arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.05322cond-mat.mtrl-scics.LG
收藏

原子分辨率相衬透射电镜图像复杂特征的深度学习分割

Deep Learning Segmentation of Complex Features in Atomic-Resolution Phase Contrast Transmission Electron Microscopy Images

Lawrence Berkeley National Laboratory(劳伦斯伯克利国家实验室)

Robbie Sadre, Colin Ophus, Anstasiia Butko, Gunther H Weber

摘要:

相衬透射电子显微镜(TEM)是对材料局部原子结构成像的有力工具。由于其高剂量效率,TEM已被大量用于诸如单层石墨烯的2D材料的缺陷结构的研究。然而,相衬成像可以产生复杂的非线性对比度,即使是弱散射样品。因此,很难使用传统的图像处理工具开发用于相衬TEM研究的全自动分析例程。对于石墨烯的大样品区域的自动分析,关键问题之一是感兴趣的结构和不需要的结构(例如表面污染物层)之间的分割。在这项研究中,我们将传统布拉格滤波方法的性能与基于U-Net架构的深度学习例程进行了比较。我们表明,深度学习方法更通用,在实践中应用更简单,并且比传统算法产生更准确和鲁棒的结果。我们为本文中的所有结果提供了易于适应的源代码,并讨论了深度学习在全自动TEM图像分析中的潜在应用。

英文摘要:

Phase contrast transmission electron microscopy (TEM) is a powerful tool for imaging the local atomic structure of materials. TEM has been used heavily in studies of defect structures of 2D materials such as monolayer graphene due to its high dose efficiency. However, phase contrast imaging can produce complex nonlinear contrast, even for weakly-scattering samples. It is therefore difficult to develop fully-automated analysis routines for phase contrast TEM studies using conventional image processing tools. For automated analysis of large sample regions of graphene, one of the key problems is segmentation between the structure of interest and unwanted structures such as surface contaminant layers. In this study, we compare the performance of a conventional Bragg filtering method to a deep learning routine based on the U-Net architecture. We show that the deep learning method is more general, simpler to apply in practice, and produces more accurate and robust results than the conventional algorithm. We provide easily-adaptable source code for all results in this paper, and discuss potential applications for deep learning in fully-automated TEM image analysis.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