Fabric defect fetection via weighted low-rank decomposition and Laplacian regularization
Source abstract
Abstract
Low-rank decomposition models have potential for fabric defect detection, where a feature matrix is decomposed into a low-rank matrix that corresponding to repeated texture structure and a sparse matrix that represent defective regions. Two limitations, however, still exist. First, previous work might fail to detect some large homogeneous defective block. Second, when the background and defective regions are relatively coherent or the texture of fabric image is complex, it is difficult to use previous methods to separate them. To deal with these problems, a new weighted low-rank decomposition model with Laplace regularization (WLRL) is proposed in this paper: (1) a weighted low-rank decomposition model that can decompose the original image into background and defective regions, and (2) a Laplace regularization that can enlarge the distance between the background and the defective regions. The performance of the proposed method WLRL is evaluated on the box- and star-patterned fabric databases, and superior results are shown compared with state-of-the-art methods, that is, 98.70% ACC (accuracy) and 72.83% TPR (true positive rate) for box-patterned fabrics, 99.09% ACC (accuracy) and 83.63% TPR (true positive rate) for star-patterned fabrics.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Industrial Vision Systems and Defect Detection · Image Processing Techniques and Applications · Optical measurement and interference techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Computer Science and Artificial Intelligence, Changzhou University, Changzhou, China
School of Digital Media, Jiangnan University, Wuxi, China
Department of Mathematics and Statistics, University of North Carolina at Charlotte, USA
School of Modern Service Industry, Changzhou College of Information Technology, Changzhou, China
Funding
zhejiang province public welfare technology application research project · Postgraduate Research & Practice Innovation Program of Jiangsu Province
References (45)
Show source-provided references
1. 10.1016/j.ijleo.2016.09.11010.1016/j.ijleo.2016.09.110 ↗
2. 10.1016/j.neucom.2015.09.01110.1016/j.neucom.2015.09.011 ↗
3. 10.1109/TPAMI.1982.476730910.1109/TPAMI.1982.4767309 ↗
4. 10.1109/28.87127410.1109/28.871274 ↗
5. 10.1364/AO.54.00296310.1364/AO.54.002963 ↗
6. 10.1016/j.rcim.2007.02.01910.1016/j.rcim.2007.02.019 ↗
7. 10.1179/136821905X2693510.1179/136821905X26935 ↗
8. 10.1109/TPAMI.2004.3010.1109/TPAMI.2004.30 ↗
9. Dogandžić A · 760 · 70410.1063/1.1916744 ↗
10. 10.1016/S0262-8856(03)00003-910.1016/S0262-8856(03)00003-9 ↗
11. 10.5505/pajes.2016.8003710.5505/pajes.2016.80037 ↗
12. 10.1016/j.engappai.2008.05.00610.1016/j.engappai.2008.05.006 ↗
13. Grech I, Micallef J, Debono C J, et al. In: ICECS’99. Proceedings of ICECS’99. 6th IEEE international conference on electronics, circuits and systems (Cat. No. 99EX357), Pafos, Cyprus, 5–8 September 1999, vol. 2, pp. 765–768. IEEE.
14. Kang Z · 597
15. 10.1137/17M111313810.1137/17M1113138 ↗
16. 10.1016/j.patcog.2004.07.00910.1016/j.patcog.2004.07.009 ↗
17. 10.1016/j.patcog.2015.09.02210.1016/j.patcog.2015.09.022 ↗
18. 10.1016/j.neucom.2017.01.03910.1016/j.neucom.2017.01.039 ↗
19. 10.1109/TASE.2017.269674810.1109/TASE.2017.2696748 ↗
20. Wang B
21. Zhang Y
22. 10.1177/155892502090302610.1177/1558925020903026 ↗
23. Gao G · 1118
24. 10.1108/IJCST-10-2015-011710.1108/IJCST-10-2015-0117 ↗
25. 10.1109/TPAMI.2016.256262610.1109/TPAMI.2016.2562626 ↗
26. 10.1145/1970392.197039510.1145/1970392.1970395 ↗
27. 10.1016/j.imavis.2013.12.00310.1016/j.imavis.2013.12.003 ↗
28. 10.1109/TPAMI.2004.126233210.1109/TPAMI.2004.1262332 ↗
29. 10.1155/2018/529635010.1155/2018/5296350 ↗
30. 10.1109/MSP.2018.282656610.1109/MSP.2018.2826566 ↗
31. 10.1016/j.cosrev.2016.11.00110.1016/j.cosrev.2016.11.001 ↗
32. Lin Z, Zhang H. Low-rank models in visual analysis: theories, algorithms, and applications. Academic Press, San Diego, CA, 2017, pp. 262.
33. Pu J · IEEE Trans Syst Man Cybern · 2020 · 50 · 2288
34. 10.1109/TIP.2018.287428910.1109/TIP.2018.2874289 ↗
35. 10.1109/JSEN.2018.287145910.1109/JSEN.2018.2871459 ↗
36. Sobral A · 1
37. 10.1109/ACCESS.2019.292556310.1109/ACCESS.2019.2925563 ↗
38. 10.1016/j.jvcir.2018.09.00910.1016/j.jvcir.2018.09.009 ↗
39. Liu YB · Adv Mat Res · 2011 · 301 · 229
40. 10.1080/00405000.2012.69294010.1080/00405000.2012.692940 ↗
41. Hu GH · 2 · 860
42. Lin Z · 612
43. 10.1137/08073897010.1137/080738970 ↗
44. 10.1109/TPAMI.2012.12010.1109/TPAMI.2012.120 ↗
45. Zhoufeng L · Microcomp Its Appl · 2013 · 10 · 016