Detection of Weld Defect Images in Radiographs Under Conditions of Limited Information on Control Sensitivity
Source abstract
Abstract
Abstract This article is devoted to improving the efficiency of segmentation of radiographic images of welded joints. The article presents an algorithm for defect image segmentation, which is performed in two stages: determination of an array of thresholds for detecting defect image pixels (various detection thresholds for defect image pixels located in areas of digital radiographic images of welded joints with characteristic brightness distribution and background brightness estimation errors) on the background sample based on the criterion of avoiding the detection of “false” defect images, and the actual search for defect images. The experimental results confirm the applicability of the developed algorithm for effective detection of defect images in radiographic images of welded joints without the use of reference sensitivity standards.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Welding Techniques and Residual Stresses · Surface Treatment and Coatings · Industrial Engineering and Technologies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (29)
Show source-provided references
1. Gonzalez, R. and Woods, R., Digital Image Processing, New York: Pearson, 2018, 4th ed.
2. Kosarina, E.I., Demidov, A.A., Krupnina, O.A., Mikhailova, N.A., Smirnov, A.V., and Osyanenko, N.V., Nerazrushayushchii kontrol’ s pomoshch’yu tsifrovoi rentgenografii i rentgenovskoi komp’yuternoi tomografii (Nondestructive Testing by Digital Radiography and X-Ray Computed Tomography), Moscow: Spektr, 2025.
3. Kapustin, V.I., Zuev, V.M., Ivanov, V.I., and Dub, A.V., Informatsionnye aspekty radiograficheskogo kontrolya (Radiographic Inspection Information Aspects), Moscow: Nauchtekhizdat, 2010.
4. NP-105-18: Rules for Metal Control of Equipment and Pipelines of Nuclear Power Plants During Manufacture and Installation.
5. GOST (State Standard) ISO 17636-2-2017: Nondestructive Testing of Welded Joints. Radiographic Testing, part 2: Methods of X-ray and Gamma-Ray Testing Using Digital Detectors.
6. GOST (State Standard) ISO 110893-7-2021: Steel Pipes, part 7: Digital Radiographic Inspection of Welds for Defect Detection.
7. GOST (State Standard) R ISO 19232-1-2024: Nondestructive Testing. Image Quality in Radiographic Images, part 1: Determination of Image Quality Indicator Values Using Wire-Type Image Quality Indicators.
8. GOST (State Standard) 23055-78: Nondestructive Testing. Fusion Welding of Metals. Weld Classification by Radiography Testing Results.
9. STO Gazprom 2-2.4-917-2014: Instructions for Radiographic Quality Control of Welded Joints During the Construction and Repair of Field and Main Pipelines.
10. The official website of the Newcom-NDT company. X-Vizor: SOFTWARE for digital and computer radiography. 2024. https://newcom-ndt.ru/x-vizor. Accessed August 26, 2025.
11. Grudsky, A.Ya. and Velichko, V.Ya., Digitization of radiographic images is not very easy, V Mire NK, 2011, no. 4 (54), pp. 74–76.
12. Grigorchenko, S.A., Search for radiographic images of defects. Problem statement, Kontrol’ Diagn., 2012, no. 10, pp. 61–64.
13. Grigorchenko, S.A. and Efimenko, L.A., Software for the automated decoding of radiographic images, Kontrol’ Diagn., 2007, no. 12, pp. 26–29.
14. Grigorchenko, S.A., Automated assessment of the quality of welded joints according to the parameters of radiographic images of flaws, Kontrol’ Diagn., 2009, no. 10, pp. 30–36.
15. Grigorchenko, S.A. and Efimenko, L.A., Automation of computer interpretation of radiation images of welded joints, Russ. J. Nondestr. Test., 2015, vol. 51, no. 1, pp. 17–21.10.1134/S1061830915010039 ↗
16. Nazarenko, S.Yu. and Udod, V.A., Application of artificial neural networks in radiation nondestructive testing, Defektoskopiya, 2019, no. 6, pp. 53–64.
