Automated part quality control system based on machine vision technology
DOI:
https://doi.org/10.34185/1562-9945-5-166-2026-14Keywords:
machine vision, automated visual inspection, quality control, digital image processing, PLC, OCR, Data Matrix, defect detection, machine vision systemAbstract
This paper addresses the development of an automated quality inspection system for industrial components based on machine vision technology intended for use in modern manufacturing environments. An analysis of the existing quality control process was carried out, identifying its main shortcomings associated with the significant influence of the human factor, excessive time required for inspection operations, the lack of centralized storage of inspection results, and insufficient repeatability of the obtained results. The feasibility of implementing an automated visual inspection system as a means of improving production efficiency and ensuring consistent product quality is substantiated.
The proposed system architecture includes a conveyor module, three inspection stations equipped with machine vision cameras, specialized lighting systems, an image processing module, a programmable logic controller (PLC), an automatic rejection mechanism, and a centralized database. The overall operating logic of the system has been developed to ensure synchronized interaction between all components, automatic image acquisition and processing, generation of inspection results, and transmission of control commands to actuating mechanisms in real time.
The paper provides a detailed description of the three inspection zones. The upper inspection zone is intended for checking power and auxiliary terminals, fastening and positioning elements, as well as detecting geometric deviations and mechanical defects. The front inspection zone performs verification of product markings, logos, the two–dimensional Data Matrix code, optical character recognition (OCR), and evaluation of selected geometric parameters. The lower inspection zone is designed to detect surface defects on the grounding plate using specialized illumination and digital image processing techniques to enhance defect contrast.
The proposed system provides comprehensive inspection of products without changing their spatial orientation, automatic decision–making regarding compliance with specified technical requirements, centralized storage of inspection results, and complete production traceability. The application of machine vision technology improves inspection accuracy and speed, minimizes the influence of the human factor, reduces the number of undetected defects, decreases production costs, and enhances the overall efficiency of automated manufacturing lines.
References
1. E.R. Davies, Machine Vision: Theory, Algorithms, Practicalities, 4th ed. Oxford, U.K.: Academic Press, 2012, 912 pp. [Online]. Available: https://www.sciencedirect.com/book/monograph/9780123869081/computer–and–machine–vision
2. M. Sonka, V. Hlavac, and R. Boyle, Image Processing, Analysis, and Machine Vision, 4th ed. Stamford, CT, USA: Cengage Learning, 2014, 944 pp. [Online]. Available: https://www.researchgate.net/publication/31734634_Image_Processing_Analysis_and_Machine_Vision_M_Sonka_V_Hlavac_R_Boyle
3. C. Steger, M. Ulrich, and C. Wiedemann, Machine Vision Algorithms and Applications. Weinheim, Germany: Wiley–VCH, 2018, 514 pp. [Online]. Available: https://www.researchgate.net/publication/322754740_Machine_Vision_Algorithms_and_Applications
4. R.C. Gonzalez and R. E. Woods, Digital Image Processing, 4th ed. Hoboken, NJ, USA: Pearson, 2018, 1024 pp. [Online]. Available: https://www.cl72.org/090imagePLib/books/Gonzales,Woods–Digital.Image.Processing.4th.Edition.pdf
5. A. Hornberg, Handbook of Machine and Computer Vision: The Guide for Developers and Users, 2nd ed. Weinheim, Germany: Wiley–VCH, 2017, 848 pp. [Online]. Available: https://soclibrary.futa.edu.ng/books/handbook–of–machine–and–computer–vision–the–guide–for–developers–and–users.9783527413393.78111.pdf
6. J. Beyerer, F. Puente León, and C. Frese, Machine Vision: Automated Visual Inspection—Theory, Practice and Applications. Berlin, Germany: Springer Vieweg, 2016, 788 pp. [Online]. Available: https://www.researchgate.net/publication/283882664_Machine_vision_Automated_visual_inspection_Theory_practice_and_applications
7. E.R. Fossum, “CMOS Image Sensors: Electronic Camera–on–a–Chip,” IEEE Transactions on Electron Devices, vol. 44, no. 10, pp. 1689–1698, Oct. 1997, doi: 10.1109/16.628824.
8. J. R. Janesick, Scientific Charge–Coupled Devices. Bellingham, WA, USA: SPIE Press, 2001, 906 pp. [Online]. Available: https://www.researchgate.net/publication/259263395_Scientific_Charge–Couple_Devices
9. Advanced Illumination, A Practical Guide to Machine Vision Lighting. Rochester, VT, USA: Advanced Illumination, 2018, 84 pp. [Online]. Available: https://www.advancedillumination.com/
10. CCS Inc., Machine Vision Lighting Handbook. Kyoto, Japan: CCS Inc., 2015, 96 pp. [Online]. Available: https://www.ccs–grp.com/
11. Opto Engineering, Telecentric Lenses and Illumination Systems Technical Guide. Man-tova, Italy: Opto Engineering, 2020, 132 pp. [Online]. Available: https://www.opto–e.com/
Downloads
Published
Issue
Section
License
Copyright (c) 2026 System technologies
This work is licensed under a Creative Commons Attribution 4.0 International License.
