DeFRCN-MAM: DeFRCN and multi-scale attention mechanism-based industrial defect detection method
With the technology development, industrial defect detection based on deep learning has attracted extensive attention in the academic community. Different from general visual objects, industrial defects have the characteristics of small sample, weak visibility and irregular shape, which hinder the a...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2024-12-01
|
| Series: | Applied Artificial Intelligence |
| Online Access: | https://www.tandfonline.com/doi/10.1080/08839514.2024.2349981 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850064126022254592 |
|---|---|
| author | Tong Zheng Liangbing Sa Chongchong Yu Aibin Song |
| author_facet | Tong Zheng Liangbing Sa Chongchong Yu Aibin Song |
| author_sort | Tong Zheng |
| collection | DOAJ |
| description | With the technology development, industrial defect detection based on deep learning has attracted extensive attention in the academic community. Different from general visual objects, industrial defects have the characteristics of small sample, weak visibility and irregular shape, which hinder the application of related studies. According to these problems, a few-shot object detection (FSOD) method based on Decoupled Faster R-CNN (DeFRCN) is proposed in this paper. Firstly, it includes fine-tuning processing, because of the small sample characteristics. To adapt to the invisible characteristics of defects, we introduce the Feature Pyramid Network (FPN) and Residual Attention Module (RAM) into DeFRCN, which can enhance the capture ability of multi-scale features and feature association information. Furthermore, the feature representation ability is strengthened by parallel connecting of two channels, consisting of R-CNN head, box classifier and box regression models. Finally, it is completed that the pre-training, fine-tuning and testing of the proposed network, with DAGM 2007 and NEU-DET public industrial defect datasets as the base class and flange shaft defect data collected in the laboratory as the new class. To verify the effectiveness of the proposed one, we compare them with other classical FSOD methods. The superiority of the proposed method is obvious. |
| format | Article |
| id | doaj-art-aeaa9be5209e425ab40fda9bd0151737 |
| institution | DOAJ |
| issn | 0883-9514 1087-6545 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Applied Artificial Intelligence |
| spelling | doaj-art-aeaa9be5209e425ab40fda9bd01517372025-08-20T02:49:23ZengTaylor & Francis GroupApplied Artificial Intelligence0883-95141087-65452024-12-0138110.1080/08839514.2024.2349981DeFRCN-MAM: DeFRCN and multi-scale attention mechanism-based industrial defect detection methodTong Zheng0Liangbing Sa1Chongchong Yu2Aibin Song3School of Artificial Intelligence, Beijing Technology and Business University, Beijing, ChinaSchool of Artificial Intelligence, Beijing Technology and Business University, Beijing, ChinaSchool of Artificial Intelligence, Beijing Technology and Business University, Beijing, ChinaWeapons and Control Department, PLA Armored Force Academy, Beijing, ChinaWith the technology development, industrial defect detection based on deep learning has attracted extensive attention in the academic community. Different from general visual objects, industrial defects have the characteristics of small sample, weak visibility and irregular shape, which hinder the application of related studies. According to these problems, a few-shot object detection (FSOD) method based on Decoupled Faster R-CNN (DeFRCN) is proposed in this paper. Firstly, it includes fine-tuning processing, because of the small sample characteristics. To adapt to the invisible characteristics of defects, we introduce the Feature Pyramid Network (FPN) and Residual Attention Module (RAM) into DeFRCN, which can enhance the capture ability of multi-scale features and feature association information. Furthermore, the feature representation ability is strengthened by parallel connecting of two channels, consisting of R-CNN head, box classifier and box regression models. Finally, it is completed that the pre-training, fine-tuning and testing of the proposed network, with DAGM 2007 and NEU-DET public industrial defect datasets as the base class and flange shaft defect data collected in the laboratory as the new class. To verify the effectiveness of the proposed one, we compare them with other classical FSOD methods. The superiority of the proposed method is obvious.https://www.tandfonline.com/doi/10.1080/08839514.2024.2349981 |
| spellingShingle | Tong Zheng Liangbing Sa Chongchong Yu Aibin Song DeFRCN-MAM: DeFRCN and multi-scale attention mechanism-based industrial defect detection method Applied Artificial Intelligence |
| title | DeFRCN-MAM: DeFRCN and multi-scale attention mechanism-based industrial defect detection method |
| title_full | DeFRCN-MAM: DeFRCN and multi-scale attention mechanism-based industrial defect detection method |
| title_fullStr | DeFRCN-MAM: DeFRCN and multi-scale attention mechanism-based industrial defect detection method |
| title_full_unstemmed | DeFRCN-MAM: DeFRCN and multi-scale attention mechanism-based industrial defect detection method |
| title_short | DeFRCN-MAM: DeFRCN and multi-scale attention mechanism-based industrial defect detection method |
| title_sort | defrcn mam defrcn and multi scale attention mechanism based industrial defect detection method |
| url | https://www.tandfonline.com/doi/10.1080/08839514.2024.2349981 |
| work_keys_str_mv | AT tongzheng defrcnmamdefrcnandmultiscaleattentionmechanismbasedindustrialdefectdetectionmethod AT liangbingsa defrcnmamdefrcnandmultiscaleattentionmechanismbasedindustrialdefectdetectionmethod AT chongchongyu defrcnmamdefrcnandmultiscaleattentionmechanismbasedindustrialdefectdetectionmethod AT aibinsong defrcnmamdefrcnandmultiscaleattentionmechanismbasedindustrialdefectdetectionmethod |