Abstract
Deep learning technology has been proven applicable in fabric defect detection, but the detection performance relies on the large-scale labeled training sets. However, it is a tedious task to construct these annotated datasets in the industrial production line. To alleviate this issue, an unsupervised fabric defect detection model based on generative adversarial network (GAN) with component-encoder is proposed. Firstly, a component encoder is integrated into the deep convolutional generative adversarial network (DCGAN) for easily training the acquired positive sample image instead of random noise, and it is easier for the model to fit the data distribution of the samples. And to ensure the authenticity of the reconstructed image, two loss functions are adopted for the original DCGAN. In the testing stage, the test image patches are input into the trained model to generate the normal image patches. Finally, the residual image obtained by subtracting the original image from the reconstructed image is segmented to localize the defect region. Experimental results on the fabric dataset demonstrate the proposed model can locate the defect region well.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Ngan, H.Y.: Automated fabric defect detection-a review. Image Vis. Comput. 29(7), 442–458 (2011)
Hanbay, K.: Fabric defect detection systems and methods-a systematic literature review. Optik 127(24), 11960–11973 (2016)
Cohen, F.S.: Automated inspection of textile fabrics using textural models. IEEE Trans. Pattern Anal. Mach. Intell. 13(08), 803–808 (1991)
Wen, W.: Verifying edges for visual inspection purposes. Pattern Recogn. Lett. 20(3), 315–328 (1999)
Kim, C.W.: Hierarchical classification of surface defects on dusty wood boards. Pattern Recogn. Lett. 15(7), 713–721 (1994)
Campbell, J.G.: Automatic visual inspection of woven textiles using a two-stage defect detector. Opt. Eng. 37(9), 2536–2542 (1998)
Yuan, X.C.: An improved Otsu method using the weighted object variance for defect detection. Appl. Surf. Sci. 349, 472–484 (2015)
Aminzadeh, M.: Automatic thresholding for defect detection by background histogram mode extents. J. Manuf. Syst. 37, 83–92 (2015)
Wood, E.J.: Applying Fourier and associated transforms to pattern characterization in textiles. Text. Res. J. 60(4), 212–220 (1990)
Haralick, R.M.: Statistical and structural approaches to texture. Proc. IEEE 67(5), 786–804 (1979)
Haralick, R.M.: Textural features for image classification. IEEE Trans. Syst. Man Cybern. 6, 610–621 (1973)
Ojala, T.: A comparative study of texture measures with classification based on featured distributions. Pattern Recogn. 29(1), 51–59 (1996)
Zhai, W., Zhu, J., Cao, Y.: A generative adversarial network based framework for unsupervised visual surface inspection. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), CONFERENCE 2018, pp. 1283–1287. IEEE (2018). https://doi.org/10.1109/ICASSP.2018.8462364
He, K., Zhang, X., Ren, S.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CONFERENCE 2016, pp. 770–778. CVPR (2016)
Huang, G., Liu, Z.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition CVPR, CONFERENCE 2017, pp. 4700–4708. CVPR (2017)
Krizhevsky, A.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems 25, pp. 1097–1105 (2012)
Simonyan, K.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Szegedy, C., Liu, W.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CONFERENCE 2015, pp. 1–9. CVPR (2015)
Wang, T.: A fast and robust convolutional neural network-based defect detection model in product quality control. Int. J. Adv. Manuf. Technol. 94(9), 3465–3471 (2018)
Chen, J.: Automatic defect detection of fasteners on the catenary support device using deep convolutional neural network. IEEE Trans. Instrum. Meas. 67(2), 257–269 (2017)
Gopalakrishnan, K.: Deep convolutional neural networks with transfer learning for computer vision-based data-driven pavement distress detection. Constr. Build. Mater. 157, 322–330 (2017)
Zhu, J.: Vision-based defects detection for bridges using transfer learning and convolutional neural networks. Struct. Infrastruct. Eng. 16(7), 1037–1049 (2020)
Goodfellow, I.: Generative adversarial networks. Commun. ACM 63(11), 139–144 (2020)
Zhao, Z., Li, B., Dong, R., Zhao, P.: A surface defect detection method based on positive samples. In: Geng, X., Kang, B.-H. (eds.) PRICAI 2018. LNCS (LNAI), vol. 11013, pp. 473–481. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-97310-4_54
Hu, G.: Unsupervised fabric defect detection based on a deep convolutional generative adversarial network. Text. Res. J. 90(3–4), 247–270 (2020)
Niu, S., Lin, H.: DefectGAN: weakly-supervised defect detection using generative adversarial network. In: 2019 IEEE 15th International Conference on Automation Science and Engineering (CASE), CONFERENCE 2019, pp. 127–132. IEEE (2019). https://doi.org/10.1109/COASE.2019.8843204
Liu, J.: Multistage GAN for fabric defect detection. IEEE Trans. Image Process. 29, 3388–3400 (2019)
Salimans, T.: Improved techniques for training GANs. Adv. Neural. Inf. Process. Syst. 29, 2234–2242 (2016)
Xie, X.: TEXEMS: texture exemplars for defect detection on random textured surfaces. IEEE Trans. Pattern Anal. Mach. Intell. 29(8), 1454–1464 (2007)
Acknowledgement
This work was supported by NSFC (No. 61772576, No. 62072489, U1804157), Henan science and technology innovation team (CXTD2017091), IRTSTHN (21IRTSTHN013), Program for Interdisciplinary Direction Team in Zhongyuan University of Technology, ZhongYuan Science and Technology Innovation Leading Talent Program (214200510013).
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Liu, Z., Gao, C., Li, C., Huang, N., Guo, Z. (2022). Unsupervised Fabric Defect Detection Based on DCGAN with Component-Encoder. In: Wallraven, C., Liu, Q., Nagahara, H. (eds) Pattern Recognition. ACPR 2021. Lecture Notes in Computer Science, vol 13188. Springer, Cham. https://doi.org/10.1007/978-3-031-02375-0_41
Download citation
DOI: https://doi.org/10.1007/978-3-031-02375-0_41
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-02374-3
Online ISBN: 978-3-031-02375-0
eBook Packages: Computer ScienceComputer Science (R0)