Correction of AFM data artifacts using a convolutional neural network trained with synthetically generated data

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F23%3APU148195" target="_blank" >RIV/00216305:26230/23:PU148195 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.sciencedirect.com/science/article/pii/S0304399122001851?via%3Dihub" target="_blank" >https://www.sciencedirect.com/science/article/pii/S0304399122001851?via%3Dihub</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.ultramic.2022.113666" target="_blank" >10.1016/j.ultramic.2022.113666</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Correction of AFM data artifacts using a convolutional neural network trained with synthetically generated data

Popis výsledku v původním jazyce

AFM microscopy from its nature produces outputs with certain distortions, inaccuracies and errors given by its physical principle. These distortions are more or less well studied and documented. Based on the nature of the individual distortions, different reconstruction and compensation filters have been developed to post-process the scanned images. This article presents an approach based on machine learning - the involved convolutional neural network learns from pairs of distorted images and the ground truth image and then it is able to process pairs of images of interest and produce a filtered image with the artifacts removed or at least suppressed. What is important in our approach is that the neural network is trained purely on synthetic data generated by a simulator of the inputs, based on an analytical description of the physical phenomena causing the distortions. The generator produces training samples involving various combinations of the distortions. The resulting trained network seems to be able to autonomously recognize the distortions present in the testing image (no knowledge of the distortions or any other human knowledge is provided at the test time) and apply the appropriate corrections. The experimental results show that not only is the new approach better or at least on par with conventional post-processing methods, but more importantly, it does not require any operator's input and works completely autonomously. The source codes of the training set generator and of the convolutional neural net model are made public, as well as an evaluation dataset of real captured AFM images.

Název v anglickém jazyce

Correction of AFM data artifacts using a convolutional neural network trained with synthetically generated data

Popis výsledku anglicky

AFM microscopy from its nature produces outputs with certain distortions, inaccuracies and errors given by its physical principle. These distortions are more or less well studied and documented. Based on the nature of the individual distortions, different reconstruction and compensation filters have been developed to post-process the scanned images. This article presents an approach based on machine learning - the involved convolutional neural network learns from pairs of distorted images and the ground truth image and then it is able to process pairs of images of interest and produce a filtered image with the artifacts removed or at least suppressed. What is important in our approach is that the neural network is trained purely on synthetic data generated by a simulator of the inputs, based on an analytical description of the physical phenomena causing the distortions. The generator produces training samples involving various combinations of the distortions. The resulting trained network seems to be able to autonomously recognize the distortions present in the testing image (no knowledge of the distortions or any other human knowledge is provided at the test time) and apply the appropriate corrections. The experimental results show that not only is the new approach better or at least on par with conventional post-processing methods, but more importantly, it does not require any operator's input and works completely autonomously. The source codes of the training set generator and of the convolutional neural net model are made public, as well as an evaluation dataset of real captured AFM images.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/FW01010183" target="_blank" >FW01010183: Nová generace integrace mikroskopie atomárních sil a elektronové mikroskopie</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Ultramicroscopy

ISSN

0304-3991

e-ISSN

1879-2723

Svazek periodika

246

Číslo periodika v rámci svazku

1

Stát vydavatele periodika

NL - Nizozemsko

Počet stran výsledku

16

Strana od-do

113666-113666

Kód UT WoS článku

000917791400001

EID výsledku v databázi Scopus

2-s2.0-85145353263