A Novel Industrial Application of CNN Approach: Real Time Fabric Inspection and Defect Classification on Circular Knitting Machine

Year 2022, Volume: 32 Issue: 4, 344 - 352, 31.12.2022

Halil İbrahim Çelik , Lale Canan Dülger , Burak Öztaş , Mehmet Kertmen Elif Gültekin

https://doi.org/10.32710/tekstilvekonfeksiyon.1017016

Cited By: 2

Abstract

Fabric Automatic Visual Inspection (FAVI) system provides reliable performance on fabric defects inspection. This study presents a machine vision system developed to adapt in circular knitting machines where fabric defects can be automatically controlled and detected defects can be classified. The knitted fabric surface are detected during real-time manufacturing. For the classification process, three different transfer learning architectures (ResNet-50, AlexNet, GoogLeNet) have been applied. The five common knitted fabric defects were recognized with the artificial intelligence-based software and classified with an average success rate of 98% using ResNet-50 architecture. The success rates of the trained networks were compared.

Keywords

Circular knitting machine, Knitted fabric, Defect detection, Deep learning, Convolutional neural network (CNNs)

Supporting Institution

Scientific and Technological Research Council of Turkey (TUBİTAK)

Project Number

5180057

Thanks

This study is supported by the Scientific and Technological Research Council of Turkey (TUBİTAK). Project Number: 5180057. We express our sincere thanks for their financial support.

References

• Goodfellow I, Bengio Y, Courville A. 2016. Deep learning (Vol. 1, No. 2). Place: MIT Press Cambridge.
• J Patterson, A Gibson. 2017. Deep Learning: A Practitioner’s Approach. Place: O’Reilly Books.
• Çelik Hİ, Dülger LC, Topalbekiroğlu M. 2013. Development of a machine Vision System: real-time fabric defect detection and classification with neural networks. The Journal of Textile Institute 105(6), 575-585.
• A Rasheed, B Zafar, A Rasheed, N. 2020. Fabric Defect Detection using Computer Vision Techniques: A Comprehensive Review. Hindawi-Mathematical Problems in Engineering.
• Sun Y, Long H. 2011. Adaptive detection of weft‐knitted fabric defects based on machine vision system. Journal of the Textile Institute 102(10), 823-836.
• W Wang, J Jiang. 2018. Computer Vision Techniques for detecting fabric defects. Applications of Computer Vision in Fashion and Textiles 47-60, Woodhead Publishing.
• J Yang, S Li, Z Wang. 2020. Using Deep Learning to Detect Defects in Manufacturing: A Comprehensive Survey and Current Challenges. Materials 13(24), 5755.
• MA Taher, MM Rahman, MA Jahangir. 2016. Study on Different Types of Knitting Faults, Causes and Remedies of Knit Fabrics. Int. J. of Textile Science 5(6), 119-131.
• RG Saeidi, M Latifi, SS Najar. 2005. Computer vision-aided fabric inspection system for on-circular knitting machine. Textile Research Journal 75(6), 492-497.
• AT Hemdan, MS Aya Tallah. 2008. Online fabric defect detection and full control in a circular knitting machine. AUTEX Research Journal l.8(1), 21-29.
• TK Torun, A Marmaralı. 2011. Online Fault Detection System for Circular Knitting Machines. Tekstil Ve Konfeksiyon 21(2), 164-170.
• L Yundang, A Jingxuan, S Changqing. 2013. Online Fabric Defect Inspection using Smart Visual Sensors. Sensors 13, 4659-4673.
• A. Şeker, KA Peker, AG Yüksek. 2016 May. Fabric defect detection using deep learning. In 24th Signal Processing and Communication Application Conference IEEE 1437-1440.
• S Takeuchi, K Nishioka, H Uematsu. 2018. Research into Development of the Defect Detection System for Knitted Fabric Produced by the Circular Knitting Machines by Image Analysis. Journal of Textile Engineering 64(2), 45-49.
• X Wang, G Wu, Y Zhong. 2018. Fabric Identification Using Convolutional Neural Network. Artificial Intelligence on Fashion and Textiles 93-100.
• K Hanbay, MF Talu, ÖF Özgüven. 2019. Real-Time Detection of Knitting Fabric Defects Using Shearlet Transform. Tekstil and Konfeksiyon 29(1), 3-10.
• K He, X Zhang, S Ren. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition 770-778.
• A Krizhevsky, I Sutskever, GE Hinton. 2012. Imagenet classification with deep convolutional neural networks. Advances in neural information processing system 25, 1097-1105.
• C Szegedy, W Liu, Y Jia. 2015. Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition 1-9.
• 2021, March. İstanbul Tekstil ve Hammaddeleri İhracatçıları Birliği 2021 March. Retrieved from http://www.ithib.org.trs