Resolution enhancement in scanning electron microscopy using deep learning

TL;DR

This paper introduces a deep learning method using generative adversarial networks to enhance the resolution of SEM images, enabling faster imaging with reduced sample damage while maintaining high resolution.

Contribution

The study presents a novel deep learning-based super-resolution technique for SEM images that accurately infers unresolved features and matches high-resolution frequency spectra.

Findings

Super-resolution SEM images match high-resolution spectra.

Faster SEM imaging with less sample damage.

Deep learning effectively infers unresolved features.

Abstract

We report resolution enhancement in scanning electron microscopy (SEM) images using a generative adversarial network. We demonstrate the veracity of this deep learning-based super-resolution technique by inferring unresolved features in low-resolution SEM images and comparing them with the accurately co-registered high-resolution SEM images of the same samples. Through spatial frequency analysis, we also report that our method generates images with frequency spectra matching higher resolution SEM images of the same fields-of-view. By using this technique, higher resolution SEM images can be taken faster, while also reducing both electron charging and damage to the samples.