A dataset for deep learning based detection of printed circuit board surface defect

Abstract

Abstract Printed circuit board (PCB) may display diverse surface defects in manufacturing. These defects not only influence aesthetics but can also affect the performance of the PCB and potentially damage the entire board. Thus, achieving efficient and highly accurate detection of PCB surface defects is fundamental for quality control in fabrication. The rapidly advancing deep learning (DL) technology holds promising prospects for providing accurate and efficient detection methods for surface defects on PCB. To facilitate DL model training, it is imperative to compile a comprehensive dataset encompassing diverse surface defect types found on PCB at a significant scale. This work categorized PCB surface defects into 9 distinct categories based on factors such as their causes, locations, and morphologies and developed a dataset of PCB surface defect (DsPCBSD+). In DsPCBSD+, a total of 20,276 defects were annotated manually by bounding boxes on the 10,259 images. This openly accessible dataset is aimed accelerating and promoting further researches and advancements in the field of DL-based detection of PCB surface defect.