PCB defect detection with self-supervised learning of local image patches

This paper presents a defect detection technique in printed circuit boards (PCBs) using self-supervised learning of local image patches (SLLIP). Defect detection in PCBs is often hindered by the problems like a lack of defect data, the existence of tiny components, and the cluttered background. From the observation that some local image patches of a PCB are similar in texture and brightness distribution but are different in semantic features, the proposed self-supervised learning method utilizes the relative position estimation, spatially adjacent similarity, and k-means clustering of patches to learn finely classified semantic features. Then, the feature consistency between the local image patches and the background is learned by a local image patch completion network. The feature differences between the estimated and the original image patches are used to detect anomaly areas in PCBs. Experiment results on the PCB defect dataset demonstrate that the proposed SLLIP outperforms the state-of-the-art methods.