17. Grigorchenko, S.A. and Kapustin, V.I., Classification of defects in computerized radiographic testing of weldss, Russ. J. Nondestr. Test., 2009, vol. 45, no. 9, pp. 658–659.10.1134/S1061830909090095 ↗
18. Vorobeichikov, S.E., Fokin, V.A., Udod, V.A., and Temnik, A.K., A study of two image-recognition algorithms for the classification of flaws in a test object according to its digital image, Russ. J. Nondestr. Test., 2015, vol. 51, no. 10, pp. 644–651.10.1134/S1061830915100101 ↗
19. Vorobeichikov, S.E., Fokin, V.A., Udod, V.A., and Temnik, A.K., Estimating the efficiency of two algorithms for segmentation of digital radiation images of test objects, Russ. J. Nondestr. Test., 2017, vol. 53, no. 2, pp. 134–141.10.1134/S1061830917020085 ↗
20. Grigorchenko, S.A. and Ukolov, I.A., Determination of the background in the problem of searching for radiographic images of defects, Truboprovodn. Transp.: Teor. Prakt., 2012, no. 2 (30), pp. 14–17.
21. Kosarina, E.I., Krupnina, O.A., Demidov, A.A., and Mikhailova, N.A., Digital optical pattern and its dependence on the radiation image in nondestructive testing by the digital radiography method, Aviats. Mater. Tekhnol., 2019, no. 1 (54), pp. 37–42. https://doi.org/10.18577/2071-9140-2019-0-1-37-4210.18577/2071-9140-2019-0-1-37-42 ↗
22. Grigorchenko, S.A. and Kapustin, O.E., On the issue of detecting radiographic images of defects in welded joints, Svarka Diagn., 2023, no. 5, pp. 17–19.
23. Bardin, B.V., Research of the possibilities of median filtering in digital processing of images of sets of local biological objects, Nauchn. Priborostr., 2011, vol. 21, no. 2, pp. 120–125.
24. Bardin, B.V., A fast algorithm for median filtering, Nauchn. Priborostr., 2011, vol. 21, no. 3, pp. 135–139.
25. Liu, T., Zheng, P., Bao, J., and Chen, H., A state-of-the-art survey of welding radiographic image analysis: Challenges, technologies and applications, Measurement, 2023, vol. 214, p. 112821. https://doi.org/10.1016/j.measurement.2023.11282110.1016/j.measurement.2023.112821 ↗
26. Say, D., Zidi, S., Qaisar, S.M., and Krichen, M., Automated categorization of multiclass welding defects using the X-ray image augmentation and convolutional neural network, Sensors, 2023, vol. 23, p. 6422. https://doi.org/10.3390/s2314642210.3390/s23146422 ↗
27. Zhao, S., Long, L., An, D., Wang, Y., Zhang, H., Liang, H., and Jin, S., Design and realization of nondestructive testing information management system for shell electron beam welds, Software Eng. Appl., 2022, vol. 11, no. 5, pp. 1005–1016. https://doi.org/10.12677/SEA.2022.11510310.12677/SEA.2022.115103 ↗
28. Harrouche, S., Nacereddine, N., and Goumeidane, A.B., A comparative study of different cnn models using transfer learning for weld defect classification in radiographic testing, Proc. of the 4th Int. Conf. on Electrical, Communication and Computer Engineering, Dubai, 2023. https://doi.org/10.1109/ICECCE61019.2023.1044205710.1109/ICECCE61019.2023.10442057 ↗
29. Verbeek, P.W., Vrooman, H.A., and Van Vliet, L.J., Low-level image processing by max-min filters, Signal Process., 1988, vol. 15, no. 3, pp. 249–258. https://doi.org/10.1016/0165-1684(88)90015-110.1016/0165-1684(88)90015-1 ↗