发表机构
Technical University of Applied Sciences Regensburg; Siemens AG, Technology（雷根斯堡应用技术大学; 西门子股份公司技术部）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究针对PCB引脚插入错位检测难题，提出结合U-Net语义分割、轮廓特征提取与逻辑回归的自动化缺陷检测方法，在工业及公开PCB数据集上取得优异检测性能，适用于工业引脚检测场景。
AI 中文摘要
印刷电路板（PCB）组装过程中的质量控制是确保电子产品可靠性的关键环节，在引脚插入过程中或插入后检测引脚错位仍是一项极具挑战性的检测任务。本文提出一种用于识别PCB上插入错误引脚的自动化缺陷检测方法，所提流程结合U-Net架构的语义分割、基于轮廓的特征提取与逻辑回归以实现板级合格/不合格分类。分割掩码用于推导单个引脚的轮廓表示，从这些表示中提取平均轮廓尺寸等板级特征，用于训练逻辑回归分类器。我们在两个数据集上评估该方法：一个是工业采集的真实PCB图像，另一个是视觉特征差异显著的公开PCB引脚检测数据集。为评估所提方法的有效性，将其与PatchCore（一种新应用于引脚检测的异常检测技术）以及基于实例分割的引脚检测方法进行对比。所开发方法在工业数据随机划分的测试集上取得受试者工作特征曲线下面积（ROC-AUC）为0.990，在公开数据集上取得1.000的ROC-AUC值，表明合格与不合格板之间具有良好的区分度。结果表明，所提方法是工业环境中自动化引脚检测的有潜力候选方案，且在针对特定数据集训练后，能在视觉特征差异显著的数据集上实现优异性能。
英文摘要
Quality control during printed circuit board (PCB) assembly is a critical step in ensuring reliable electronic products. Detecting misaligned pins during or after pin insertion remains a particularly challenging inspection task. This paper presents an automated defect detection method for identifying incorrectly inserted pins on PCBs. The proposed pipeline combines semantic segmentation using a U-Net architecture with contour-based feature extraction and logistic regression for board-level pass/fail classification. Segmentation masks are used to derive contour representations of individual pins, from which board-level features -such as average contour size- are extracted and used to train a logistic regression classifier. We evaluate the method on two datasets: an industrial collection of real-world PCB images, and a publicly available PCB pin-inspection dataset with substantially different visual characteristics. To assess the effectiveness of the proposed approach, a comparison against PatchCore, an anomaly detection technique new to be applied to pin inspection, as well as instance segmentation-based pin detection is made. The developed method achieved Area Under the Receiver Operating Characteristic Curve (ROC-AUC) values of 0.990 on a random test set split from the industrial data and 1.000 on the public dataset indicating strong separation between pass and fail boards. The results indicate that the proposed approach is a promising candidate for automated pin inspection in industrial environments and achieves strong performance on datasets with substantially different visual characteristics after dataset-specific training.
