A New Approach to Non-Destructive Testing Using OpenCV-Based Image Processing

Abstract

This study investigates the potential of image processing techniques to improve quality control processes in welding and to enable the effective detection of defects. Given the inherent human errors and time-consuming nature of traditional quality control methods, image processing technologies emerge as an automated and highly precise alternative. In this context, the OpenCV library was utilized to analyze defects in weld seams and their geometric properties. Reference points were established on images using a two-point laser system to facilitate high-accuracy measurements on planar surfaces. Through the implementation of image processing techniques such as edge detection and contour analysis, welding defects were automatically identified, yielding results that are fasters.

Keywords

• Weld quality
• Image processing
• OpenCV
• Non-destructive testing
• Weld defects
• Point laser

References

1. Ajmi C, Zapata J, Elferchichi S, Laabidi K. 2024. Advanced faster-rcnn model for automated recognition and detection of weld defects on limited x-ray image dataset. J Nondestruct Eval, 43(1): 14.
2. Akkus A, Gorgun E. 2015. The investigation of mechanical behaviors of poly methyl methacrylate (PMMA) with the addition of bone ash, hydroxyapatite and keratin. Adv Mater, 4(1): 16–19.
3. Cardellicchio A, Nitti M, Patruno C, Mosca N, Di Summa M, Stella E, Renò V. 2024. Automatic quality control of aluminium parts welds based on 3D data and artificial intelligence. J Intell Manuf, 35(4): 1629–1648.
4. Gook S, El-Sari B, Biegler M, Rethmeier M. 2024. Application of AI-based welding process monitoring for quality control in pipe production. Paton Weld J, 2024(6).
5. Gorgun E. 2022. Characterization of superalloys by artificial neural network method. Int Symp Appl Math Eng (ISAME22), January 21-23, 2022, Istanbul, Türkiye, pp: 67.
6. Gorgun E. 2024. Investigation of the effect of SMAW parameters on properties of AH36 joints and the chemical composition of seawater. Int J Innov Eng Appl, 8(1): 28–36.
7. Gorgun E. 2024. Numerical analysis of inflow turbulence intensity impact on the stress and fatigue life of vertical axis hydrokinetic turbine. Phys Fluids, 36(1).
8. Gorgun E, Karamis MB. 2019. Ultrasonic testing to measure the stress statement of steel parts. J Mech Sci Technol, 33(7): 3231–3236.

9. Guo Q, Yang Z, Xu J, Jiang Y, Wang W, Liu Z, Zhao W, Sun Y. 2024. Progress, challenges and trends on vision sensing technologies in automatic/intelligent robotic welding: State-of-the-art review. Robot Comput Integr Manuf, 89: 102767.
10. Islam MR, Zamil MZH, Rayed ME, Kabir MM, Mridha MF, Nishimura S, Shin. 2024. Deep learning and computer vision techniques for enhanced quality control. IEEE Access, Manuf Process, Seoul, South Korea, pp:52-60.
11. Ji W, Luo Z, Luo K, Shi X, Li P, Yu Z. 2024. Computer vision–based surface defect identification method for weld images. Mater Lett, 371: 136972.
12. Liu W, Hu J, Qi J. 2025. Resistance spot welding defect detection based on visual inspection. Improved Faster R-CNN model. Machines, 13(1): 33.
13. Lopez-Fuster MA, Morgado-Estevez A, Diaz-Cano I, Badesa FJ. 2024. A neural-network-based cost-effective method for initial weld point extraction from 2D images. Machines, 12(7): 447.
14. Mobaraki M. 2025. Vision-based seam tracking and multi-modal defect detection in GMAW fillet welding using artificial intelligence. PhD Thesis, University of British Columbia, pp: 45-49.
15. Pham DA, Bui DQ, Le TD, Tran DH, Nguyen TH. 2024. Automatic welding seam tracking and real-world coordinates identification with machine learning method. Results Eng, 23: 102565.
16. Stavropoulos P, Sabatakakis K. 2024. Quality assurance in resistance spot welding: state of practice, state of the art, and prospects. Metals, 14(2): 185.
17. Sutherland C, Henderson AD, Giosio DR, Trotter AJ, Smith GG. 2024. Synchronising an IMX219 image sensor and AS7265x spectral sensor to make a novel low-cost spectral camera. HardwareX, 19: e00573.
18. Voelkel J, Meissner M, Bartsch H, Feldmann M. 2024. The influence of external weld imperfection size on the load-bearing capacity of butt-welded joints. J Constr Steel Res, 220: 108808.
19. Wang Y, Lee W, Jang S, Truong VD, Jeong Y, Won C, Lee J, Yoon J. 2024. Prediction of internal welding penetration based on IR thermal image supported by machine vision and ANN-model during automatic robot welding process. J Adv Join Process, 9: 100199.
20. Xu J, Hu X, Zhan H. 2025. CU-NET: Context extractor network based U-Net for magnetic tile segmentation. In: Proc Int Conf Equip Intell Oper Maint (ICEIOM 2023), Hefei, China, Sep 21–23, 2023 (Vol II). CRC Press: 155.
21. Yu Q, Xiao L, Zheng D, Peng Z, Song K. 2024. A computer vision-based lithium battery tab welding quality detection system. Trans China Weld Inst, 45(10): 38–49.
22. Yue Y. 2024. Research on welding seam detection and recognition technology for industrial boilers. Proc 2024 IEEE 7th Inf Technol Netw Electron Autom Control Conf (ITNEC): IEEE: 413–416.
23. Zhang B, Wang X, Cui J, Wu J, Xiong Z, Zhang W, Yu X. 2024. Enhancing weld inspection through comparative analysis of traditional algorithms and deep learning approaches. J Nondestruct Eval, 43(2): 38.