Team project
Defect detection on printed circuit boards
YOLOv8 models fine-tuned to detect surface defects, then measured for missed defects and false alarms.
Measured on a separate test set
Missed defects False alarms
- Period
- Dec 2025 – Mar 2026
- Type
- Team project
- Course
- Advanced Machine Learning for Computer Vision
- University
- IT University of Copenhagen
- Tools
Method
- Fine-tuned YOLOv8 models to detect surface defects
- Kept training runs repeatable with configuration files
- Tracked detection metrics in Weights & Biases
- Compared saved checkpoints and chose a threshold on validation images
- Measured missed defects and false alarms on a separate test set