Abstract
Automatic detection of fabric defects based on machine vision is an important topic in the quality control of cotton textile factories. There are many kinds of defects in fabric production, it is very difficult to classify the defects automatically. In recent years, deep learning image processing technology based on a convolutional neural network (CNN) can train and extract features of the target image automatically. Since a large number of defect samples cannot be collected completely, we compared unsupervised learning algorithms based on CNN, including auto encoder (AE), variational automatic encoder (VAE), and generative adversarial networks (GAN). Because of the large amount of calculation and the difficulty of training in GAN, we chose AE and VAE codec networks and then introduced mean structural similarity (MSSIM) as network training loss function to improve the performance that only used \({L}_{p}\)-distance loss function for image brightness comparison. After training finished, the authors used the trained model to obtain target defects from SSIM residual maps between input and reconstruct images. According to the evaluation results, we finally implemented a fabric defect detection system based on VAE on Jetson TX2 from Nvidia Corporation, USA. The optimized algorithm can meet the real-time requirements of the project and realize its popularization and application.
Similar content being viewed by others
References
Ngan, H., Pang, G., Yung, N.: Automated fabric defect detection-A review. Image Vis. Comput. 29(7), 442–458 (2011)
Chiu, S.H., Chou, S., Liaw, J.J.: Textural defect segmentation using a Fourier-domain maximum likelihood estimation method. Text. Res. J. 72(3), 253–258 (2002)
Tsai, D.M., Huang, T.Y.: Automated surface inspection for statistical textures. Image Vis. Comput. 21(4), 307–323 (2003)
Chan, C.H., Pang, G.K.H.: Fabric defect detection by Fourier analysis. IEEE Trans. Ind. Appl. 36(5), 1267–1276 (2000)
Cohen F.S., Fan Z.G., Attali, S.: Automated inspection of textile fabric using textural models. IEEE Trans. Pattern Anal. Mach. Intell. 13(8), 803–808 (1991)
Chan H.Y., Raju C., Sari-Sarraf H.: A general approach to defect detection in textured materials using a wavelet domain model and level sets. Proceedings of SPIE—The International Society for Optical Engineering 6001(3), 309–310 (2005).
Castilho, H.P., Goncalves, P.J.S., Pinto, J.R.C.: Intelligent real-time fabric defect detection. Image Anal. Recognit. 4633, 1297–1307 (2007)
Zhang, Y., Lu, Z., Li, J.: Fabric defect classification using radial basis function network. Pattern Recogn. Lett. 31(13), 2033–2042 (2010)
Yin, Y., Zhang, K., Lu, W.: Textile flaw classification by wavelet reconstruction and BP neural network. Lect. Notes Comput. Sci. 5552, 694–701 (2009)
Ngan, H.Y.T., Pang, G.K.H., Yung, N.H.C.: Performance evaluation for motif-based patterned texture defect detection. IEEE Trans. Autom. Sci. Eng. 7(1), 58–72 (2010)
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)
Ren, S.Q., He, K.M., Ross, G.: Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39, 1137–1149 (2017).
Liu, W., Anguelov, D., Erhan, D.: SSD: Single shot multibox detector. European Conference on Computer Vision 9905, 21–37 (2016)
Redmon, J., Farhadi, A.: Yolo9000: better, faster, stronger. IEEE Conference on Computer Vision and Pattern Recognition, pp 6517–6525 (2017).
Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313, 504–507 (2006)
Tan, C.C., Eswaran, C.: Using autoencoders for mammogram compression. J. Med. Syst. 35(1), 49–58 (2011)
Kingma, D.P., Max, W.: Auto-encoding variational bayes. arXiv:1312.6114 (2013).
