标题： 超导探测器视觉特性自动化分析 显示英文标题

标题： Automated analysis of the visual properties of superconducting detectors

摘要： 低温超导探测器的测试和质量保证是一个耗时且劳动密集的过程。随着实验部署的探测器阵列越来越大，需要新的方法来快速进行这些测试。在这里，我们提出了一种在探测器进行低温测试之前标记表现不佳的晶圆片的方法。探测器在光学显微镜下成像，使用计算机视觉技术分析这些图像，寻找视觉缺陷和其他性能不佳的预测指标。通过一系列带有模拟缺陷的图像验证了管道的性能，检测准确率达到98.6%。最后，展示了在计划中的SPT-3G+实验的原型微波激发电感探测器上运行该管道的结果。 显示英文摘要

摘要： The testing and quality assurance of cryogenic superconducting detectors is a time- and labor-intensive process. As experiments deploy increasingly larger arrays of detectors, new methods are needed for performing this testing quickly. Here, we propose a process for flagging under-performing detector wafers before they are ever tested cryogenically. Detectors are imaged under an optical microscope, and computer vision techniques are used to analyze the images, searching for visual defects and other predictors of poor performance. Pipeline performance is verified via a suite of images with simulated defects, yielding a detection accuracy of 98.6%. Lastly, results from running the pipeline on prototype microwave kinetic inductance detectors from the planned SPT-3G+ experiment are presented.