TEMImageNet Training Library and AtomSegNet Deep-Learning Models for High-Precision Atom Segmentation, Localization, Denoising, and Super-Resolution Processing of Atomic-Resolution Images

TL;DR

This paper introduces TEMImageNet, a training library and deep learning models that significantly improve atom segmentation, localization, denoising, and super-resolution in atomic-resolution STEM images, outperforming traditional methods.

Contribution

Development of a comprehensive training library and robust deep learning models for high-precision atom analysis in STEM images, adaptable to experimental data.

Findings

Deep learning models outperform traditional Gaussian fitting in atom localization.

Models show robustness under challenging contrast and noise conditions.

Open-source tools and datasets facilitate wider adoption and further research.

Abstract

Atom segmentation and localization, noise reduction and deblurring of atomic-resolution scanning transmission electron microscopy (STEM) images with high precision and robustness is a challenging task. Although several conventional algorithms, such has thresholding, edge detection and clustering, can achieve reasonable performance in some predefined sceneries, they tend to fail when interferences from the background are strong and unpredictable. Particularly, for atomic-resolution STEM images, so far there is no well-established algorithm that is robust enough to segment or detect all atomic columns when there is large thickness variation in a recorded image. Herein, we report the development of a training library and a deep learning method that can perform robust and precise atom segmentation, localization, denoising, and super-resolution processing of experimental images. Despite using simulated images as training datasets, the deep-learning model can self-adapt to experimental STEM images and shows outstanding performance in atom detection and localization in challenging contrast conditions and the precision consistently outperforms the state-of-the-art two-dimensional Gaussian fit method. Taking a step further, we have deployed our deep-learning models to a desktop app with a graphical user interface and the app is free and open-source. We have also built a TEM ImageNet project website for easy browsing and downloading of the training data.