Visual inspection of surface defects of extreme size based on an advanced FCOS
Surface defects of industrial products are generally detected through anchor-based object detection methods during manufacturing. However, these methods are prone to missed and false detection for ultra-elongated and ultra-fine defects. An advanced fully convolutional one-stage object detector (FCOS...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2022-12-01
|
| Series: | Applied Artificial Intelligence |
| Online Access: | http://dx.doi.org/10.1080/08839514.2022.2122222 |
| _version_ | 1827774566285443072 |
|---|---|
| author | Hui Shi Rui Lai Gangyan Li Wenyong Yu |
| author_facet | Hui Shi Rui Lai Gangyan Li Wenyong Yu |
| author_sort | Hui Shi |
| collection | DOAJ |
| description | Surface defects of industrial products are generally detected through anchor-based object detection methods during manufacturing. However, these methods are prone to missed and false detection for ultra-elongated and ultra-fine defects. An advanced fully convolutional one-stage object detector (FCOS) is proposed. This method is based on an anchor-free FCOS network model. First, a novel type of center-ness is proposed to reduce the suppression of off-centered positions of defects of extreme size. In addition, to eliminate background interference, a self-adaptive center sampling method is proposed as a replacement for the conventional center sampling method. The regularization method and the loss function are also improved according to the defect characteristics. Experimental results show that this advanced-FCOS-based method outperforms anchor-based methodson the surface defect dataset. The proposed method effectively detects defects of extreme size without affecting the detection of normal defects. The performance of the proposed method meets the requirements of real industrial applications. |
| first_indexed | 2024-03-11T13:40:10Z |
| format | Article |
| id | doaj.art-3e445dd4e856498c9467737f6cf30fd1 |
| institution | Directory Open Access Journal |
| issn | 0883-9514 1087-6545 |
| language | English |
| last_indexed | 2024-03-11T13:40:10Z |
| publishDate | 2022-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Applied Artificial Intelligence |
| spelling | doaj.art-3e445dd4e856498c9467737f6cf30fd12023-11-02T13:36:38ZengTaylor & Francis GroupApplied Artificial Intelligence0883-95141087-65452022-12-0136110.1080/08839514.2022.21222222122222Visual inspection of surface defects of extreme size based on an advanced FCOSHui Shi0Rui Lai1Gangyan Li2Wenyong Yu3Wuhan University of TechnologyHuazhong University of Science and TechnologyWuhan University of TechnologyHuazhong University of Science and TechnologySurface defects of industrial products are generally detected through anchor-based object detection methods during manufacturing. However, these methods are prone to missed and false detection for ultra-elongated and ultra-fine defects. An advanced fully convolutional one-stage object detector (FCOS) is proposed. This method is based on an anchor-free FCOS network model. First, a novel type of center-ness is proposed to reduce the suppression of off-centered positions of defects of extreme size. In addition, to eliminate background interference, a self-adaptive center sampling method is proposed as a replacement for the conventional center sampling method. The regularization method and the loss function are also improved according to the defect characteristics. Experimental results show that this advanced-FCOS-based method outperforms anchor-based methodson the surface defect dataset. The proposed method effectively detects defects of extreme size without affecting the detection of normal defects. The performance of the proposed method meets the requirements of real industrial applications.http://dx.doi.org/10.1080/08839514.2022.2122222 |
| spellingShingle | Hui Shi Rui Lai Gangyan Li Wenyong Yu Visual inspection of surface defects of extreme size based on an advanced FCOS Applied Artificial Intelligence |
| title | Visual inspection of surface defects of extreme size based on an advanced FCOS |
| title_full | Visual inspection of surface defects of extreme size based on an advanced FCOS |
| title_fullStr | Visual inspection of surface defects of extreme size based on an advanced FCOS |
| title_full_unstemmed | Visual inspection of surface defects of extreme size based on an advanced FCOS |
| title_short | Visual inspection of surface defects of extreme size based on an advanced FCOS |
| title_sort | visual inspection of surface defects of extreme size based on an advanced fcos |
| url | http://dx.doi.org/10.1080/08839514.2022.2122222 |
| work_keys_str_mv | AT huishi visualinspectionofsurfacedefectsofextremesizebasedonanadvancedfcos AT ruilai visualinspectionofsurfacedefectsofextremesizebasedonanadvancedfcos AT gangyanli visualinspectionofsurfacedefectsofextremesizebasedonanadvancedfcos AT wenyongyu visualinspectionofsurfacedefectsofextremesizebasedonanadvancedfcos |