Quality Inspection of Printed Circuit Board Pin Insertion via Semantic Segmentation and Board-Level Feature Extraction
2026-08-24 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors developed a computer-based method to find misaligned pins on printed circuit boards (PCBs), which is important for making sure electronics work well. Their method uses a type of artificial intelligence called U-Net to identify pins in images, then analyzes the shapes of the pins to decide if the board passes or fails inspection. They tested their approach on two different collections of PCB images and found it was very accurate compared to other methods. This suggests their system could help automate quality checks in factories that make PCBs. The system performs well even when tested on very different types of images after being trained on each specific dataset.
Printed Circuit Board (PCB)Pin InspectionSemantic SegmentationU-NetContour ExtractionLogistic RegressionAnomaly DetectionROC-AUCInstance SegmentationAutomated Quality Control
Authors
Nils Rabeneck, André Kiunke, Nicole Hoess, Wolfgang Mauerer
Abstract
Quality control during printed circuit board (PCB) assembly is a critical step in ensuring reliable electronic products. Detecting misaligned pins during or after pin insertion remains a particularly challenging inspection task. This paper presents an automated defect detection method for identifying incorrectly inserted pins on PCBs. The proposed pipeline combines semantic segmentation using a U-Net architecture with contour-based feature extraction and logistic regression for board-level pass/fail classification. Segmentation masks are used to derive contour representations of individual pins, from which board-level features -such as average contour size- are extracted and used to train a logistic regression classifier. We evaluate the method on two datasets: an industrial collection of real-world PCB images, and a publicly available PCB pin-inspection dataset with substantially different visual characteristics. To assess the effectiveness of the proposed approach, a comparison against PatchCore, an anomaly detection technique new to be applied to pin inspection, as well as instance segmentation-based pin detection is made. The developed method achieved Area Under the Receiver Operating Characteristic Curve (ROC-AUC) values of 0.990 on a random test set split from the industrial data and 1.000 on the public dataset indicating strong separation between pass and fail boards. The results indicate that the proposed approach is a promising candidate for automated pin inspection in industrial environments and achieves strong performance on datasets with substantially different visual characteristics after dataset-specific training.