Colloquium announcement
Faculty of Engineering Technology
Department Design, Production and Management
Master programme Mechanical Engineering
As part of his / her master assignment
Freriks, K. (Koen)
will hold a speech entitled:
Weld defect classification using deep learning based on RGB and depth Images
| Date | 05-06-2025 |
| Time | 13:00 |
| Room | HT700A |
Summary
This thesis explores the use of deep learning for automated weld inspection, focusing on the classification of weld defects using combined RGB and depth images. Several convolutional neural network models were developed, each incorporating input modalities differently through unimodal, early fusion, or aggregated output strategies. A comparative study revealed that the fusion models significantly outperformed the unimodal models , with the early fusion model achieving 96.00% accuracy and the aggregated output model reaching 96.86%. These results demonstrate that integrating RGB and depth data enhances classification performance, supporting the reliability of such models for industrial weld inspection.
Assessment committee |
chair Signature d.d. |
|
| Prof.dr. I. Gibson Dr.ir. S. Arastehfar Dr.ing. S. Altnji J. Kampman |
(chair) (supervisor) (external member) (mentor from company) |
|