...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10806493/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536172054020096 |
|---|---|
| author | Chengshun Zhu Yong Sun Hongji Zhang Shilong Yuan Hui Zhang |
| author_facet | Chengshun Zhu Yong Sun Hongji Zhang Shilong Yuan Hui Zhang |
| author_sort | Chengshun Zhu |
| collection | DOAJ |
| description | Due to the influence of manufacturing process and external factors, there will be some undesired defects on the steel surface, which seriously affects the lifetime of steel, and the traditional surface defect detection efficiency and speed are not satisfactory. Therefore, based on the industrial scenario of low computational force, this study proposed a lightweight and efficient defect detector called LE-YOLOv5. First, we utilize ShuffleNetv2 as the backbone of the model, which greatly reduces the number of parameters. Second, we propose a CBMM module to expand the global receptive field of the model in the initial down sampling stage, which facilitates the model in capturing global information. Third, we also propose a parallelized C2N module for the detection of small defects. Finally, we design a global coordination attention (GCA) to efficiently connect position and spatial information from the feature map. Numerous experimental results demonstrate that LE-YOLOv5 has a highly superior overall performance, reaching 79.1% mean Average Precision (mAP) on the NEU-DET dataset while inferring an image on the CPU in 196.1 ms, which is 5% and 1.5% improved mAP compared to YOLOv5M and YOLOv5L, respectively. At the same time, under the condition that the inference time for an image on a CPU-dependent low computing power force remains the same, the accuracy has improved by 5.3% compared to YOLOv8. It provides excellent potential for defect detection of steel in industrial environment. |
| format | Article |
| id | doaj-art-4fea8149fe7d4ebcbc95de0e3fc226f9 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-4fea8149fe7d4ebcbc95de0e3fc226f92025-01-15T00:01:40ZengIEEEIEEE Access2169-35362024-01-011219524219525510.1109/ACCESS.2024.351916110806493LE-YOLOv5: A Lightweight and Efficient Neural Network for Steel Surface Defect DetectionChengshun Zhu0Yong Sun1Hongji Zhang2Shilong Yuan3Hui Zhang4https://orcid.org/0000-0001-8467-8852School of Mechanical Engineering, Jiangsu University of Science and Technology, Zhenjiang, ChinaSchool of Mechanical Engineering, Jiangsu University of Science and Technology, Zhenjiang, ChinaSchool of Mechanical Engineering, Jiangsu University of Science and Technology, Zhenjiang, ChinaSchool of Mechanical Engineering, Jiangsu University of Science and Technology, Zhenjiang, ChinaSchool of Mechanical Engineering, Jiangsu University of Science and Technology, Zhenjiang, ChinaDue to the influence of manufacturing process and external factors, there will be some undesired defects on the steel surface, which seriously affects the lifetime of steel, and the traditional surface defect detection efficiency and speed are not satisfactory. Therefore, based on the industrial scenario of low computational force, this study proposed a lightweight and efficient defect detector called LE-YOLOv5. First, we utilize ShuffleNetv2 as the backbone of the model, which greatly reduces the number of parameters. Second, we propose a CBMM module to expand the global receptive field of the model in the initial down sampling stage, which facilitates the model in capturing global information. Third, we also propose a parallelized C2N module for the detection of small defects. Finally, we design a global coordination attention (GCA) to efficiently connect position and spatial information from the feature map. Numerous experimental results demonstrate that LE-YOLOv5 has a highly superior overall performance, reaching 79.1% mean Average Precision (mAP) on the NEU-DET dataset while inferring an image on the CPU in 196.1 ms, which is 5% and 1.5% improved mAP compared to YOLOv5M and YOLOv5L, respectively. At the same time, under the condition that the inference time for an image on a CPU-dependent low computing power force remains the same, the accuracy has improved by 5.3% compared to YOLOv8. It provides excellent potential for defect detection of steel in industrial environment.https://ieeexplore.ieee.org/document/10806493/Deep learningYOLOv5surface defect detectionattention mechanism |
| spellingShingle | Chengshun Zhu Yong Sun Hongji Zhang Shilong Yuan Hui Zhang LE-YOLOv5: A Lightweight and Efficient Neural Network for Steel Surface Defect Detection IEEE Access Deep learning YOLOv5 surface defect detection attention mechanism |
| title | LE-YOLOv5: A Lightweight and Efficient Neural Network for Steel Surface Defect Detection |
| title_full | LE-YOLOv5: A Lightweight and Efficient Neural Network for Steel Surface Defect Detection |
| title_fullStr | LE-YOLOv5: A Lightweight and Efficient Neural Network for Steel Surface Defect Detection |
| title_full_unstemmed | LE-YOLOv5: A Lightweight and Efficient Neural Network for Steel Surface Defect Detection |
| title_short | LE-YOLOv5: A Lightweight and Efficient Neural Network for Steel Surface Defect Detection |
| title_sort | le yolov5 a lightweight and efficient neural network for steel surface defect detection |
| topic | Deep learning YOLOv5 surface defect detection attention mechanism |
| url | https://ieeexplore.ieee.org/document/10806493/ |
| work_keys_str_mv | AT chengshunzhu leyolov5alightweightandefficientneuralnetworkforsteelsurfacedefectdetection AT yongsun leyolov5alightweightandefficientneuralnetworkforsteelsurfacedefectdetection AT hongjizhang leyolov5alightweightandefficientneuralnetworkforsteelsurfacedefectdetection AT shilongyuan leyolov5alightweightandefficientneuralnetworkforsteelsurfacedefectdetection AT huizhang leyolov5alightweightandefficientneuralnetworkforsteelsurfacedefectdetection |