Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Atomic-scale regulation of ion motion and phonon scattering: ALD-driven interface engineering for stabilizing β-Zn<sub>4</sub>Sb<sub>3</sub>.

Science advances·2026
Same author

Mechanically driven Li dendrite penetration in garnet solid electrolyte.

Nature·2026
Same author

In Situ EC-EPR Spectroscopy and DFT Analysis of H<sub>UPD</sub> on Polycrystalline Pt.

ChemSusChem·2026
Same author

Identifying grain boundary and intragranular pinning centres in Sm<sub>2</sub>(Co,Fe,Cu,Zr)<sub>17</sub> permanent magnets to guide performance optimisation.

Nature communications·2025
Same author

A python workflow definition for computational materials design.

Digital discovery·2025
Same author

Microstructural transformation for robust and high-efficiency Zintl thermoelectrics.

Nature communications·2025

Related Experiment Video

Updated: Oct 19, 2025

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning
12:06

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Published on: March 3, 2023

4.3K

Segmentation of Static and Dynamic Atomic-Resolution Microscopy Data Sets with Unsupervised Machine Learning Using

Ning Wang1, Christoph Freysoldt1, Siyuan Zhang1

  • 1Max-Planck-Institut für Eisenforschung GmbH, Max-Planck-Straße 1, 40237Düsseldorf, Germany.

Microscopy and Microanalysis : the Official Journal of Microscopy Society of America, Microbeam Analysis Society, Microscopical Society of Canada
|September 21, 2021
PubMed
Summary

We developed an unsupervised machine learning method for segmenting atomic-resolution microscopy images and videos. This approach uses symmetry features and clustering for pixel labeling, enhancing speed for dynamic data.

Keywords:
HAADF-STEMsegmentationsymmetry descriptorsunsupervised learning

More Related Videos

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps
08:59

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps

Published on: October 28, 2018

7.2K
From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
12:08

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

24.7K

Related Experiment Videos

Last Updated: Oct 19, 2025

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning
12:06

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Published on: March 3, 2023

4.3K
Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps
08:59

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps

Published on: October 28, 2018

7.2K
From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
12:08

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

24.7K

Area of Science:

  • Materials Science
  • Data Science
  • Microscopy

Background:

  • Atomic-resolution microscopy generates complex datasets requiring advanced analysis.
  • Segmentation of static and dynamic microscopy data is crucial for understanding material structures.

Purpose of the Study:

  • To present an unsupervised machine learning approach for segmenting atomic-resolution microscopy data.
  • To improve the efficiency of segmenting image sequences.

Main Methods:

  • Feature extraction using symmetry operations.
  • Dimension reduction and clustering in feature space for pixel labeling.
  • Development of stride and upsampling schemes for faster video segmentation.

Main Results:

  • Successful application to static and dynamic atomic-resolution scanning transmission electron microscopy data.
  • Demonstrated effectiveness of the unsupervised machine learning approach for segmentation.
  • Developed methods to accelerate the segmentation of image sequences.

Conclusions:

  • The presented unsupervised machine learning approach provides an effective tool for segmenting atomic-resolution microscopy data.
  • The developed methods enhance the speed and applicability of microscopy data analysis.
  • The open-source Python module facilitates broader use in scientific research.