Complex-Phase Steel Microstructure Segmentation Using UNet: Analysis across Different Magnifications and Steel Types
The quantification of the phase fraction is critical in materials science, bridging the gap between material composition, processing techniques, microstructure, and resultant properties. Traditional methods involving manual annotation are precise but labor-intensive and prone to human inaccuracies....
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-11-01
|
Series: | Materials |
Subjects: | |
Online Access: | https://www.mdpi.com/1996-1944/16/23/7254 |
_version_ | 1797399946397220864 |
---|---|
author | Bishal Ranjan Swain Dahee Cho Joongcheul Park Jae-Seung Roh Jaepil Ko |
author_facet | Bishal Ranjan Swain Dahee Cho Joongcheul Park Jae-Seung Roh Jaepil Ko |
author_sort | Bishal Ranjan Swain |
collection | DOAJ |
description | The quantification of the phase fraction is critical in materials science, bridging the gap between material composition, processing techniques, microstructure, and resultant properties. Traditional methods involving manual annotation are precise but labor-intensive and prone to human inaccuracies. We propose an automated segmentation technique for high-tensile strength alloy steel, where the complexity of microstructures presents considerable challenges. Our method leverages the UNet architecture, originally developed for biomedical image segmentation, and optimizes its performance via careful hyper-parameter selection and data augmentation. We employ Electron Backscatter Diffraction (EBSD) imagery for complex-phase segmentation and utilize a combined loss function to capture both textural and structural characteristics of the microstructures. Additionally, this work is the first to examine the scalability of the model across varying magnifications and types of steel and achieves high accuracy in terms of dice scores demonstrating the adaptability and robustness of the model. |
first_indexed | 2024-03-09T01:48:29Z |
format | Article |
id | doaj.art-fc4dc879dbd146ee954662cb03b0bb9b |
institution | Directory Open Access Journal |
issn | 1996-1944 |
language | English |
last_indexed | 2024-03-09T01:48:29Z |
publishDate | 2023-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Materials |
spelling | doaj.art-fc4dc879dbd146ee954662cb03b0bb9b2023-12-08T15:20:21ZengMDPI AGMaterials1996-19442023-11-011623725410.3390/ma16237254Complex-Phase Steel Microstructure Segmentation Using UNet: Analysis across Different Magnifications and Steel TypesBishal Ranjan Swain0Dahee Cho1Joongcheul Park2Jae-Seung Roh3Jaepil Ko4Department of Computer & AI Convergence Engineering, Kumoh National Institute of Technology, Gumi-si 39177, Republic of KoreaResearch Institute of Science and Technology, Pohang-si 790660, Republic of KoreaResearch Institute of Science and Technology, Pohang-si 790660, Republic of KoreaSchool of Materials Science and Engineering, Kumoh National Institute of Technology, Gumi-si 39177, Republic of KoreaDepartment of Computer & AI Convergence Engineering, Kumoh National Institute of Technology, Gumi-si 39177, Republic of KoreaThe quantification of the phase fraction is critical in materials science, bridging the gap between material composition, processing techniques, microstructure, and resultant properties. Traditional methods involving manual annotation are precise but labor-intensive and prone to human inaccuracies. We propose an automated segmentation technique for high-tensile strength alloy steel, where the complexity of microstructures presents considerable challenges. Our method leverages the UNet architecture, originally developed for biomedical image segmentation, and optimizes its performance via careful hyper-parameter selection and data augmentation. We employ Electron Backscatter Diffraction (EBSD) imagery for complex-phase segmentation and utilize a combined loss function to capture both textural and structural characteristics of the microstructures. Additionally, this work is the first to examine the scalability of the model across varying magnifications and types of steel and achieves high accuracy in terms of dice scores demonstrating the adaptability and robustness of the model.https://www.mdpi.com/1996-1944/16/23/7254steel microstructurephase fraction calculationUNet segmentationEBSD segmentation |
spellingShingle | Bishal Ranjan Swain Dahee Cho Joongcheul Park Jae-Seung Roh Jaepil Ko Complex-Phase Steel Microstructure Segmentation Using UNet: Analysis across Different Magnifications and Steel Types Materials steel microstructure phase fraction calculation UNet segmentation EBSD segmentation |
title | Complex-Phase Steel Microstructure Segmentation Using UNet: Analysis across Different Magnifications and Steel Types |
title_full | Complex-Phase Steel Microstructure Segmentation Using UNet: Analysis across Different Magnifications and Steel Types |
title_fullStr | Complex-Phase Steel Microstructure Segmentation Using UNet: Analysis across Different Magnifications and Steel Types |
title_full_unstemmed | Complex-Phase Steel Microstructure Segmentation Using UNet: Analysis across Different Magnifications and Steel Types |
title_short | Complex-Phase Steel Microstructure Segmentation Using UNet: Analysis across Different Magnifications and Steel Types |
title_sort | complex phase steel microstructure segmentation using unet analysis across different magnifications and steel types |
topic | steel microstructure phase fraction calculation UNet segmentation EBSD segmentation |
url | https://www.mdpi.com/1996-1944/16/23/7254 |
work_keys_str_mv | AT bishalranjanswain complexphasesteelmicrostructuresegmentationusingunetanalysisacrossdifferentmagnificationsandsteeltypes AT daheecho complexphasesteelmicrostructuresegmentationusingunetanalysisacrossdifferentmagnificationsandsteeltypes AT joongcheulpark complexphasesteelmicrostructuresegmentationusingunetanalysisacrossdifferentmagnificationsandsteeltypes AT jaeseungroh complexphasesteelmicrostructuresegmentationusingunetanalysisacrossdifferentmagnificationsandsteeltypes AT jaepilko complexphasesteelmicrostructuresegmentationusingunetanalysisacrossdifferentmagnificationsandsteeltypes |