Detection of missing components on a PCB using image processing

Manual inspection of PCB components is often inaccurate and inefficient due to human error, posing a significant risk to quality control in electronic systems. This study used YOLOv8, a state-of-the-art object detection model, for PCB inspections. The system, known for its speed and accuracy, achieved an impressive of 98.3% accuracy rate across 773 instances on six component classes. The system performance was evaluated under various conditions, with 98% accuracy under ideal conditions and 96% under non-ideal conditions. Error rates rose from 1% in ideal conditions to 3% in non-ideal conditions, indicating their sensitivity to environmental factors. Feedback from students, technicians, and instructors praised the system's potential, with mean rating of 4.8 for accuracy, 4.7 for functionality, 4.8 for reliability, and 4.7 for user-friendliness. The results reveal that the system is a reliable tool for PCB verification. However, optimal camera resolution and size limits are crucial for effective inspections and component identification. This research is potential to significantly enhance efficiency and accuracy in quality control processes within the electronics manufacturing industry.