Role of Image Processing Techniques for Extracting Features in NDE Weld Images

DOI

10.2991/978-94-6239-750-7_66How to use a DOI?

Keywords

Non-destructive evaluation; Non-destructive testing; Weld images; image processing; feature extraction

Abstract

Non-destructive evaluation (NDE) is a cornerstone of quality assurance in high-stakes industries such as aerospace, automotive, and infrastructure, where the structural integrity of welded components is paramount. Traditional inspection methods, while effective, often rely heavily on the subjective interpretation of human inspectors, leading to inconsistencies and potential oversight. This paper investigates the application of digital image processing techniques to automate and enhance the detection of flaws in weld images acquired through ultrasonic and X-ray modalities. By synthesizing methodologies ranging from fundamental edge detection to advanced texture analysis and Artificial Neural Networks (ANN), this research delineates a robust framework for feature extraction. The findings indicate that automated feature extraction not only improves the reliability of defect detection but also significantly reduces the cycle time required for inspection, paving the way for intelligent, real-time NDE systems. A comparative analysis across 12 samples shows image processing results align closer to radiographic findings than ultrasonic testing, with measurement accuracies within 2% of destructive verification. Automated feature extraction reduces inspection cycle time while improving reliability over traditional subjective methods.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Pankaj Pratap Singh
AU  - Vijay R. Rathod
AU  - Varun Singh Chauhan
PY  - 2026
DA  - 2026/08/31
TI  - Role of Image Processing Techniques for Extracting Features in NDE Weld Images
BT  - Proceedings of the International Conference on Advanced Design, Manufacturing, and Sustainable Energy Systems (ICADMSES 2026)
PB  - Atlantis Press
SP  - 921
EP  - 932
SN  - 2589-4943
UR  - https://doi.org/10.2991/978-94-6239-750-7_66
DO  - 10.2991/978-94-6239-750-7_66
ID  - Singh2026
ER  -