Goodfellow, I.J., Pouget-Adadie, J., Mirza, M.: Generative adversarial networks. Adv. Neural. Inf. Process. Syst. 3, 2672–2680 (2014)
Ngan, H., Pang, G., Yung, N.: Patterned fabric defect detection using a motif-based approach. IEEE Int. Conf. Image Process. 2, 33–36 (2007)
Bi, M., Sun, Z.G., Zou, C.: Real-time textural defect detection based on label run-length co-occurrence matrix. International Conference on Transportation, Mechanical, and Electrical Enginerring (2011). https://doi.org/https://doi.org/10.1109/TMEE.2011.6199195.
Si, X.S., Zheng, H., Hu, X.M.: Fabric defect detection based on SRG-PCNN. Adv. Mater. Res. 148–149, 1319–1326 (2010).
Karras, D.A.: Improved defect detection using support vector machines and wavelet Feature extraction based on vector quantization and SVD techniques. Proc. Int. Jt. Conf. (2003). https://doi.org/10.1109/IJCNN.2003.1223774
Li, P., Liang, J., Shen, X., et al.: Textile fabric defect detection based on low-rank representation. Multimed. Tools Appl. 78, 99–124 (2019). https://doi.org/10.1007/s11042-017-5263-z
Lizarraga-Morales, R.A., Correa-Tome, F.E., Sanchez-Yanez, R.E.: On the use of binary features in a rule-based approach for defect detection on patterned textiles. IEEE Access 7, 18042–18049 (2019). https://doi.org/10.1109/ACCESS.2019.2896078
Wei, B., Hao, K., Tang, X.S.: Fabric defect detection based on faster RCNN. In International Conference on Artificial Intelligence on Textile and Apparel, pp.45–51 (2018). https://doi.org/https://doi.org/10.1007/978-3-319-99695-0_6.
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323, 533–536 (1986)
Christoph, B., Benedikt, W., Shadi, A.: Deep autoencoding models for unsupervised anomaly segmentation in brain MR images. arXiv:1804.04488 (2018).
Arjovsky, M., Bottou, L.: Towards principled methods for training generative adversarial networks. arXiv: arXiv:1701.04862 (2017).
An, J.W., Cho, S.Z.: Variational autoencoder based anomaly detection using reconstruction probability. SNU Data Mining Center. https://dm.snu.ac.kr/static/docs/TR/SNUDM-TR-2015-03.pdf (2015). Accessed 15 Feb 2015.
Wang, Z., Alan, C.B., Hamid, R.S.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)
Wang, Z., Alan, C.B.: A universal image quality index. IEEE Signal Process. Lett. 9(3), 81–84 (2002).
Workgroup on Texture Analysis of DFG. TILDA Textile Texture Database. https://lmb.informatik.uni-freiburg.de/resources/datasets/tilda.en.html (1996). Accessed 1 Aug 1996.
KLI-2113 Linear CCD image sensor. Literature Distribution Center of ON Semiconductor. https://cn.alldatasheet.com/datasheet-pdf/pdf/787597/ONSEMI/KLI-2113-D.html (2015). Accessed 1 Nov 2015.
Wei, W., Deng, D.X., Zeng, L., Zhang, C.: Classification of foreign fibers using deep learning and its implementation on embedded system. Int. J. Adv. Rob. Syst. 16(4), 1–20 (2019)
Zhang, C., Sun, S.L., Shi, W.X.: Design and test of foreign fiber removal machine based on embedded system. Trans. Chin. Soc. Agric. Mach. 48(3), 43–53 (2017)
Alec, R., Luke, M., Soumith, C.: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv:1511.06434(2015).
Kumar, A., Gupta, S.: Real time DSP based identification of surface defects using content-based imaging technique. Proc. IEEE Int. Conf. Ind. Technol. (2000). https://doi.org/10.1109/ICIT.2000.854109
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Wei, W., Deng, D., Zeng, L. et al. Real-time implementation of fabric defect detection based on variational automatic encoder with structure similarity. J Real-Time Image Proc 18, 807–823 (2021). https://doi.org/10.1007/s11554-020-01023-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11554-020-01023-5