Multi-label classification of PCB defects based on convolutional neural network

Printed Circuit Board (PCB) defect detection is a critical task in electronic manufacturing quality control. This paper proposes a multi-label classification method based on Convolutional Neural Network (CNN) for detecting and classifying various types of defects on PCBs. The proposed method can effectively identify multiple defect types simultaneously, improving the accuracy and efficiency of PCB defect detection. Experimental results demonstrate the effectiveness of the CNN-based approach in multi-label defect classification.

Journal article

The Journal of Engineering