Search research articles

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

Detecting muscle strain in professional football players through plasma myoglobin levels.

The Journal of sports medicine and physical fitness·2025

Same author

Plasma myoglobin indicates muscle damage associated with acceleration/deceleration during football.

The Journal of sports medicine and physical fitness·2023

Same author

Multidimensional cerebellar computations for flexible kinematic control of movements.

Nature communications·2023

Same author

Exploration of Chemical Space Guided by PixelCNN for Fragment-Based De Novo Drug Discovery.

Journal of chemical information and modeling·2022

Same author

Identification of microstructures critically affecting material properties using machine learning framework based on metallurgists' thinking process.

Scientific reports·2022

Same author

An interactive platform for detecting cerebellar complex spikes.

Journal of neurophysiology·2022

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Dec 5, 2025

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

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

Published on: August 13, 2014

Unsupervised microstructure segmentation by mimicking metallurgists' approach to pattern recognition.

Hoheok Kim¹, Junya Inoue^2,3, Tadashi Kasuya⁴

¹Institute for Industrial Science, The University of Tokyo, 4-6-1 Komaba, Meguro, Tokyo, 153-0041, Japan.

Scientific Reports

|October 21, 2020

Summary

This study introduces an unsupervised deep learning method for classifying low carbon steel microstructures without labeled images. The approach effectively segments steel textures using convolutional neural networks and superpixels.

More Related Videos

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Published on: March 3, 2023

Three-Dimensional Particle Shape Analysis Using X-ray Computed Tomography: Experimental Procedure and Analysis Algorithms for Metal Powders

Three-Dimensional Particle Shape Analysis Using X-ray Computed Tomography: Experimental Procedure and Analysis Algorithms for Metal Powders

Published on: December 4, 2020

Related Experiment Videos

Last Updated: Dec 5, 2025

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

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

Published on: August 13, 2014

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Published on: March 3, 2023

Three-Dimensional Particle Shape Analysis Using X-ray Computed Tomography: Experimental Procedure and Analysis Algorithms for Metal Powders

Three-Dimensional Particle Shape Analysis Using X-ray Computed Tomography: Experimental Procedure and Analysis Algorithms for Metal Powders

Published on: December 4, 2020

Area of Science:

Materials Science
Computer Science
Artificial Intelligence

Background:

Classifying steel microstructures is crucial for material property prediction.
Existing machine learning methods often require extensive labeled image datasets, posing a significant challenge.
Developing automated methods for microstructure analysis is essential for efficient material characterization.

Purpose of the Study:

To present an efficient deep learning method for distinguishing microstructures of low carbon steel.
To overcome the challenge of requiring vast labeled image datasets in microstructure classification.
To develop an unsupervised machine learning technique for steel microstructure segmentation.

Main Methods:

Utilized an unsupervised machine learning technique based on convolutional neural networks (CNNs).
Integrated a superpixel algorithm for image segmentation of steel microstructures.
Applied the method to optical microscopy images of low carbon steel with varying patterns and resolutions.

Main Results:

Successfully segmented low-carbon steel microstructures without the need for labeled images.
Demonstrated the effectiveness of the unsupervised deep learning method on diverse steel microstructure images.
Investigated various evaluation criteria for unsupervised segmentation and performed hyperparameter optimization.

Conclusions:

The proposed unsupervised deep learning method offers an efficient alternative for steel microstructure analysis.
This technique reduces the dependency on large labeled datasets, making microstructure classification more accessible.
The study highlights the potential of combining CNNs and superpixel algorithms for automated material science image analysis.