Detecting missing parts on printed circuit boards remains difficult
PCB-MC: Missing Component Analysis in Printed Circuit Boards
Computer Vision and Pattern Recognition
Summary
Finding parts that are missing from printed circuit boards is very different from finding things that are there. The authors created a special dataset called PCB-MC to help computers learn this task better, using many designs and examples. They tested various methods and found that current ways struggle a lot with new board designs or when parts are out of place. This shows that detecting missing pieces on diverse circuit boards is still a hard problem.
What this means in practice
- •For industrial quality control teams: Improve inspection processes by detecting missing components on circuit boards across varying designs using the PCB-MC dataset and benchmarks.
- •For manufacturing automation engineers: Design automated systems that identify absent parts in diverse PCB layouts, using the PCB-MC dataset to train and evaluate detection models.
Authors
Betsy Villa Brochero, Ian Gibson, Estefania Talavera
Abstract
Detecting missing components on printed circuit boards (PCBs) differs fundamentally from conventional object detection, as the model must localize components that are not present. We introduce PCB-MC, a curated dataset for missing component detection with footprint level annotations built on top of the RF100 dataset. The dataset contains 197 distinct board types, each corresponding to a unique PCB design, with multiple augmented samples per type. We also provide benchmark results on PCB-MC by evaluating a diverse set of supervised and unsupervised methods. To ensure fair evaluation, we propose board type aware cross validation splits that prevent layout leakage between training and test sets. Supervised models showcase high false negative rates on unseen board designs, and unsupervised anomaly detection methods fail entirely due to the lack of spatial alignment with a board specific reference. These results confirm that missing component detection on diverse PCB layouts remains an open challenge. We release PCB-MC and all training protocols to support reproducible research on structural absence detection in industrial inspection.