Ensuring consistent mesh geometry is essential for mechanical reliability and quality control of knotted nets in factory production line inspections. This paper presents a fully automated visual inspection system that integrates knot detection, mesh topology reconstruction, and real-world dimensional measurements within a distortion-aware deep learning framework. The knots were detected using a YOLOv11-based object detector trained to localize small and densely arranged targets under varying illumination, deformation, and partial occlusion. To enable accurate metric measurements over large net areas, the images captured using a 150° ultrawide-angle lens were rectified through camera calibration and distortion correction. Knot centroids were extracted from the detected bounding boxes and organized using a row-wise directional linking strategy that reconstructed a diamond-shaped mesh topology while avoiding physically implausible connections. Interknot distances were computed in the rectified image plane and converted into real-world measurements using a K-nearest neighbors (KNN) regression model, which compensated for the residual nonlinearities remaining after distortion correction. The scope of inspection in this study was limited to mesh size and knot spacing evaluation. However, missing knots, broken strands, or other structural defects may affect the dimensional consistency of the net and may be indicated indirectly through abnormal mesh measurements. The proposed system is not intended for direct detection or classification of such defects. It was evaluated on a custom dataset of 1,054 industrial fishing net images, achieving a high detection performance with an mAP50 of 0.99 and mAP50–95 of 0.86. The calibration stage achieved distance estimation errors within ±3.53% relative to the nominal mesh size. The results demonstrated that the proposed approach enabled the automated and quantitative assessment of mesh uniformity, providing a practical and scalable solution for industrial net quality inspection.

1. [1] L. Liu and P. Ma, “Review on the performances and applications of mesh-fabrics,” J. Ind. Text., Vol.52, 2022. https://doi.org/10.1177/15280837221136292
2. [2] Y. Wu, Y. Duan, Y. Wei, D. An, and J. Liu, “Application of intelligent and unmanned equipment in aquaculture: A review,” Comput. Electron. Agric., Vol.199, Article No.107201, 2022. https://doi.org/10.1016/j.compag.2022.107201
3. [3] J. Atalah and P. Sanchez-Jerez, “Global assessment of ecological risks associated with farmed fish escapes,” Glob. Ecol. Conserv., Vol.21, Article No.e00842, 2020. https://doi.org/10.1016/j.gecco.2019.e00842
4. [4] Ø. Jensen, T. Dempster, E. B. Thorstad, I. Uglem, and A. Fredheim, “Escapes of fishes from Norwegian sea-cage aquaculture: Causes, consequences and prevention,” Aquac. Environ. Interact., Vol.1, pp. 71-83, 2010. https://doi.org/10.3354/aei00008
5. [5] K. Slater, “Yarn evenness,” Text. Prog., Vol.14, Nos.3-4, pp. 1-90, 1986. https://doi.org/10.1080/00405168608688901
6. [6] K. Srinivasan, P. H. Dastoor, P. Radhakrishnaiah, and S. Jayaraman, “FDAS: A knowledge-based framework for analysis of defects in woven textile structures,” J. Text. Inst., Vol.83, No.3, pp. 431-448, 1992. https://doi.org/10.1080/00405009208631217
7. [7] R. Shamey and T. Hussein, “Critical solutions in the dyeing of cotton textile materials,” Text. Prog., Vol.37, Nos.1-2, pp. 1-84, 2005. https://doi.org/10.1533/tepr.2005.0001
8. [8] W. Qin, “On-line yarn evenness detection using CCD image sensor,” Proc. 2011 Chin. Control Decis. Conf. (CCDC), pp. 1787-1790, 2011. https://doi.org/10.1109/CCDC.2011.5968487
9. [9] N. Gonçalves, V. Carvalho, F. Soares, and R. Vasconcelos, “Studies on the yarn mass parameters determination using Image Processing techniques,” Proc. 2012 IEEE 17th Int. Conf. Emerg. Technol. Fact. Autom. (ETFA), 2012. https://doi.org/10.1109/ETFA.2012.6489765
10. [10] P. Zhong et al., “Evaluation method for yarn diameter unevenness based on image sequence processing,” Text. Res. J., Vol.85, No.4, pp. 369-379, 2015. https://doi.org/10.1177/0040517514547211
11. [11] R. Pinto, F. Pereira, V. Carvalho, F. Soares, and R. Vasconcelos, “Yarn linear mass determination using image processing: First insights,” Proc. 45th Annu. Conf. IEEE Ind. Electron. Soc. (IECON), pp. 198-203, 2019. https://doi.org/10.1109/IECON.2019.8926650
