Automated fabric inspection system development aided with convolutional autoencoder-based defect detection

Abstract

Industrial automatic fabric inspection system, a critical technology in the industry, enhances both total production quantity and quality compared to conventional inspection techniques. This study aims to create a reliable and effective real-time automated visual inspection system for fabrics, focusing on defect detection. The goals of the study can be stated as; installing a system with advanced technology for capturing and processing images swiftly, the development and deployment of a system capable of autonomously learning and scanning fabrics in use, and the creation of a smart framework for accurate fabric defect detection and classification. We focus on the development of unsupervised fabric defect detection using a convolutional autoencoder model, and defect classification using a convolutional neural network model, which takes input as the feature vector generated by the convolutional autoencoder. The experimental outcomes have displayed significant success rates in both detecting defects and classifying them, confirming the effectiveness of the framework in real-time visual inspection systems.

Keywords

• Fabric defect detection
• Fabric inspection system
• Convolutional autoencoder

Evrişimli otokodlayıcı tabanlı hata tespiti ile desteklenen otomatik kumaş inceleme sistemi geliştirilmesi

Öz

Endüstriyel otomatik kumaş inceleme sistemi, endüstride klasik inceleme tekniklerine göre hem toplam üretim miktarını hem de kaliteyi artıran kritik bir teknolojidir. Bu çalışma, kumaşlar için güvenilir ve etkili bir gerçek zamanlı otomatik görsel inceleme sistemi oluşturmayı amaçlamaktadır ve odak noktası olarak hata tespiti üzerinde yoğunlaşmaktadır. Çalışmanın hedefleri; hızlı bir şekilde görüntüleri yakalama ve işleme yeteneğine sahip gelişmiş teknolojiye sahip bir sistem kurmak, kullanımdaki kumaşları otomatik olarak öğrenme ve tarayabilme yeteneğine sahip bir sistem geliştirme ve, doğru kumaş hata tespiti ve sınıflandırması için akıllı bir yaklaşım oluşturmak şeklinde ifade edilebilir. Çalışmada, evrişimli otokodlayıcı modeli kullanarak denetimsiz bir kumaş hata tespiti ve evrişimli sinir ağı modeli kullanarak hata sınıflandırma geliştirme işlemleri üzerinde durulmaktadır. Sınıflandırmada kullanılan evrişimli sinir ağının girişine evrişimli otokodlayıcı tarafından üretilen özellik vektörü sunulmaktadır. Deney sonuçları analiz edildiğinde, hem hataları tespitte hem de bunları sınıflandırmada önemli başarı sergilenmiştir ve yaklaşımın gerçek zamanlı görsel inceleme sistemlerindeki etkinliğini gösterilmiştir.

Anahtar Kelimeler

• Kumaş hatası tespiti
• Kumaş inceleme sistemi
• Evrişimli otokodlayıcı

Kaynakça

1. K. Srinivasan, P. H. Dastoor, and S. Jayaraman, FDAS: architecture and implementation. Expert Systems, 9, 115-124, 1992. http://dx.doi.org/10.1111/j.1468-0394.1992.tb00392.x.
2. C.H. Chan and G. K. H. Pang, Fabric defect detection by Fourier analysis. IEEE Transactions on Industry Applications, 36(5), 1267-1276, 2000. http://dx.doi.org/10.1109/28.871274.
3. Standard Test Methods for Visually Inspecting and Grading Fabrics. D5430–13, 2017.
4. Fabric inspection systems: Agteks. https://www.agteks.com/fabric-inspection-systems Accessed 25 April 2024.
5. C. Li, J. Li, Y. Li, L. He, X. Fu, and J. Chen, Fabric defect detection in textile manufacturing: a survey of the state of the art. Security and Communication Networks, 1-13, 2023. http://dx.doi.org/10.1155/2021/9948808.
6. M. F. Talu, K. Hanbay, and M. H. Varjovi, CNN-based fabric defect detection system on loom fabric inspection. Textile And Apparel, 32(3), 208-219, 2022. https://doi.org/10.32710/tekstilvekonfeksiyon. 1032529.
7. G. Gao C. Liu, Z. Liu, C. Li, and R. Yang, Fabric defect detection based on Gabor filter and tensor low-rank recovery. 4th IAPR Asian Conference on Pattern Recognition (ACPR), Nanjing, China, 2017, 73-78, 2017.
8. J. Chockalingam and S. Mondal, Fractal-based pattern extraction from time-Series NDVI data for feature identification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 10(12), 5258-5264, December, 2017. http://dx.doi.org/ 0.1109/JSTARS.2017.2748989.

