Defect Classification of Electronic Circuit Board Using Multi-Input Convolutional Neural Network

Automatic Optical Inspection (AOI) is introduced in the manufacturing process. Detected defect is classified by the human eys check and human eye check may cause problem of unbalanced accuracy and that of cost. Based on these reasons, automatic defect classification is desired to the manufacuturing process. This paper proposes a convolutional neural network (CNN) of multiple input images with two different connection layers using two test images taken under two different conditions of illumination. Comparison is demonstrated in the experiments and the result suggests that better accuracy is obtained from the multi-input CNN which connects the two different connection layers near input layer. The performance of the proposed approach was validated with the obtained result of experiments.