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 Experiment Videos

Aachen-Heerlen annotated steel microstructure dataset.

Deniz Iren1, Marc Ackermann2, Julian Gorfer3

  • 1Center for Actionable Research of Open Universiteit, Valkenburgerweg 177, 6419 AT, Heerlen, The Netherlands. deniz.iren@ou.nl.

Scientific Data
|May 27, 2021
PubMed
Summary
This summary is machine-generated.

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

Indexing the Event Calculus: Towards practical human-readable Personal Health Systems.

Artificial intelligence in medicine·2018
Same author

Type 2 Diabetes Patients Benefit from the COMODITY12 mHealth System: Results of a Randomised Trial.

Journal of medical systems·2016
Same author

Processing Diabetes Mellitus Composite Events in MAGPIE.

Journal of medical systems·2015
Same author

Performance comparison of multi-label learning algorithms on clinical data for chronic diseases.

Computers in biology and medicine·2015
Same author

Multi-label classification of chronically ill patients with bag of words and supervised dimensionality reduction algorithms.

Journal of biomedical informatics·2014
Same journal

Dataset of Optimized Structures of Aliphatic Chains Chemisorbed on Si(110) and Si(111) Surfaces via First-Principles Methods.

Scientific data·2026
Same journal

EURO-PROBE - Manual segmentations of the prostate and intraprostatic urethra on T2-weighted MRI.

Scientific data·2026
Same journal

Chromosome-Level Genome Assembly of Southern Africa Mozambique Tilapia (Oreochromis mossambicus) using PacBio HiFi and Omni-C sequencing.

Scientific data·2026
Same journal

Ovarian Stainology: Database of evidence-based immunohistochemical antigen expression in ovarian tumors.

Scientific data·2026
Same journal

A dataset of small protein conformational ensembles from all-atom molecular dynamics simulations.

Scientific data·2026
Same journal

A real-world Fitbit-derived dataset of activity, sleep, and heart rate with matched clinical factors in on-treatment lung cancer patients.

Scientific data·2026
See all related articles

This study introduces a new dataset of steel microstructures to train machine learning models for identifying Martensite-Austenite (MA) islands. This resource aids material scientists and computer vision experts in analyzing steel properties and developing advanced object segmentation techniques.

Area of Science:

  • Materials Science
  • Computer Vision
  • Machine Learning

Background:

  • Steel microstructure significantly influences mechanical properties.
  • Martensite-Austenite (MA) islands in bainitic steel have complex, hard-to-identify shapes.
  • Accurate detection of MA islands is crucial for understanding steel behavior.

Purpose of the Study:

  • To provide a high-quality dataset for training machine learning models.
  • To facilitate the automatic and accurate detection of MA islands in bainitic steel.
  • To support research linking steel morphology to mechanical characteristics.

Main Methods:

  • Compilation of 1,705 scanning electron microscopy images of bainitic steel.
  • Expert annotation of 8,909 polygons detailing MA island geometry.

Related Experiment Videos

  • Dataset creation for machine learning model training.

    • Main Results:

    • A comprehensive dataset of annotated scanning electron microscopy images.
    • Enables training of object segmentation models for abstract geometries.
    • Facilitates exploration of structure-property relationships in bainitic steel.

    Conclusions:

    • The dataset is valuable for both material science and computer vision research.
    • It advances the development of AI-driven tools for microstructure analysis.
    • Promotes deeper understanding of bainitic steel properties through advanced data analysis.