Jove
Visualize
Contact Us

Related Concept Videos

Detection of Black Holes01:10

Detection of Black Holes

2.2K
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...
2.2K

You might also read

Related Articles

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

Sort by
Same author

Structure-Dependent Dynamics of Quantum Emitters in Single-Layer WSe<sub>2</sub>.

Nano letters·2025
Same author

Increased Formation of Trions and Charged Biexcitons by Above-Gap Excitation in Single-layer WSe<sub>2</sub>.

ACS nano·2024
Same author

Predicting quantum emitter fluctuations with time-series forecasting models.

Scientific reports·2024
Same author

Programmable nanowrinkle-induced room-temperature exciton localization in monolayer WSe<sub>2</sub>.

Nature communications·2024
Same author

Incommensurate Antiferromagnetic Order in Weakly Frustrated Two-Dimensional van der Waals Insulator CrPSe<sub>3</sub>.

Inorganic chemistry·2023
Same author

Direct nano-imaging of light-matter interactions in nanoscale excitonic emitters.

Nature communications·2023
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 Experiment Video

Updated: Aug 12, 2025

Detection and Quantification of Tunneling Nanotubes Using 3D Volume View Images
12:45

Detection and Quantification of Tunneling Nanotubes Using 3D Volume View Images

Published on: August 31, 2022

3.0K

Automatic detection of multilayer hexagonal boron nitride in optical images using deep learning-based computer

Fereshteh Ramezani1, Sheikh Parvez2,3, J Pierce Fix2,3

  • 1Electrical and Computer Engineering Department, Montana State University, Bozeman, USA. fereshteh.ramezani@student.montana.edu.

Scientific Reports
|January 28, 2023
PubMed
Summary

Computer vision automates the identification of 2D materials like hexagonal boron nitride (hBN) in microscope images. This deep learning approach accurately detects thin hBN flakes, accelerating research and development in quantum technologies.

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.9K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

600

Related Experiment Videos

Last Updated: Aug 12, 2025

Detection and Quantification of Tunneling Nanotubes Using 3D Volume View Images
12:45

Detection and Quantification of Tunneling Nanotubes Using 3D Volume View Images

Published on: August 31, 2022

3.0K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.9K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

600

Area of Science:

  • Materials Science
  • Computer Vision
  • Quantum Information Science

Background:

  • Two-dimensional (2D) materials possess unique properties crucial for quantum information science and engineering.
  • Hexagonal boron nitride (hBN), an isomorph of graphene, is a 2D material with a layered structure vital for applications.
  • Mechanical exfoliation and optical microscopy are standard for preparing and identifying 2D materials, but manual analysis is time-consuming.

Purpose of the Study:

  • To develop and implement a deep learning pipeline for automated classification of hexagonal boron nitride (hBN) crystallites.
  • To improve the efficiency and accuracy of identifying 2D materials in reflected-light optical micrographs.
  • To address the limitations of manual search and tedious identification processes in 2D material research.

Main Methods:

  • Utilized a deep learning pipeline employing the DetectoRS object detector.
  • Trained the model on 177 reflected-light optical micrographs containing hexagonal boron nitride (hBN) flakes of varying thicknesses.
  • Focused on classifying crystallites based on coarse thickness, specifically targeting rare, thin flakes.

Main Results:

  • Achieved high detection accuracy for thin hexagonal boron nitride (hBN) flakes (down to a few atomic layers).
  • Demonstrated the pipeline's robustness across different microscope settings, including variations in color and substrate background.
  • Successfully automated the flake detection task, minimizing the need for human intervention.

Conclusions:

  • The implemented deep learning pipeline effectively automates the identification and classification of 2D materials like hBN.
  • This approach significantly enhances the efficiency of 2D material research, particularly for identifying critical thin flakes.
  • The model's generalizability suggests broad applicability in materials science and quantum technology development.