Saved in:
Bibliographic Details
Main Authors: Chae, Jinwoong, Hong, Sungwook, Kim, Sungkyu, Yoon, Sungroh, Kim, Gunn
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.11225
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912194401140736
author Chae, Jinwoong
Hong, Sungwook
Kim, Sungkyu
Yoon, Sungroh
Kim, Gunn
author_facet Chae, Jinwoong
Hong, Sungwook
Kim, Sungkyu
Yoon, Sungroh
Kim, Gunn
contents Transmission electron microscope (TEM) images are often corrupted by noise, hindering their interpretation. To address this issue, we propose a deep learning-based approach using simulated images. Using density functional theory calculations with a set of pseudo-atomic orbital basis sets, we generate highly accurate ground truth images. We introduce four types of noise into these simulations to create realistic training datasets. Each type of noise is then used to train a separate convolutional neural network (CNN) model. Our results show that these CNNs are effective in reducing noise, even when applied to images with different noise levels than those used during training. However, we observe limitations in some cases, particularly in preserving the integrity of circular shapes and avoiding visible artifacts between image patches. To overcome these challenges, we propose alternative training strategies and future research directions. This study provides a valuable framework for training deep learning models for TEM image denoising.
format Preprint
id arxiv_https___arxiv_org_abs_2501_11225
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CNN-based TEM image denoising from first principles
Chae, Jinwoong
Hong, Sungwook
Kim, Sungkyu
Yoon, Sungroh
Kim, Gunn
Materials Science
Computer Vision and Pattern Recognition
Image and Video Processing
Transmission electron microscope (TEM) images are often corrupted by noise, hindering their interpretation. To address this issue, we propose a deep learning-based approach using simulated images. Using density functional theory calculations with a set of pseudo-atomic orbital basis sets, we generate highly accurate ground truth images. We introduce four types of noise into these simulations to create realistic training datasets. Each type of noise is then used to train a separate convolutional neural network (CNN) model. Our results show that these CNNs are effective in reducing noise, even when applied to images with different noise levels than those used during training. However, we observe limitations in some cases, particularly in preserving the integrity of circular shapes and avoiding visible artifacts between image patches. To overcome these challenges, we propose alternative training strategies and future research directions. This study provides a valuable framework for training deep learning models for TEM image denoising.
title CNN-based TEM image denoising from first principles
topic Materials Science
Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2501.11225