9. K. Sakhare, A. Kulkarni, M. Kumbhakarn, N. Kare, Spectral and spatial domain approach for fabric defect detection and classification. 2015 International Conference on Industrial Instrumentation and Control (ICIC), Pune, India, 2015.
10. A. Bakhshipour, A. Jafari, S. Nassiri, and D. Zare, Weed segmentation using texture features extracted from wavelet sub-images. Biosystems Engineering, 157,1-12,2017. https://doi.org/10.1016/J.BIOSYSTEMSENG.2017.02.002.
11. J. Liang, C. Che, L. Jiuzhen, and H. Zhenjie, Fabric defect inspection based on lattice segmentation and Gabor filtering, Neurocomputing, 238, 84-102, 2017. https://doi.org/10.1016/j.neucom.2017.01.039.
12. Z. Ren, F. Fang, and Y. Y. Wu, State of the art in defect detection based on machine vision. International Journal of Precision Engineering and Manufacturing-Green Technology, 9, 661–691 2022. http://dx.doi.org/10.1007/s40684-021-00343-6.
13. J. H. Dewan, R. Das, S. D. Thepade, H. Jadhav, N. Narsale, A. Mhasawade, and S. Nambiar, Image classification by transfer learning using pre-trained CNN models. 2023 International Conference on Recent Advances in Electrical, Electronics, Ubiquitous Communication, and Computational Intelligence (RAEEUCCI), Chennai, India, 1-6, 2023.
14. O. Ronneberger, P. Fischer, and T. Brox, U-net: convolutional networks for biomedical image segmentation. MICCAI 2015, Lecture Notes in Computer Science, 9351, 234–241. Springer, Cham, 2015. https://doi.org/10.48550/arXiv.1505.04597.
15. S.S. Mohammed and H.G. Clarke, A hybrid machine learning approach to fabric defect detection and classification, ICECENG 2022. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, 436, 135-147, 2022. http://dx.doi.org/10.1177/09544054231209782.
16. J. Silvestre-Blanes, T. Albero-Albero, I. Miralles, R. Pérez-Llorens, and J. Moreno, A public fabric database for defect detection methods and results. Autex Res. J. 19(4), 363–374, 2019. http://dx.doi.org/10.2478/aut-2019-0035.
17. J. Jing, A. Dong, P. Li, and K. Zhang, Yarn-dyed fabric defect classification based on convolutional neural network. Optical Engineering, 56(9), 93104, 2017. https://doi.org/10.1117/1.OE.56.9.093104.
18. Y. Guo, X. Kang, J. Li, and Y. Yang, Automatic fabric defect detection method using AC-YOLOv5, Electronics, 2023, 12, 2950, 2023. http://dx.doi.org/10.3390/electronics12132950.
19. T. Wang, Y. Chen, M. Qiao, and H. Snoussi, A fast and robust convolutional neural network-based defect detection model in product quality control. Int Journal of Advance Manufacturing Technology, 94, 3465–3471, 2018. https://doi.org/10.1007/s00170-017-0882-0.
20. H. Zhou, B. Jang, Y. Chen, and D. Troendle, Exploring faster RCNN for fabric defect detection. Third International Conference on Artificial Intelligence for Industries (AI4I), Irvine, CA, USA, 52-55, 2020.
21. Y. Zhao, K. Hao, H. He, X. Tang, and B. Wei, A visual long-short-term memory based integrated CNN model for fabric defect image classification, Neurocomputing, 380, 259-270, 2020. http://dx.doi.org/10.1016/j.neucom.2019.10.067.
22. B. Olimov, B. Subramanian, and J. Kim, Unsupervised deep learning-based end-to-end network for anomaly detection and localization. Thirteenth International Conference on Ubiquitous and Future Networks (ICUFN), Barcelona, Spain, 2022.
23. M. Sewak, S.K. Sahay, and H. Rathore, An overview of deep learning architecture of deep neural networks and autoencoders, Journal of Computational and Theoretical Nanoscience, 17(1), 182-188, January 2020. http://dx.doi.org/10.1166/jctn.2020.8648.
24. H. Tian and F. Li, Autoencoder-based fabric defect detection with drossp similarity. 16th International Conference on Machine Vision Applications (MVA), Tokyo, Japan, 2019.
25. P. Bergmann, S. Löwe, M. Fauser, D. Sattlegger, and C. Steger, Improving unsupervised defect segmentation by applying structural similarity to autoencoders. Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAP’13), Madeira Portugal, 27-29 Jan 2018.
26. E. Solovyeva and A. Abdullah, Dual autoencoder network with separable convolutional layers for denoising and deblurring Images. Journal of Imaging, 8(9), 250, 2022. https://doi.org/10.3390/jimaging8090250.
27. S. Mei, Y. Wang, and G. Wen Automatic fabric defect detection with a multi-scale convolutional denoising autoencoder network model, Sensors, 18, 1064, 2018. https://doi.org/10.3390/s18041064.
28. O. Rippel M. Müller, and D. Merhof, GAN-based defect dynthesis for anomaly setection in fabrics. 25th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), Vienna, Austria, 2020.
29. I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, Generative adversarial nets, advances in neural information processing systems. 3(6), 2014. https://doi.org/10.48550/arXiv.1406.2661.
30. J. Fan, W. K. Wong, J. Wen, C. Gao, D. Mo, and Z. Lai, Fabric defect detection using deep convolution neural network. AATCC Journal of Research, 8 (1_suppl),143-150, 2021. https://doi.org/10.14504/ajr.8.S1.18.
31. J. Masci, U. Meier, D. Cire, and J. Schmidhuber, Stacked convolutional auto-encoders for hierarchical feature extraction. Proceedings of the International Conference on Artificial Neural Networks, Springer, pp. 52–59, 2011.
32. Y. J. Han and H. J. Yu, Fabric defect detection system using stacked convolutional denoising auto-encoders trained with synthetic defect data. Applied Sciences, 10(7), 2511, 2020. https://doi.org/10.3390/app10072511.
33. C. C. Chen, C.H. We, and C.S. Lin, Fast detection of fabric defects based on neural networks. Sixth International Symposium on Computer, Consumer and Control (IS3C), Taichung, Taiwan, 2023.
34. A. Taherkhani, C. Georgina, T. McGinnity, AdaBoost-CNN: an adaptive boosting algorithm for convolutional neural networks to classify multi-class imbalanced datasets using transfer learning. Neurocomputing, 404, 351-366, 2020. https://doi.org/10.1016/j.neucom.2020.03.064.