Robust autofocusing for scanning electron microscopy based on a dual deep learning network

Woojin Lee,Jun Hee Lee,Young Gon Kim,Hyeong Soo Nam,Hongki Yoo,Yong Ju Kim

doi:10.1038/s41598-021-00412-5

Woojin Lee, Jun Hee Lee + Show 4 more

Open Access

https://doi.org/10.1038/s41598-021-00412-5

Copy DOI

Abstract

Scanning electron microscopy (SEM) is a high-resolution imaging technique with subnanometer spatial resolution that is widely used in materials science, basic science, and nanofabrication. However, conducting SEM is rather complex due to the nature of using an electron beam and the many parameters that must be adjusted to acquire high-quality images. Only trained operators can use SEM equipment properly, meaning that the use of SEM is restricted. To broaden the usability of SEM, we propose an autofocus method for a SEM system based on a dual deep learning network, which consists of an autofocusing-evaluation network (AENet) and an autofocusing-control network (ACNet). The AENet was designed to evaluate the quality of given images, with scores ranging from 0 to 9 regardless of the magnification. The ACNet can delicately control the focus of SEM online based on the AENet’s outputs for any lateral sample position and magnification. The results of these dual networks showed successful autofocus performance on three trained samples. Moreover, the robustness of the proposed method was demonstrated by autofocusing on unseen samples. We expect that our autofocusing system will not only contribute to expanding the versatility of SEM but will also be applicable to various microscopes.

Highlights

Scanning electron microscopy (SEM) is a high-resolution imaging technique with subnanometer spatial resolution that is widely used in materials science, basic science, and nanofabrication
We propose an autofocus method for a SEM system based on a dual deep learning network consisting of an autofocusing-evaluation network (AENet) and an autofocusing-control network (ACNet)
The ACNet determines how much the working distance (WD) needs to be adjusted at the current state using a combination of the AENet score, the SEM parameters, and additional image quality metrics

Summary

Introduction

Scanning electron microscopy (SEM) is a high-resolution imaging technique with subnanometer spatial resolution that is widely used in materials science, basic science, and nanofabrication. In order to provide optimally focused SEM images with high quality regardless of a user’s level of expertise, a robust autofocus system that can control these parameters is of importance for broadening the variety of research applications. Et al.[11] and Na, et al.[12] respectively proposed an autofocus method for optical microscopy and SEM that receives a defocused image as an input and outputs a virtual focused image based on deep learning. Even though most conventional autofocus systems have been successfully studied and applied to optical microscopes, SEM is difficult to apply because image quality is more sensitive to parameter changes due to its inherent high magnification. A new autofocus system tailored to the technical characteristics of SEM is required

Objectives

Methods

Results

Conclusion