Printed Circuit Board
Printed circuit boards (PCBs) are fundamental to modern electronics, and ensuring their quality and efficient recycling is crucial. Current research heavily emphasizes automated defect detection and component identification using computer vision and machine learning, frequently employing deep learning architectures like YOLOv5, EfficientDet, and various U-Net variations. These advancements aim to improve manufacturing efficiency, reduce e-waste, and enable more effective component-level recycling through automated disassembly and sorting, ultimately impacting both industrial processes and environmental sustainability.
Papers
Virtual Mines -- Component-level recycling of printed circuit boards using deep learning
Muhammad Mohsin, Stefano Rovetta, Francesco Masulli, Alberto Cabri
Measuring the Recyclability of Electronic Components to Assist Automatic Disassembly and Sorting Waste Printed Circuit Boards
Muhammad Mohsin, Xianlai Zeng, Stefano Rovetta, Francesco Masulli
PCB Component Detection using Computer Vision for Hardware Assurance
Wenwei Zhao, Suprith Gurudu, Shayan Taheri, Shajib Ghosh, Mukhil Azhagan Mallaiyan Sathiaseelan, Navid Asadizanjani
FPIC: A Novel Semantic Dataset for Optical PCB Assurance
Nathan Jessurun, Olivia P. Dizon-Paradis, Jacob Harrison, Shajib Ghosh, Mark M. Tehranipoor, Damon L. Woodard, Navid Asadizanjani