Research on textile defects detection based on improved generative adversarial network
Source abstract
Abstract
Fabric defects seriously affect the textile industry in China. Given that traditional manual detection methods have low efficiency and poor accuracy, using automatic textile defect detection methods is urgently needed. A fabric defect detection method based on an improved generative adversarial network is thus developed to address the shortage of fabric defect samples. This method learns to reconstruct the fabric image in an unsupervised manner and locates the defect areas based on the differences between the original image and the reconstruction. Afterward, the defect-related features are extracted from these areas to further recognize specific fabric defects. The central loss constraint is introduced to improve the recognition performance of this method, and lightweight processing is applied to guarantee its real-time operation in embedded systems. The application of this method is then evaluated on the publicly available Tianchi dataset. Both quantitative and qualitative results show that the proposed method can accurately detect fabric defects.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Industrial Vision Systems and Defect Detection · Textile materials and evaluations · Integrated Circuits and Semiconductor Failure Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China
Changzhou Vocational Institute of Textile and Garment, Changzhou, China
References (54)
Show source-provided references
1. 10.1080/0040500920863121710.1080/00405009208631217 ↗
2. Liu Z · J. Textile Res · 2014 · 35 · 62
3. 10.1109/ICSPS.2010.555563310.1109/ICSPS.2010.5555633 ↗
4. Hao M · J Electron Meas Instrum · 2018 · 32 · 95
5. 10.1080/00405000.2012.69294010.1080/00405000.2012.692940 ↗
6. 10.1109/ITCE.2018.831661110.1109/ITCE.2018.8316611 ↗
7. 10.1080/00405000.2013.87615410.1080/00405000.2013.876154 ↗
8. 10.1016/j.ijleo.2013.05.00410.1016/j.ijleo.2013.05.004 ↗
9. Konda Reddy RO · Int J Inf Eng Electron Bus · 2013 · 5 · 25
10. 10.1109/IIC.2015.715082010.1109/IIC.2015.7150820 ↗
11. 10.1177/004051751245834010.1177/0040517512458340 ↗
12. 10.1080/00405000.2018.148995110.1080/00405000.2018.1489951 ↗
13. 10.21608/mjeer.2020.10328610.21608/mjeer.2020.103286 ↗
14. 10.1109/EBBT.2018.839144010.1109/EBBT.2018.8391440 ↗
15. 10.1109/TNNLS.2021.308414310.1109/TNNLS.2021.3084143 ↗
16. 10.1108/IJCST-11-2018-013510.1108/IJCST-11-2018-0135 ↗
17. Wei B · 2018 · 45
18. Che J · J Jilin Univ · 2019 · 49 · 2038
19. 10.1177/155892502090826810.1177/1558925020908268 ↗
20. 10.1007/978-3-030-31654-9_4510.1007/978-3-030-31654-9_45 ↗
21. 10.1109/ACCESS.2017.267594010.1109/ACCESS.2017.2675940 ↗
22. 10.1109/ACCESS.2020.304184910.1109/ACCESS.2020.3041849 ↗
23. 10.1007/s11042-017-5263-z10.1007/s11042-017-5263-z ↗
24. Li C · Secur Commun Netw · 2021 · 2021 · 1
25. 10.1109/TASE.2017.269674810.1109/TASE.2017.2696748 ↗
26. Brad R · J Text Eng Fash Technol · 2017 · 3 · 00107
27. 10.1016/j.patcog.2003.10.01110.1016/j.patcog.2003.10.011 ↗
28. 10.1016/j.procs.2018.07.05810.1016/j.procs.2018.07.058 ↗
29. Ren S · Adv Neural Inf Process Syst · 2015 · 28 · 91
30. 10.1109/CVPR.2016.9110.1109/CVPR.2016.91 ↗
31. Liu Z
32. 10.1109/ACCESS.2019.291362010.1109/ACCESS.2019.2913620 ↗
33. 10.1109/TIP.2019.295974110.1109/TIP.2019.2959741 ↗
34. 10.1016/j.neucom.2019.09.10710.1016/j.neucom.2019.09.107 ↗
35. 10.3390/s1804106410.3390/s18041064 ↗
36. 10.1109/CVPR.2001.99051710.1109/CVPR.2001.990517 ↗
37. 10.1109/CVPR.2014.8110.1109/CVPR.2014.81 ↗
38. 10.1109/ICCV.2015.16910.1109/ICCV.2015.169 ↗
39. 10.1109/ICCV.2017.32210.1109/ICCV.2017.322 ↗
40. 10.1007/978-3-319-46448-0_210.1007/978-3-319-46448-0_2 ↗
41. 10.1109/ICCV.2017.32410.1109/ICCV.2017.324 ↗
42. Jin P, Rathod V, Zhu X. Pooling pyramid network for object detection. 2018. ArXiv preprint arXiv: 1807.03284.
43. Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. 2014. arXiv preprint arXiv: 1409.1556.
44. 10.1109/CVPR.2016.9010.1109/CVPR.2016.90 ↗
45. 10.1109/CVPR.2017.24310.1109/CVPR.2017.243 ↗
46. Howard AG, Zhu M, Chen B, et al Mobilenets: efficient convolutional neural networks for mobile vision applications. 2017. ArXiv preprint arXiv: 1704.04861.
47. Iandola FN, Han S, Moskewicz MW, et al. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5 MB model size 2016. ArXiv preprint arXiv: 1602.07360.
48. 10.1109/CVPR.2018.0071610.1109/CVPR.2018.00716 ↗
49. Wang RJ, Li X, Ling CX Pelee: a real-time object detection system on mobile devices. 2018. ArXiv preprint arXiv: 1804.06882.
50. Ren H · Investig Ophthalmol Vis Sci · 2020 · 61 · 1635
51. 10.1007/s00521-018-3894-210.1007/s00521-018-3894-2 ↗
52. 10.1109/MSP.2017.276520210.1109/MSP.2017.2765202 ↗
53. 10.1007/978-3-319-46478-7_3110.1007/978-3-319-46478-7_31 ↗
54. Wu Z · J Comput Aided Des Comput Graph · 2018 · 30 · 2262