Improved RT-DETR Network for High-Quality Defect Detection on Digital Printing Fabric
Source abstract
Abstract
Digital printing technology has been successfully implemented in actual production within factories. However, issues with various digital printing heads can still lead to defects in printed fabrics, reducing the pass rate of digital printing textiles. To promptly detect these printing defects, we have constructed a dataset of fabric defects caused by digital printing head malfunctions and propose a high-quality digital printing defect detection model tailored to our self-built dataset. Our model is built upon the Real-Time Detection Transformer (RT-DETR) framework, with an added detection head designed for detailed processing in complex backgrounds. We also incorporated an inverted residual mobile block (iRMB) to integrate attention mechanisms into the network’s feature extraction process, and improved the bounding box loss function to enhance the model’s detection accuracy. Experimental results demonstrate that our model achieves state-of-the-art accuracy on the COCO metrics, with a detection accuracy of 0.588 on the AP index, compared to other advanced detection models. This method effectively identifies fabric defects caused by nozzle failures in digital printing equipment, offering a novel solution for fabric defect detection.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Industrial Vision Systems and Defect Detection · Surface Roughness and Optical Measurements · Image and Object Detection Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Xi’an Polytechnic University
Funding
National Natural Science Foundation of China · Research and Development · Innovation Capability Support Program of Shaanxi · Shaanxi Provincial Education Department
References (45)
Show source-provided references
1. 10.1016/S0167-8655(97)00148-710.1016/S0167-8655(97)00148-7 ↗
2. 10.1007/978-3-030-58452-8_1310.1007/978-3-030-58452-8_13 ↗
3. 10.1109/ICCV51070.2023.0061010.1109/ICCV51070.2023.00610 ↗
4. 10.1016/j.aej.2021.03.06010.1016/j.aej.2021.03.060 ↗
5. 10.1109/ICCV48922.2021.0034910.1109/ICCV48922.2021.00349 ↗
6. 10.48550/arXiv.2107.0843010.48550/arXiv.2107.08430 ↗
7. 10.1109/CVPR.2008.458771510.1109/CVPR.2008.4587715 ↗
8. 10.48550/arXiv.2209.0857510.48550/arXiv.2209.08575 ↗
9. 10.1088/1742-6596/1168/2/02203710.1088/1742-6596/1168/2/022037 ↗
10. 10.1109/TIM.2020.304719010.1109/TIM.2020.3047190 ↗
11. 10.1117/12.302160110.1117/12.3021601 ↗
12. 10.1177/004051751984063610.1177/0040517519840636 ↗
13. 10.1007/s11263-019-01204-110.1007/s11263-019-01204-1 ↗
14. 10.1109/TPAMI.2023.333541010.1109/TPAMI.2023.3335410 ↗
15. 10.1109/ICCV51070.2023.0154010.1109/ICCV51070.2023.01540 ↗
16. 10.1109/TPAMI.2018.285882610.1109/TPAMI.2018.2858826 ↗
17. 10.1109/TIP.2019.295974110.1109/TIP.2019.2959741 ↗
18. 10.48550/arXiv.2201.1232910.48550/arXiv.2201.12329 ↗
19. 10.1007/978-3-319-46448-0_210.1007/978-3-319-46448-0_2 ↗
20. 10.1109/CVPR52729.2023.0138610.1109/CVPR52729.2023.01386 ↗
21. 10.48550/arXiv.2212.0778410.48550/arXiv.2212.07784 ↗
22. 10.1109/ICCV48922.2021.0036310.1109/ICCV48922.2021.00363 ↗
23. 10.48550/arXiv.1807.0651410.48550/arXiv.1807.06514 ↗
24. 10.3390/app1023843410.3390/app10238434 ↗
25. 10.1016/j.engappai.2023.10709410.1016/j.engappai.2023.107094 ↗
26. Redmon J. and A. J. A. Farhadi. 2018. “YOLOv3: An Incremental Improvement. abs/1804.02767. https://arXiv:1804.02767.
27. 10.1109/TPAMI.2016.257703110.1109/TPAMI.2016.2577031 ↗
28. 10.1111/cote.1208710.1111/cote.12087 ↗
29. 10.1111/cote.1200410.1111/cote.12004 ↗
30. 10.1080/00405000.2013.87615410.1080/00405000.2013.876154 ↗
31. 10.1177/0040517523119632410.1177/00405175231196324 ↗
32. 10.1109/ICCV.2019.0097210.1109/ICCV.2019.00972 ↗
33. 10.1016/j.engappai.2023.10644210.1016/j.engappai.2023.106442 ↗
34. 10.1109/CVPR52729.2023.0072110.1109/CVPR52729.2023.00721 ↗
35. 10.1007/978-3-030-01234-2_110.1007/978-3-030-01234-2_1 ↗
36. 10.48550/arXiv.2403.0112310.48550/arXiv.2403.01123 ↗
37. 10.1109/TAI.2021.305702710.1109/TAI.2021.3057027 ↗
38. 10.48550/arXiv.2203.0360510.48550/arXiv.2203.03605 ↗
39. 10.1109/CVPR42600.2020.0097810.1109/CVPR42600.2020.00978 ↗
40. 10.1109/CVPR52729.2023.0070810.1109/CVPR52729.2023.00708 ↗
41. 10.1049/iet-cim.2020.006210.1049/iet-cim.2020.0062 ↗
42. 10.1016/j.cie.2023.10968110.1016/j.cie.2023.109681 ↗
43. 10.1007/s10845-024-02387-210.1007/s10845-024-02387-2 ↗
44. 10.1109/CVPR52733.2024.0160510.1109/CVPR52733.2024.01605 ↗
45. 10.48550/arXiv.2010.0415910.48550/arXiv.2010.04159 ↗