CFM-YOLOv5:CFPNet moudle and muti-target prediction head incorporating YOLOv5 for metal surface defect detection.
Aiming at the problem of low efficiency of manual detection in the field of metal surface defect detection, a deep learning defect detection method based on improved YOLOv5 algorithm is proposed. Firstly, in the feature enhancement part, we replace the multi-head self-attention module of the standar...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2023-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0289179&type=printable |
| _version_ | 1797377765407719424 |
|---|---|
| author | Yuntao Xu Peigang Jiao Jiaqi Liu |
| author_facet | Yuntao Xu Peigang Jiao Jiaqi Liu |
| author_sort | Yuntao Xu |
| collection | DOAJ |
| description | Aiming at the problem of low efficiency of manual detection in the field of metal surface defect detection, a deep learning defect detection method based on improved YOLOv5 algorithm is proposed. Firstly, in the feature enhancement part, we replace the multi-head self-attention module of the standard transformer encoder with the EVC module to improve the feature extraction ability. Second, in the prediction part, adding a small target detection head can reduce the negative impact of drastic object scale changes and improve the accuracy and stability of detection. Finally, the performance of the algorithm is verified by ablation experiments and analogy experiments. The experimental results show that the improved algorithm has greatly improved mAP and FPS on the data set, and can quickly and accurately identify the types of metal surface defects, which has reference significance for practical industrial applications. |
| first_indexed | 2024-03-08T19:57:12Z |
| format | Article |
| id | doaj.art-7bb2e10bb6ba43e08020b075f3359798 |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-03-08T19:57:12Z |
| publishDate | 2023-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-7bb2e10bb6ba43e08020b075f33597982023-12-24T05:33:19ZengPublic Library of Science (PLoS)PLoS ONE1932-62032023-01-011812e028917910.1371/journal.pone.0289179CFM-YOLOv5:CFPNet moudle and muti-target prediction head incorporating YOLOv5 for metal surface defect detection.Yuntao XuPeigang JiaoJiaqi LiuAiming at the problem of low efficiency of manual detection in the field of metal surface defect detection, a deep learning defect detection method based on improved YOLOv5 algorithm is proposed. Firstly, in the feature enhancement part, we replace the multi-head self-attention module of the standard transformer encoder with the EVC module to improve the feature extraction ability. Second, in the prediction part, adding a small target detection head can reduce the negative impact of drastic object scale changes and improve the accuracy and stability of detection. Finally, the performance of the algorithm is verified by ablation experiments and analogy experiments. The experimental results show that the improved algorithm has greatly improved mAP and FPS on the data set, and can quickly and accurately identify the types of metal surface defects, which has reference significance for practical industrial applications.https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0289179&type=printable |
| spellingShingle | Yuntao Xu Peigang Jiao Jiaqi Liu CFM-YOLOv5:CFPNet moudle and muti-target prediction head incorporating YOLOv5 for metal surface defect detection. PLoS ONE |
| title | CFM-YOLOv5:CFPNet moudle and muti-target prediction head incorporating YOLOv5 for metal surface defect detection. |
| title_full | CFM-YOLOv5:CFPNet moudle and muti-target prediction head incorporating YOLOv5 for metal surface defect detection. |
| title_fullStr | CFM-YOLOv5:CFPNet moudle and muti-target prediction head incorporating YOLOv5 for metal surface defect detection. |
| title_full_unstemmed | CFM-YOLOv5:CFPNet moudle and muti-target prediction head incorporating YOLOv5 for metal surface defect detection. |
| title_short | CFM-YOLOv5:CFPNet moudle and muti-target prediction head incorporating YOLOv5 for metal surface defect detection. |
| title_sort | cfm yolov5 cfpnet moudle and muti target prediction head incorporating yolov5 for metal surface defect detection |
| url | https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0289179&type=printable |
| work_keys_str_mv | AT yuntaoxu cfmyolov5cfpnetmoudleandmutitargetpredictionheadincorporatingyolov5formetalsurfacedefectdetection AT peigangjiao cfmyolov5cfpnetmoudleandmutitargetpredictionheadincorporatingyolov5formetalsurfacedefectdetection AT jiaqiliu cfmyolov5cfpnetmoudleandmutitargetpredictionheadincorporatingyolov5formetalsurfacedefectdetection |