Multisensor Image Fusion for Automated Detection of Defects in Printed Circuit Boards

This paper presents multisensor image fusion of polarization and infrared imaging to detect defects in printed circuit boards (PCBs). Many existing automated optical inspection techniques rely on visible imaging sensors. However, collected images suffer from uneven brightness levels due to the influence of lighting environment, which may significantly affect detection accuracies. Polarization information characterizes material types, surface roughness, and geometric shape of an object. Thermal infrared imaging reveals heat radiation difference between the defect region and the background. Polarization and infrared imaging are not sensitive to background illumination and contrast. In this paper, we utilize polarization information as well as infrared imaging to detect the defects in PCBs that conventional optical inspection techniques cannot easily detect. We design a multi-source image acquisition system to simultaneously acquire brightness intensity, polarization, and infrared intensity. Then a Multisensor Lightweight Detection Network (MLDN), trained on the PCB dataset collected, fuses polarization information and the brightness intensities in the visible and thermal infrared spectra to detect defects in challenging lighting conditions. Experiment results show that the proposed network outperforms the state-of-the-art automated optical inspection techniques in terms of mean average precision.