Proceedings of the 8th International Conference on Applied Engineering (ICAE 2025)

<Previous Article In Volume
Next Article In Volume>

Optimizing Weld Defect Detection Enhancement in Non-Uniform Illumination Environments

Authors
Yonky Pernando1, *, Nur Afny Catur Andryani1, Andry Chowanda2, Widodo Budiarto2
1Computer Science Department, BINUS Graduate Program – Doctor of Computer Science, Bina Nusantara University, Jakarta, 11480, Indonesia
2Computer Science Department, School of Computer Science, Bina Nusantara University, Jakarta, 11480, Indonesia
*Corresponding author. Email: yonky.pernando@binus.ac.id
Corresponding Author
Yonky Pernando
Available Online 29 December 2025.
DOI
10.2991/978-94-6463-982-7_18How to use a DOI?
Keywords
Weld Defect Detection; CLAHE; YOLOv8n; Mobile Deployment; Computer vision
Abstract

Welded steel structures must be inspected reliably, yet visual inspection often fails under uneven lighting due to glare, shadows, and low contrast. We present a mobile weld-defect detection system that couples CLAHE-based local contrast enhancement with a YOLOv8 detector for robust, real-time inference in the field. Plat steel targets low-light and non-uniform illumination common in shipyards and construction sites, enabling on-device analysis We train on a weld dataset comprising three defect classes (crack, porosity, spatter) and augment it with samples acquired in a shipyard environment. Experiments show that CLAHE improves small-defect visibility and reduces false detections under challenging lighting, yielding mAP@0.5 = 0.8, and FPS = 6.8 on a mobile platform. Ablations isolate the contribution of CLAHE and quantify robustness across lighting conditions. The proposed approach demonstrates a practical path toward fast, portable, and accurate weld inspection under real-world illumination variability.

Copyright
© 2025 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)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the 8th International Conference on Applied Engineering (ICAE 2025)
Series
Advances in Engineering Research
Publication Date
29 December 2025
ISBN
978-94-6463-982-7
ISSN
2352-5401
DOI
10.2991/978-94-6463-982-7_18How to use a DOI?
Copyright
© 2025 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.

Cite this article

risenwbib
TY  - CONF
AU  - Yonky Pernando
AU  - Nur Afny Catur Andryani
AU  - Andry Chowanda
AU  - Widodo Budiarto
PY  - 2025
DA  - 2025/12/29
TI  - Optimizing Weld Defect Detection Enhancement in Non-Uniform Illumination Environments
BT  - Proceedings of the  8th International Conference on Applied Engineering (ICAE 2025)
PB  - Atlantis Press
SP  - 299
EP  - 313
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-982-7_18
DO  - 10.2991/978-94-6463-982-7_18
ID  - Pernando2025
ER  -