journal article·2022-01Open access

CARL-YOLOF: A well-efficient model for digital printing fabric defect detection

Jingwei Wu, Pengfei Li, Huanhuan Zhang, Zebin Su

Abstract

Deep-learning models have been successfully applied to fabric defect detection fields. However, due to the lack of available dataset for the digital printing fabric defect detection field, the study is still under-explored. Besides, there are two tough challenges that currently existing deep-learning models cannot resolve well. On the one hand, the actual production requires the models to improve its detection accuracy as much as possible while ensuring real-time detection. On the other hand, the objectives of classification and localization are correlated, so the link between classification and localization should be established for an excellent object detection model. To solve these problems, such Classification-Aware Regression Loss (CARL) is embedded into the YOLOF to correlate the classification and localization tasks so that the model is named CARL-YOLOF. The performance of the proposed model has been trained and evaluated by the self-built digital printing fabric defect detection dataset (DPFD-DET). Experimental results demonstrate that CARL-YOLOF achieves 0.54 AP on COCO metrics, which achieves a gain of 0.04 compared with YOLOF. Besides, CARL-YOLOF maintains the speed advantage of YOLOF, which reaches 42 FPS. Therefore, the proposed model is suitable for the real-time digital printing fabric defect detection.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Industrial Vision Systems and Defect Detection · Advanced Neural Network Applications · Visual Attention and Saliency Detection

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Xi’an Polytechnic University School of Electronics and Information, Xi’an, China

Xi’an University of Technology School of Mechanical and Instrumental Engineering, Xi’an, China

References (26)

Show source-provided references
1. 10.1177/004051751037363710.1177/0040517510373637 ↗
2. 10.1007/s12221-010-0223-510.1007/s12221-010-0223-5 ↗
3. 10.1016/j.aej.2021.03.06010.1016/j.aej.2021.03.060 ↗
4. Ma P. · Asian J Chem · 2012 · 24 · 3833
5. 10.1108/0955622041052053110.1108/09556220410520531 ↗
6. 10.3390/app1023843410.3390/app10238434 ↗
7. 10.1109/JIOT.2020.298305010.1109/JIOT.2020.2983050 ↗
8. 10.1177/004051752095522910.1177/0040517520955229 ↗
9. 10.1109/TPAMI.2016.257703110.1109/TPAMI.2016.2577031 ↗
10. 10.1109/CVPR42600.2020.0097810.1109/CVPR42600.2020.00978 ↗
11. 10.1109/CVPR46437.2021.0128410.1109/CVPR46437.2021.01284 ↗
12. 10.1007/978-3-319-46448-0_210.1007/978-3-319-46448-0_2 ↗
13. 10.1109/CVPR42600.2020.0110010.1109/CVPR42600.2020.01100 ↗
14. 10.1109/CVPR42600.2020.0116010.1109/CVPR42600.2020.01160 ↗
15. 10.3390/rs1105053110.3390/rs11050531 ↗
16. Joseph REDMON, Farhadi ALI. YOLOv3: an incremental improvement. arXiv preprint arXiv:1804.02767, 2018. 2, 4, 7, 11.
17. Bochkovskiy A, Wang CY, Liao HYM. Yolov4: optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934, 2020.7.
18. Purkait P, Zhao C, Zach C. SPP-Net: deep absolute pose regression with synthetic views. arXiv preprint arXiv:1712.03452, 2017.
19. 10.1109/ICCV.2015.16910.1109/ICCV.2015.169 ↗
20. 10.1145/2964284.296727410.1145/2964284.2967274 ↗
21. 10.1109/CVPR.2019.0007510.1109/CVPR.2019.00075 ↗
22. 10.1609/aaai.v34i07.699910.1609/aaai.v34i07.6999 ↗
23. 10.1109/CVPR.2017.10610.1109/CVPR.2017.106 ↗
24. 10.1109/CVPR.2018.0091310.1109/CVPR.2018.00913 ↗
25. 10.1109/CVPR42600.2020.0107910.1109/CVPR42600.2020.01079 ↗
26. Qiao S, Chen LC, Yuille A. Detectors: detecting objects with recursive feature pyramid and switchable atrous convolution. arXiv 2020. arXiv preprint arXiv:2006.02334.10.1109/CVPR46437.2021.01008 ↗