1. КК
  2. All Volumes and Issues
  3. № 1 (49) / 2026
  4. Machine Learning-Based Quality Control Systems in Print Production

Machine Learning-Based Quality Control Systems in Print Production

КК.
2026;
Volume № 1, Number 49
: pp. 121-131
ISSN: 2411-3611

https://doi.org/10.32403/2411-3611-2026-1-49-121-131
Received: March 01, 2026
Accepted: May 14, 2026
Published: May 20, 2026
Authors:
  1. V. V. Bernatsek
  2. T. V. Vladyka
  3. N. V. Vladyka
  4. R. P. Marchuk
1
Lviv Polytechnic National University Institute of Printing Art and Media Technologies
ORCID: 0000-0001-8955-1762
2
Lviv Polytechnic National University Institute of Printing Art and Media Technologies
ORCID: 0009-0006-4769-0303
3
Lviv Polytechnic National University Institute of Printing Art and Media Technologies
ORCID: 0009-0002-4808-9836
4
Lviv Polytechnic National University Institute of Printing Art and Media Technologies
ORCID: 0009-0008-1777-7488

The integration of machine learning technologies into print quality control systems represents a significant advancement in modern printing production. This article examines the application of artificial intelligence methods and computer vision algorithms for automated defect detection, colour consistency monitoring, and real-time quality assessment in printing processes. The study analyses current approaches to implementing neural networks, particularly convolutional neural networks (CNNs), for identifying various types of printing defects including misregistration, colour deviation, streaking, and substrate irregularities. Special attention is given to the development of information models that describe the interaction between quality control subsystems, production workflow, and decision-making mechanisms. The research demonstrates that machine learning-based systems can achieve defect detection accuracy exceeding 95%, significantly reducing material waste and improving overall production efficiency. The article presents a comprehensive analysis of existing solutions, identifies key challenges in implementing intelligent quality control systems, and proposes directions for future research. The findings indicate that hybrid approaches combining traditional image processing techniques with deep learning methods show the most promising results for industrial applications. The practical significance of this work lies in providing a systematic framework for developing and implementing automated quality control systems in printing enterprises

machine learning
print quality control
computer vision
convolutional neural networks
defect detection
information technologies
automated inspection systems
deep learning
  1. Masod M. Y., Zakaria S. F. Artificial Intelligence in the Printing Industry: ASystematic Review of Industrial Applications, Challenges and Benefits. International Journal of Research and Innovation in Social Science. 2024. P. 1713–1732.
  2. Deep learning for industrial computer vision quality control in the printing industry 4.0 /J. Villalba-Diez et al. Sensors. 2019. Vol. 19, No. 18. Art. No. 3987. DOI: https://doi.org/ 10.3390/s19183987.
  3. A deep learning based printing defect classification method with imbalanced samples /E. Zhang et al. Symmetry. 2019. Vol. 11, No. 12. Art. No. 1440. DOI: https://doi.org/10.3390/ sym11121440.
  4. A novel inspection system for variable data printing using deep learning / O. Haik et al. Proceedings of the IEEE/CVF winter conference on applications of computer vision. 2020. P. 3541–3550.
  5. A hybrid deep learning approach to automate industrial quality control / K. Vinod et al. Inter- national Journal of Computer Integrated Manufacturing. 2025. P. 1–21. DOI: https://doi.org/ 10.1080/0951192X.2024.2449886.
  6. Bhandarkar V. V., Karnati M., Tandon P. Real-time layer-by-layer defects detection in 3D-printed multi-geometry polymer components using deep learning. Measurement. 2026. Art. No. 120332. DOI: https://doi.org/10.1016/j.measurement.2024.120332.
  7. Defect detection in 3D printing: A review of image processing and machine vision techni- ques / E. Armin et al. The International Journal of Advanced Manufacturing Technology. 2025. Vol. 140, No. 3. P. 2103–2128. DOI: https://doi.org/10.1007/s00170-025-14958-1.
  8. Selot A., Dwivedi R. K. Machine learning and sensor-based approach for defect detection in MEX additive manufacturing process-A Review. Journal of the Brazilian Society of Me- chanical Sciences and Engineering. 2023. Vol. 45, No. 10. Art. No. 535. DOI: https://doi. org/10.1007/s40430-023-04444-2.
  9. Ling Q., Isa N. A. M. Printed circuit board defect detection methods based on image proces- sing, machine learning and deep learning: A survey. IEEE Access. 2023. Vol. 11. P. 15921– 15944. DOI: https://doi.org/10.1109/ACCESS.2023.3245093.
  10. Deep residual learning for image recognition / K. He et al. Proceedings of the IEEE conference on computer vision and pattern recognition. 2016. P. 770–778. DOI: https://doi.org/10.1109/ CVPR.2016.90.
  11. Tan M., Le Q. EfficientNet: Rethinking model scaling for convolutional neural networks. International conference on machine learning. 2019. P. 6105–6114.
  12. You only look once: Unified, real-time object detection / J. Redmon et al. Proceedings of the IEEE conference on computer vision and pattern recognition. 2016. P. 779–788. DOI: https:// doi.org/10.1109/CVPR.2016.91.
  13. Ronneberger O., Fischer P., Brox T. U-net: Convolutional networks for biomedical image seg- mentation. Medical image computing and computer-assisted intervention. 2015. P. 234–241. DOI: https://doi.org/10.1007/978-3-319-24574-4_28.
  14. VGG-16 | CNN model. GeeksforGeeks. 2025. URL: https://www.geeksforgeeks.org/compu- ter-vision/vgg-16-cnn-model/ (дата звернення: 19.01.2026).