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

Measurement-aware learning for reliable grain-boundary analysis in quantitative metallography.

Scientific reports·2026
Same author

Reclassification and weighting of multiple causes of death: US death certificates 2003-2023.

Proceedings of the National Academy of Sciences of the United States of America·2026
Same author

Structure-aware graph learning predicts RNA editability across tissues and species.

Research square·2026
Same author

Reclassification and Weighting of Multiple Causes of Death: US Death Certificates 2003-2023.

medRxiv : the preprint server for health sciences·2026
Same author

Structure-aware Graph Learning Predicts RNA Editability Across Tissues and Species.

bioRxiv : the preprint server for biology·2026
Same author

ADAR-GPT: A continually fine-tuned language model for predicting A-to-I RNA editing sites.

Proceedings of the National Academy of Sciences of the United States of America·2026

Related Experiment Video

Updated: Sep 29, 2025

Author Spotlight: A Machine-Vision Approach to Transmission Electron Microscopy Workflows, Results Analysis and Data Management
10:23

Author Spotlight: A Machine-Vision Approach to Transmission Electron Microscopy Workflows, Results Analysis and Data Management

Published on: June 23, 2023

3.0K

An end-to-end computer vision methodology for quantitative metallography.

Matan Rusanovsky1,2, Ofer Beeri3, Gal Oren4,5

  • 1Scientific Computing Center, Nuclear Research Center-Negev, Be'er-Sheva, Israel.

Scientific Reports
|March 22, 2022
PubMed
Summary

This study introduces an AI model for quantitative metallography, automating impurity anomaly detection in alloys. The model identifies and analyzes inclusions, guiding experts to critical areas for material assessment.

More Related Videos

In Depth Analyses of LEDs by a Combination of X-ray Computed Tomography CT and Light Microscopy LM Correlated with Scanning Electron Microscopy SEM
10:42

In Depth Analyses of LEDs by a Combination of X-ray Computed Tomography CT and Light Microscopy LM Correlated with Scanning Electron Microscopy SEM

Published on: June 16, 2016

9.4K
Processing of Bulk Nanocrystalline Metals at the US Army Research Laboratory
08:58

Processing of Bulk Nanocrystalline Metals at the US Army Research Laboratory

Published on: March 7, 2018

9.5K

Related Experiment Videos

Last Updated: Sep 29, 2025

Author Spotlight: A Machine-Vision Approach to Transmission Electron Microscopy Workflows, Results Analysis and Data Management
10:23

Author Spotlight: A Machine-Vision Approach to Transmission Electron Microscopy Workflows, Results Analysis and Data Management

Published on: June 23, 2023

3.0K
In Depth Analyses of LEDs by a Combination of X-ray Computed Tomography CT and Light Microscopy LM Correlated with Scanning Electron Microscopy SEM
10:42

In Depth Analyses of LEDs by a Combination of X-ray Computed Tomography CT and Light Microscopy LM Correlated with Scanning Electron Microscopy SEM

Published on: June 16, 2016

9.4K
Processing of Bulk Nanocrystalline Metals at the US Army Research Laboratory
08:58

Processing of Bulk Nanocrystalline Metals at the US Army Research Laboratory

Published on: March 7, 2018

9.5K

Area of Science:

  • Materials Science
  • Artificial Intelligence
  • Image Analysis

Background:

  • Metallography is essential for assessing material properties, focusing on grain distribution and inclusions.
  • Current methods for analyzing inclusions and precipitates can be labor-intensive and subjective.
  • Automating quantitative metallography can improve efficiency and accuracy in material characterization.

Purpose of the Study:

  • To develop a holistic, few-shot artificial intelligence (AI) model for quantitative metallography.
  • To automate the detection and quantification of anomalies in alloy impurities.
  • To provide an end-to-end system that assists experts in material analysis.

Main Methods:

  • Deep semantic segmentation for identifying and masking inclusions.
  • Deep image inpainting to generate 'clean' images for grain analysis.
  • Deep anomaly detection and pattern recognition on inclusion masks for spatial and shape analysis.
  • Utilizing separate metallographic datasets for inclusions and grain boundaries.

Main Results:

  • An automated workflow for quantitative metallography, including anomaly detection.
  • Generation of inclusion masks and clean images for further analysis.
  • Identification of spatial, shape, and area anomalies in inclusions.
  • A system that recommends areas of interest to experts for focused examination.

Conclusions:

  • The developed AI model offers a powerful tool for automated quantitative metallography and anomaly detection in alloys.
  • The methodology can be generalized to other microscopy-based automation problems.
  • Publicly available code and datasets facilitate reproducibility and further research.