Muhammed Fatih TALU, Kazım HANBAY, Mahdi HATAMİ VARJOVİ

CNN-Based Fabric Defect Detection System on Loom Fabric Inspection

Fabric defect detection is generally performed based on human visual inspection. This method is not effective and it has various difficulties such as eye delusion and labor cost. To deal with these problems, machine learning, and computer vision-based intelligent systems have been developed. In this paper, a novel real-time fabric defect detection system is proposed. The proposed industrial vision system has been operated in real-time on a loom. Firstly, two fabric databases are constructed by using real fabric images and defective patch capture (DPC) algorithm. Thanks to the novel developed fast Fourier transform-based DPC algorithm, defective texture areas become visible and defect-free areas are suppressed, even on complex denim fabric textures. Secondly, an appropriate convolution neural networks (CNN) model integrated negative mining is determined. However, traditional feature extraction and classification approaches are also used to compare classification performances of deep models and traditional models. Experimental results show that our proposed CNN model integrated negative mining can classify the defected images with high accuracy. Also, the proposed CNN model has been tested in real-time on a loom, and it achieves 100% detection accuracy.

Keywords:

Computer vision fabric defect detection, CNN, feature extraction,

PDF

___

1. K. Hanbay, M.F. Talu, Ö.F. Özgüven, Fabric defect detection systems and methods—A systematic literature review, Optik (Stuttg). 127 (2016) 11960–11973. doi:http://doi.org/10.1016/j.ijleo.2016.09.110.
2. H. Zuo, Y. Wang, X. Yang, X. Wang, Fabric defect detection based on texture enhancement, in: 2012 5th Int. Congr. Image Signal Process., 2012: pp. 876–880. doi:10.1109/CISP.2012.6469799.
3. C. Duchesne, J.J. Liu, J.F. MacGregor, Multivariate image analysis in the process industries: A review, Chemom. Intell. Lab. Syst. 117 (2012) 116–128.
4. K.-L. Mak, P. Peng, K.F.C. Yiu, Fabric defect detection using morphological filters, Image Vis. Comput. 27 (2009) 1585–1592.
5. L. Tong, W.K. Wong, C.K. Kwong, Differential evolution-based optimal Gabor filter model for fabric inspection, Neurocomputing. 173 (2016) 1386–1401.
6. K. Hanbay, M. Talu, O. Ozguven, Real time fabric defect detection by using fourier transform, J. Fac. Eng. Archit. Gazi Univ. 32 (2017) 151–158.
7. P. Anandan, R.S. Sabeenian, Fabric defect detection using discrete curvelet transform, Procedia Comput. Sci. 133 (2018) 1056–1065.
8. J.P. Monaco, A. Madabhushi, Class-specific weighting for Markov random field estimation: Application to medical image segmentation, Med. Image Anal. 16 (2012) 1477–1489.
9. Y. Zhao, K. Hao, H. He, X. Tang, B. Wei, A visual long-short-term memory based integrated CNN model for fabric defect image classification, Neurocomputing. 380 (2020) 259–270.
10. J. Jing, H. Zhang, J. Wang, P. Li, J. Jia, Fabric defect detection using Gabor filters and defect classification based on LBP and Tamura method, J. Text. Inst. 104 (2013) 18–27.
11. K. Hanbay, Fabric Defect Detection System Based on Image Processing for Circular Knitting Machines, Univ. of Inonu, 2016.
12. Jiahan Chen, Anil K. Jain, A Structural Approach To Identify Defects In Textured Images, in: Proc. 1988 IEEE Int. Conf. Syst. Man, Cybern., 1988: pp. 29–32. doi:10.1109/ICSMC.1988.754234.
13. Z. Wen, J. Cao, X. Liu, S. Ying, Fabric defects detection using adaptive wavelets, Int. J. Cloth. Sci. Technol. (2014).
14. L. Jia, C. Chen, S. Xu, J. Shen, Fabric defect inspection based on lattice segmentation and template statistics, Inf. Sci. (Ny). 512 (2020) 964–984.
