An Automated Vision-Based Inspection System for Metallic Lock Surface Defects Using a Transformer-Enhanced U-Net

Hong-Dar Lin1, Shun-Yan Li1, Chou-Hsien Lin2

  • 1Department of Industrial Engineering and Management, Chaoyang University of Technology, Taichung 413310, Taiwan.

Summary

This study introduces an advanced visual inspection framework for metallic lock components, overcoming challenges like reflections and low-contrast defects. The system uses controlled imaging and deep learning for reliable surface anomaly detection.

Related Concept Videos