Authors : Akramul Hoque Tamgid; Yihong Zhang; Sumonta Ghosh; Rony Shaha; Md Ahasan Habib Tushar

Volume/Issue : Volume 11 - 2026, Issue 5 - May

Google Scholar : https://tinyurl.com/4nvtew9h

Scribd : https://tinyurl.com/4x36ty4t

DOI : https://doi.org/10.38124/ijisrt/26May1881

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : The integration of robotics and artificial intelligence (AI) is revolutionizing the textile industry by overcoming the constraints of conventional fabric fault inspection during production, which is labor-intensive, prone to errors, and timeconsuming. Production efficiency, occupational safety, and environmental sustainability are all improved by automated defect identification that makes use of AI and safe human-robot interaction (HRI). To keep product quality and reduce waste, it is essential to use fabrics free of defects. Discarded defective materials cause substantial economic losses. Deep learning models powered by artificial intelligence provide a quicker and more accurate substitute for traditional manual inspection in real-time quality control. This research utilizes numerous authentic datasets obtained directly from Chenab Textiles, representing actual manufacturing conditions. An efficient YOLOv8 model was developed to detect flaws in seven different types of cloth as it achieved an average accuracy of 84.8%, a precision of 0.818, and a recall of 0.839. Comparative assessments utilizing MobileNetV2-SSD FPN-Lite revealed YOLOv8's enhanced performance regarding speed and accuracy. The findings highlight the model's resilience and capacity for scalable, real-time fault identification, even across varied conditions of plain and printed textiles. This study enhances automated quality control in the textile sector, facilitating sustainable and economical production methods that meet contemporary industrial requirements.

Keywords : Fabric Defect, YOLOv8, SSDMobilenet, Human-Robot Interaction, Industry 5.0

References :

1. FELSBERGER A, QAISER F H, CHOUDHARY A, et al. The impact of Industry 4.0 on the reconciliation of dynamic capabilities: Evidence from the European manufacturing industries [J]. Production Planning & Control, 2022, 33(2-3): 277-300.
2. GLOY Y-S. Industry 4.0 in textile production [M]. Springer, 2021.
3. WEIß M, TILEBEIN M, GEBHARDT R, et al. Smart Factory Modelling for SME: Modelling the Textile Factory of the Future; proceedings of the International Symposium on Business Modeling and Software Design, F, 2018 [C]. Springer.
4. ESTEVA A, KUPREL B, NOVOA R A, et al. Dermatologist-level classification of skin cancer with deep neural networks [J]. nature, 2017, 542(7639): 115-8.
5. DAL FORNO A J, BATAGLINI W V, STEFFENS F, et al. Industry 4.0 in textile and apparel sector: a systematic literature review [J]. Research Journal of Textile and Apparel, 2023, 27(1): 95-117.
6. SINGH P, KARPAVICE J, BELIATIS M, et al. Digital dataspace and business ecosystem growth for industrial roll-to-roll label printing manufacturing: A case study [J]. Thinkmind Digital Library: Lisbon, Portugal, 2023.
7. JIA Z, SHI Z, QUAN Z, et al. Fabric defect detection based on transfer learning and improved Faster R-CNN [J]. Journal of engineered fibers and fabrics, 2022, 17: 15589250221086647.
8. BURRA L R, KARUNA A, TUMMA S, et al. MobileNetV2-based transfer learning model with edge computing for automatic fabric defect detection [J]. Journal of Scientific & Industrial Research, 2022, 82(1): 128-34.
9. NASIM M, MUMTAZ R, AHMAD M, et al. Fabric defect detection in real world manufacturing using deep learning [J]. Information, 2024, 15(8): 476.
10. LYSTBÆK M, GIANNAKIDIS A, BELIATIS M J, et al. Removing unwanted text from architectural images with multi-scale deformable attention-based machine learning; proceedings of the 2023 IEEE International Conference on Imaging Systems and Techniques (IST), F, 2023 [C]. IEEE.
11. NG W, MINASNY B, MCBRATNEY A. Convolutional neural network for soil microplastic contamination screening using infrared spectroscopy [J]. Science of the Total Environment, 2020, 702: 134723.
12. HASSAN S A, KHALIL M A, AULETTA F, et al. Contamination detection using a deep convolutional neural network with safe machine—environment interaction [J]. Electronics, 2023, 12(20): 4260.
13. WANG Y-X, ZOU J-Y, HU L-F, et al. Yue [J]. Q-q, 2019.
14. ZHANG H-W, ZHANG L-J, LI P-F, et al. Yarn-dyed fabric defect detection with YOLOV2 based on deep convolution neural networks; proceedings of the 2018 IEEE 7th data driven control and learning systems conference (DDCLS), F, 2018 [C]. IEEE.
15. GAO Y, GAO L, LI X. A hierarchical training-convolutional neural network with feature alignment for steel surface defect recognition [J]. Robotics and Computer-Integrated Manufacturing, 2023, 81: 102507.
16. LI C, LI J, LI Y, et al. Fabric defect detection in textile manufacturing: a survey of the state of the art [J]. Security and Communication Networks, 2021, 2021(1): 9948808.
17. TSAI I-S, HU M-C. Automatic inspection of fabric defects using an artificial neural network technique [J]. Textile Research Journal, 1996, 66(7): 474-82.
18. GERMANY D F. Tilda textile texture-database [J]. Database, 1996.
19. SURANA A, LYNCH M E, NASSAR A R, et al. Flaw detection in multi-laser powder bed fusion using in situ coaxial multi-spectral sensing and deep learning [J]. Journal of Manufacturing Science and Engineering, 2023, 145(5): 051005.
20. WANG J, GAO P, ZHANG J, et al. Knowledge augmented broad learning system for computer vision based mixed-type defect detection in semiconductor manufacturing [J]. Robotics and Computer-Integrated Manufacturing, 2023, 81: 102513.
21. IWAHORI Y, TAKADA Y, SHIINA T, et al. Defect classification of electronic board using dense SIFT and CNN [J]. Procedia Computer Science, 2018, 126: 1673-82.
22. MONTALBO F J P. A computer-aided diagnosis of brain tumors using a fine-tuned YOLO-based model with transfer learning [J]. KSII Transactions on Internet and Information Systems (TIIS), 2020, 14(12): 4816-34.
23. GIRSHICK R. Fast r-cnn; proceedings of the Proceedings of the IEEE international conference on computer vision, F, 2015 [C].