MeDERT: A Metal Surface Defect Detection Model
Defects in various products are unavoidable because of measurement errors and equipment accuracy limitations in the production process. Recent advances in metal surface defect detection have focused on optimizing traditional methods, developing new detection techniques, and exploring deep learning-b...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10082895/ |
| _version_ | 1827967697067966464 |
|---|---|
| author | Chenglong Wang Heng Xie |
| author_facet | Chenglong Wang Heng Xie |
| author_sort | Chenglong Wang |
| collection | DOAJ |
| description | Defects in various products are unavoidable because of measurement errors and equipment accuracy limitations in the production process. Recent advances in metal surface defect detection have focused on optimizing traditional methods, developing new detection techniques, and exploring deep learning-based algorithms, providing technological support to improve metal manufacturing quality and production efficiency. To ensure the highest yield rate and meet production requirements, all products must undergo defect inspections before leaving the factory. However, Traditional methods for detecting metal surface defects require a lot of manual involvement, are difficult to accurately detect small defects, are susceptible to environmental interference, and lack stability and reliability. To address this issue, we propose the MeDERT model for metal surface defect detection. Our approach involves a new Span-sensitive Texture Fusion (STF) module structure that focuses on multi-headed attention modules to recover lost details and boost inspection speed and on top of that use the Jump-sensitive detail recovery feature fusion module to ensure the validity of the extracted textures. Additionally, we introduce singular value decomposition and pretzel noise to model the noise and enhance model robustness through data augmentation. Our MeDERT model achieved state-of-the-art (SOTA) results on a specified dataset, demonstrating its effectiveness in enhancing inspection efficiency and accuracy. |
| first_indexed | 2024-04-09T18:10:11Z |
| format | Article |
| id | doaj.art-7f6665b7b8334a53a07c9e244ad73d93 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-09T18:10:11Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-7f6665b7b8334a53a07c9e244ad73d932023-04-13T23:00:57ZengIEEEIEEE Access2169-35362023-01-0111354693547810.1109/ACCESS.2023.326226410082895MeDERT: A Metal Surface Defect Detection ModelChenglong Wang0https://orcid.org/0000-0002-1196-4169Heng Xie1School of Electronic Information and Electrical Engineering, Huizhou University, Huizhou, ChinaSchool of Electronic Information and Electrical Engineering, Huizhou University, Huizhou, ChinaDefects in various products are unavoidable because of measurement errors and equipment accuracy limitations in the production process. Recent advances in metal surface defect detection have focused on optimizing traditional methods, developing new detection techniques, and exploring deep learning-based algorithms, providing technological support to improve metal manufacturing quality and production efficiency. To ensure the highest yield rate and meet production requirements, all products must undergo defect inspections before leaving the factory. However, Traditional methods for detecting metal surface defects require a lot of manual involvement, are difficult to accurately detect small defects, are susceptible to environmental interference, and lack stability and reliability. To address this issue, we propose the MeDERT model for metal surface defect detection. Our approach involves a new Span-sensitive Texture Fusion (STF) module structure that focuses on multi-headed attention modules to recover lost details and boost inspection speed and on top of that use the Jump-sensitive detail recovery feature fusion module to ensure the validity of the extracted textures. Additionally, we introduce singular value decomposition and pretzel noise to model the noise and enhance model robustness through data augmentation. Our MeDERT model achieved state-of-the-art (SOTA) results on a specified dataset, demonstrating its effectiveness in enhancing inspection efficiency and accuracy.https://ieeexplore.ieee.org/document/10082895/Metal profilesdefect detectiondeep learningsalt-and-pepper noisesingular value decompositionDERT |
| spellingShingle | Chenglong Wang Heng Xie MeDERT: A Metal Surface Defect Detection Model IEEE Access Metal profiles defect detection deep learning salt-and-pepper noise singular value decomposition DERT |
| title | MeDERT: A Metal Surface Defect Detection Model |
| title_full | MeDERT: A Metal Surface Defect Detection Model |
| title_fullStr | MeDERT: A Metal Surface Defect Detection Model |
| title_full_unstemmed | MeDERT: A Metal Surface Defect Detection Model |
| title_short | MeDERT: A Metal Surface Defect Detection Model |
| title_sort | medert a metal surface defect detection model |
| topic | Metal profiles defect detection deep learning salt-and-pepper noise singular value decomposition DERT |
| url | https://ieeexplore.ieee.org/document/10082895/ |
| work_keys_str_mv | AT chenglongwang medertametalsurfacedefectdetectionmodel AT hengxie medertametalsurfacedefectdetectionmodel |