15. L. Jia, J. Liang, Fabric defect inspection based on isotropic lattice segmentation, J. Franklin Inst. 354 (2017) 5694–5738.
16. C.-F.J. Kuo, C.-J. Lee, A back-propagation neural network for recognizing fabric defects, Text. Res. J. 73 (2003) 147–151.
17. K.L. Mak, P. Peng, An automated inspection system for textile fabrics based on Gabor filters, Robot. Comput. Integr. Manuf. 24 (2008) 359–369.
18. H. Bu, J. Wang, X. Huang, Fabric defect detection based on multiple fractal features and support vector data description, Eng. Appl. Artif. Intell. 22 (2009) 224–235.
19. K. Hanbay, M.F. Talu, Ö.F. Özgüven, D. Öztürk, Real-Time Detection of Knitting Fabric Defects Using Shearlet Transform., J. Text. Appar. 29 (2019) 3–10.
20. K. Zhang, Y. Yan, P. Li, J. Jing, Z. Wang, Z. Xiong, Fabric defect detection using saliency of multi-scale local steering kernel, IET Image Process. 14 (2020) 1265–1272. doi:10.1049/iet-ipr.2018.5857.
21. J. Jing, A. Dong, P. Li, K. Zhang, Yarn-dyed fabric defect classification based on convolutional neural network, Opt. Eng. 56 (2017) 93104.
22. Z. Wang, J. Jing, Pixel-Wise Fabric Defect Detection by CNNs Without Labeled Training Data, IEEE Access. 8 (2020) 161317–161325. doi:10.1109/ACCESS.2020.3021189.
23. M. An, S. Wang, L. Zheng, X. Liu, Fabric defect detection using deep learning: An Improved Faster R-approach, in: 2020 Int. Conf. Comput. Vision, Image Deep Learn., 2020: pp. 319–324. doi:10.1109/CVIDL51233.2020.00-78.
24. H. Zhou, B. Jang, Y. Chen, D. Troendle, Exploring Faster RCNN for Fabric Defect Detection, in: 2020 Third Int. Conf. Artif. Intell. Ind., 2020: pp. 52–55. doi:10.1109/AI4I49448.2020.00018.
25. Y. Dong, J. Wang, C. Li, Z. Liu, J. Xi, A. Zhang, Fusing Multilevel Deep Features for Fabric Defect Detection Based NTV-RPCA, IEEE Access. 8 (2020) 161872–161883. doi:10.1109/ACCESS.2020.3021482.
26. S. Mei, Y. Wang, G. Wen, Automatic fabric defect detection with a multi-scale convolutional denoising autoencoder network model, Sensors. 18 (2018) 1064.
27. W. Wei, D. Deng, L. Zeng, C. Zhang, Real-time implementation of fabric defect detection based on variational automatic encoder with structure similarity, J. Real-Time Image Process. (2020) 1–17.
28. Uster Technologies AG. Fabric inspection, (n.d.). https://www.uster.com/en/instruments/fabric-inspection/ (accessed July 15, 2020).
29. BMSvision, Camera Inspection, (2019).
30. N. Dalal, B. Triggs, Histograms of oriented gradients for human detection, in: 2005 IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., 2005: pp. 886–893 vol. 1. doi:10.1109/CVPR.2005.177.
31. R.M. Haralick, K. Shanmugam, I. Dinstein, Textural Features for Image Classification, IEEE Trans. Syst. Man. Cybern. SMC-3 (1973) 610–621. doi:10.1109/TSMC.1973.4309314.
32. T. Watanabe, S. Ito, K. Yokoi, Co-occurrence Histograms of Oriented Gradients for Pedestrian Detection, in: Adv. Image Video Technol., Springer Berlin Heidelberg, Berlin, Heidelberg, 2009: pp. 37–47.
33. Chi-Ho Chan, G.K.H. Pang, Fabric defect detection by Fourier analysis, IEEE Trans. Ind. Appl. 36 (2000) 1267–1276. doi:10.1109/28.871274.
34. M.N. Do, M. Vetterli, Wavelet-based texture retrieval using generalized Gaussian density and Kullback-Leibler distance, IEEE Trans. Image Process. 11 (2002) 146–158.
35. G. Easley, D. Labate, W.-Q. Lim, Sparse directional image representations using the discrete shearlet transform, Appl. Comput. Harmon. Anal. 25 (2008) 25–46.
36. CALIK DENIM, (n.d.). July 20, 2020, https://www.calikdenim.com.

ISSN: 1300-3356
Yayın Aralığı: Yılda 4 Sayı
Yayıncı: Ege Üniversitesi Tekstil ve Konfeksiyon Araştırma & Uygulama Merkezi

Arşiv