PDF(Pubmed)
Abstract：
The manual identification and in situ correction of the state of the scanning probe tip is one of the most time-consuming and tedious processes in atomic-resolution scanning probe microscopy. This is due to the random nature of the probe tip on the atomic level, and the requirement for a human operator to compare the probe quality via manual inspection of the topographical images after any change in the probe. Previous attempts to automate the classification of the scanning probe state have focused on the use of machine learning techniques, but the training of these models relies on large, labeled data sets for each surface being studied. These data sets are extremely time-consuming to create and are not always available, especially when considering a new substrate or adsorbate system. In this paper, we show that the problem of tip classification from a topographical image can be solved by using only a single image of the surface along with a small amount of prior knowledge of the appearance of the system in question with a method utilizing template matching (TM). We find that by using these TM methods, comparable accuracy and precision can be achieved to values obtained with the use of machine learning. We demonstrate the efficacy of this technique by training a machine learning-based classifier and comparing the classifications with the TM classifier for two prototypical silicon-based surfaces. We also apply the TM classifier to a number of other systems where supervised machine learning-based training was not possible due to the nature of the training data sets. Finally, the applicability of the TM method to surfaces used in the literature, which have been classified using machine learning-based methods, is considered.
摘要：
扫描探针尖端状态的手动识别和原位校正是原子分辨率扫描探针显微镜中最耗时和繁琐的过程之一。这是由于探针尖端在原子水平上的随机性，以及要求操作人员在探头发生任何变化后通过人工检查地形图像来比较探头质量。以前对扫描探针状态自动分类的尝试都集中在使用机器学习技术，但是这些模型的训练依赖于大量的，每个被研究表面的标记数据集。创建这些数据集非常耗时，并且并不总是可用，特别是在考虑新的底物或吸附物系统时。在本文中,我们表明，通过使用模板匹配（TM）的方法，可以通过仅使用表面的单个图像以及有关系统外观的少量先验知识来解决地形图像的尖端分类问题。我们发现，通过使用这些TM方法，可以实现与使用机器学习获得的值相当的准确性和精确度。我们通过训练基于机器学习的分类器并将分类与TM分类器比较两个原型硅基表面来证明该技术的有效性。我们还将TM分类器应用于许多其他系统，其中由于训练数据集的性质，基于监督机器学习的训练是不可能的。最后,TM方法对文献中使用的表面的适用性，已经使用基于机器学习的方法进行了分类，被考虑。