12. [12] M. M. Khodier, S. M. Ahmed, and M. S. Sayed, “Complex pattern jacquard fabrics defect detection using convolutional neural networks and multispectral imaging,” IEEE Access, Vol.10, pp. 10653-10660, 2022. https://doi.org/10.1109/ACCESS.2022.3144843
13. [13] J. Redmon and A. Farhadi, “YOLOv3: An incremental improvement,” arXiv:1804.02767, 2018. https://doi.org/10.48550/arXiv.1804.02767
14. [14] Y. Li, Z. Zhou, and Y. Pan, “YOLOv11-BSS: Damaged region recognition based on spatial and channel synergistic attention and bi-deformable convolution in sanding scenarios,” Electronics, Vol.14, No.7, Article No.1469, 2025. https://doi.org/10.3390/electronics14071469
15. [15] D. Wang et al., “SDS-YOLO: An improved vibratory position detection algorithm based on YOLOv11,” Measurement, Vol.244, Article No.116518, 2025. https://doi.org/10.1016/j.measurement.2024.116518
16. [16] R. Khanam and M. Hussain, “YOLOv11: An overview of the key architectural enhancements,” arXiv:2410.17725, 2024. https://doi.org/10.48550/arXiv.2410.17725
17. [17] D. Schneider, E. Schwalbe, and H.-G. Maas, “Validation of geometric models for fisheye lenses,” ISPRS J. Photogramm. Remote Sens., Vol.64, No.3, pp. 259-266, 2009. https://doi.org/10.1016/j.isprsjprs.2009.01.001
18. [18] P. Hansen, H. Alismail, P. Rander, and B. Browning, “Visual mapping for natural gas pipe inspection,” Int. J. Robot. Res., Vol.34, Nos.4-5, pp. 532-558, 2015. https://doi.org/10.1177/0278364914550133
19. [19] Z. Zhang, “A flexible new technique for camera calibration,” IEEE Trans. Pattern Anal. Mach. Intell., Vol.22, No.11, pp. 1330-1334, 2000. https://doi.org/10.1109/34.888718
20. [20] OpenCV, “Camera calibration and 3D reconstruction,” 2026. https://docs.opencv.org/4.x/d9/d0c/group__calib3d.html [Accessed January 28, 2026]
21. [21] strawberry, “Amita Knot Detection (box) Dataset,” 2025. https://universe.roboflow.com/strawberry-kc79b/amita-knot-detection-box-rbhkc [Accessed January 28, 2026]
22. [22] J. Rong, H. Zhou, F. Zhang, T. Yuan, and P. Wang, “Tomato cluster detection and counting using improved YOLOv5 based on RGB-D fusion,” Comput. Electron. Agric., Vol.207, Article No.107741, 2023. https://doi.org/10.1016/j.compag.2023.107741
23. [23] Z. Liu, G. Gao, L. Sun, and Z. Fang, “HRDNet: High-resolution detection network for small objects,” arXiv:2006.07607, 2020. https://doi.org/10.48550/arXiv.2006.07607
24. [24] M. H. Noor Akashah, H. P. Nguyen, and N. Uchiyama, “Strawberry detection and weight estimation using YOLO and K-nearest neighbors regression model,” Sens. Actuators A: Phys., Vol.394, Article No.116890, 2025. https://doi.org/10.1016/j.sna.2025.116890
25. [25] M. H. N. Akashah, M. Yamamoto, and N. Uchiyama, “A vision-based measurement framework with optimized K-nearest neighbor regression for net mesh size control,” Proc. 2026 IEEE 19th Int. Conf. Adv. Motion Control (AMC), 2026. https://doi.org/10.1109/AMC67705.2026.11435829
26. [26] M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman, “The PASCAL Visual Object Classes (VOC) challenge,” Int. J. Comput. Vis., Vol.88, No.2, pp. 303-338, 2010. https://doi.org/10.1007/s11263-009-0275-4
27. [27] T.-Y. Lin et al., “Microsoft COCO: Common objects in context,” Proc. 13th Eur. Conf. Comput. Vis. (ECCV), Part 5, pp. 740-755, 2014. https://doi.org/10.1007/978-3-319-10602-1_48
28. [28] N. S. Altman, “An introduction to kernel and nearest-neighbor nonparametric regression,” Am. Stat., Vol.46, No.3, pp. 175-185, 1992. https://doi.org/10.1080/00031305.1992.10475879
29. [29] S. Chan, X. Zhou, C. Huang, S. Chen, and Y. F. Li, “An improved method for fisheye camera calibration and distortion correction,” Proc. 2016 Int. Conf. Adv. Robot. Mechatron. (ICARM), pp. 579-584, 2016. https://doi.org/10.1109/ICARM.2016.7606985
30. [30] X. Yue, Q. Wang, L. He, Y. Li, and D. Tang, “Research on tiny target detection technology of fabric defects based on improved YOLO,” Appl. Sci., Vol.12, No.13, Article No.6823, 2022. https://doi.org/10.3390/app12136823
31. [31] A. Kumar and G. K. H. Pang, “Fabric defect segmentation using multichannel blob detectors,” Opt. Eng., Vol.39, No.12, pp. 3176-3190, 2000. https://doi.org/10.1117/1.1327837
32. [32] X. Gong, J. Yu, H. Zhang, and X. Dong, “AED-YOLO11: A small object detection model based on YOLO11,” Digit. Signal Process., Vol.166, Article No.105411, 2025. https://doi.org/10.1016/j.dsp.2025.105411
33. [33] L. Liu and Z. Xu, “Optimizing lightweight neural networks for efficient mobile edge computing,” Sci. Rep., Vol.15, Article No.22056, 2025. https://doi.org/10.1038/s41598-025-04652-7