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

Detection of Gross Error: The Q Test01:00

Detection of Gross Error: The Q Test

6.6K
When one or more data points appear far from the rest of the data, there is a need to determine whether they are outliers and whether they should be eliminated from the data set to ensure an accurate representation of the measured value. In many cases, outliers arise from gross errors (or human errors) and do not accurately reflect the underlying phenomenon. In some cases, however, these apparent outliers reflect true phenomenological differences. In these cases, we can use statistical methods...
6.6K
Detection of Black Holes01:10

Detection of Black Holes

2.3K
Although black holes were theoretically postulated in the 1920s, they remained outside the domain of observational astronomy until the 1970s.
Their closest cousins are neutron stars, which are composed almost entirely of neutrons packed against each other, making them extremely dense. A neutron star has the same mass as the Sun but its diameter is only a few kilometers. Therefore, the escape velocity from their surface is close to the speed of light.
Not until the 1960s, when the first neutron...
2.3K

You might also read

Related Articles

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

Sort by
Same author

Charge density wave in a band insulator.

Nature communications·2026
Same author

Topology of Ultralocalized Insulators and Superconductors.

Physical review letters·2026
Same author

Proximity Induced Magnetic Anisotropy and Trefoil Fermiology in Monolayer FeCl<sub>2</sub>/Bi(111).

Advanced materials (Deerfield Beach, Fla.)·2026
Same author

Regarding the existence of abelian fractional topological insulators in twisted MoTe<sub>2</sub> and related systems.

Communications physics·2026
Same author

A practical guide for microdevice fabrication using a focused ion beam equipped with a flip-stage.

The Review of scientific instruments·2026
Same author

Decoupling Electric Field and Temperature-Driven Atomistic Forming Mechanisms in TaO<sub><i>x</i></sub>/HfO<sub>2</sub>-Based ReRAMs Using Reactive Molecular Dynamics Simulations.

ACS applied materials & interfaces·2026

Related Experiment Video

Updated: Nov 6, 2025

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography
11:34

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Published on: May 15, 2017

11.3K

Learning-based defect recognition for quasi-periodic HRSTEM images.

Nik Dennler1, Antonio Foncubierta-Rodriguez2, Titus Neupert3

  • 1IBM Research Europe - Zurich, Rüschlikon, 8803, Switzerland; University of Zurich and ETH Zurich, Institute of Neuroinformatics, Zurich, 8057, Switzerland.

Micron (Oxford, England : 1993)
|May 10, 2021
PubMed
Summary
This summary is machine-generated.

This study introduces a machine learning tool to automatically detect defects in crystalline materials from high-resolution scanning transmission electron microscopy images. The method speeds up analysis and improves accuracy, even with limited data or noisy images.

Keywords:
Computer visionCrystalline defects recognitionHigh-resolution scanning transmission electron microscopyIII–V/Si materialsMachine learning

More Related Videos

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

1.4K
Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging
11:38

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

Published on: October 4, 2024

818

Related Experiment Videos

Last Updated: Nov 6, 2025

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography
11:34

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Published on: May 15, 2017

11.3K
Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

1.4K
Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging
11:38

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

Published on: October 4, 2024

818

Area of Science:

  • Materials Science
  • Condensed Matter Physics
  • Computational Science

Background:

  • Controlling crystalline material defects is essential for device performance.
  • Current defect analysis using high-resolution scanning transmission electron microscopy (HRSTEM) relies on time-consuming human expertise.
  • Existing methods can be tedious, slow, and yield ambiguous results.

Purpose of the Study:

  • To develop a semi-supervised machine learning method for automated lattice defect detection in atomic-resolution HRSTEM images.
  • To provide an efficient and accurate alternative to manual defect identification.
  • To create an open-source tool for the microscopy community.

Main Methods:

  • A convolutional neural network (CNN) classifies image patches as defective or non-defective.
  • A graph-based heuristic selects a non-defective patch as a model.
  • An automatically generated convolutional filter bank highlights symmetry-breaking defects (stacking faults, twin defects, grain boundaries).
  • A variance filter segments amorphous and beam defects.

Main Results:

  • The algorithm successfully detected lattice defects in III-V/Si crystalline materials.
  • The method demonstrated promising results with small training datasets and noisy images.
  • Performance was evaluated against various metrics and a baseline approach, showing significant improvements.

Conclusions:

  • The developed machine learning approach combines deep learning's speed and robustness with image filter effectiveness.
  • This tool streamlines HRSTEM analysis of crystalline materials, aiding defect identification.
  • The open-source tool offers a valuable resource for researchers and microscopists.