BoardVision: Deployment-ready and Robust Motherboard Defect Detection with YOLO+Faster-RCNN Ensemble

2025-10-16

AI Summary

Systematic research on visual detection of motherboard-level defects (e.g., missing screws, loose fan cables, surface scratches) in high-volume electronics manufacturing remains lacking. Method: We propose the first reproducible, production-line-oriented visual inspection framework, integrating YOLOv7 and Faster R-CNN with a lightweight Confidence-Temporal Voting (CTV Voter) ensemble mechanism, augmented by image enhancement and multimodal feature fusion; a GUI-driven deployable tool is also developed. Contribution/Results: To our knowledge, this work presents the first systematic robustness evaluation under realistic industrial perturbations—including illumination variation and occlusion. Evaluated on the MiracleFactory dataset, our framework significantly improves detection stability and generalization in complex scenes. It achieves superior precision–recall trade-offs and industrial deployability compared to existing bare-board or trace-level methods, effectively bridging the gap between academic performance and real-world quality inspection requirements.

Technology Category

• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Ensemble Methods

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Motherboard defect detection is critical for ensuring reliability in high-volume electronics manufacturing. While prior research in PCB inspection has largely targeted bare-board or trace-level defects, assembly-level inspection of full motherboards inspection remains underexplored. In this work, we present BoardVision, a reproducible framework for detecting assembly-level defects such as missing screws, loose fan wiring, and surface scratches. We benchmark two representative detectors - YOLOv7 and Faster R-CNN, under controlled conditions on the MiracleFactory motherboard dataset, providing the first systematic comparison in this domain. To mitigate the limitations of single models, where YOLO excels in precision but underperforms in recall and Faster R-CNN shows the reverse, we propose a lightweight ensemble, Confidence-Temporal Voting (CTV Voter), that balances precision and recall through interpretable rules. We further evaluate robustness under realistic perturbations including sharpness, brightness, and orientation changes, highlighting stability challenges often overlooked in motherboard defect detection. Finally, we release a deployable GUI-driven inspection tool that bridges research evaluation with operator usability. Together, these contributions demonstrate how computer vision techniques can transition from benchmark results to practical quality assurance for assembly-level motherboard manufacturing.

Problem

• Detects assembly-level motherboard defects like missing screws and loose wiring
• Addresses precision-recall trade-offs through ensemble model combining YOLO and Faster-R-CNN
• Evaluates robustness under real-world perturbations and provides deployable inspection tool

Innovation

• Ensembles YOLO and Faster-RCNN for defect detection
• Uses Confidence-Temporal Voting to balance precision
• Provides deployable GUI tool for practical usability