SMT Solder Joint Inspection via a Novel Cascaded Convolutional Neural Network

Abstract

Due to the excellent self-learning ability of deep learning, we propose a novel deep-learning-based method to inspect surface-mount technology (SMT) solder joints in this paper. In contrast to the state-of-the-art learning-based methods in which low-level features are extracted before learning, our method directly implements the inspection task without low-level feature extraction, which is based on a novel cascaded convolutional neural network (CNN). Three kinds of CNNs with different network parameters compose the proposed cascaded CNN. First, one kind of CNN is employed to adaptively learn the regions of interest (ROIs) of SMT solder joint images. Then, both the learned ROIs and the entire solder joint images are fed into the other two kinds of CNNs, respectively. Finally, inspection results are achieved by the learned cascaded CNN. Comparison experiments indicate that our proposed method can achieve more excellent inspection performance for SMT solder joints than that of the state-of-the-art methods.