Computer Vision-Based Detection and Classification of Welding Defects

DOI

10.2991/978-94-6239-616-6_90How to use a DOI?

Keywords

Weld quality inspection; YOLOv8n; deep learning; automated defect detection

Abstract

Weld quality inspection is vital for ensuring industrial safety and manufacturing reliability, but traditional manual inspection methods are limited by subjectivity, time, and cost. To address these limitations, this paper proposes an automated, real-time solution for weld defect detection and classification using the YOLOv8n deep learning model. The methodology utilizes a dataset of 2953 images for training, validation, and testing. The trained model achieved a mean Average Precision (mAP@0.5) of 98.1% and an inference speed of 4 ms, showing high accuracy and real-time capability. These results establish YOLOv8n as a highly effective and efficient solution for automated weld inspection, offering a practical and scalable alternative to manual processes.

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  - Chinthakuntla Meghan Sai
AU  - Murarisetty V. Sai Kartheek
AU  - Sita Devi Bharatula
AU  - Sunil Kumar
PY  - 2026
DA  - 2026/03/31
TI  - Computer Vision-Based Detection and Classification of Welding Defects
BT  - Proceedings of the International Conference on Artificial Intelligence and Secure Data Analytics (ICAISDA 2025)
PB  - Atlantis Press
SP  - 1225
EP  - 1235
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-616-6_90
DO  - 10.2991/978-94-6239-616-6_90
ID  - Sai2026
ER  -