Capacitor Detection in PCB Using YOLO Algorithm

Optical inspection is an important task of PCB manufacturing. Once PCB manufactured in small batch production, it needs a fast way to teach and adjust the automatic optical inspection (AOI) system for the inspection of the batch of product. This paper proposes a capacitor detection method based on YOLO algorithm for printed circuit board (PCB) assembly. YOLO is a kind of fast object detection method based on convolutional neural network (CNN). The deep network architecture of CNN can detect discrimination features from all of the input images, so we do not need experts to define image features. To verify the effectiveness of the proposed approach, samples of PCB images with nine kinds of capacitors are collected and trained by YOLO. Experimental results show all the types of capacitors in PCB can be detected and the average detection time is less than 0.3 second. The detection time is fast enough to develop an on-line PCB assembly inspection.