2D Microstructure Reconstruction for SEM via Non-local Patch-Based Image Inpainting

Anh Tran; Hoang Tran

doi:10.1007/978-3-030-65261-6_45

2D Microstructure Reconstruction for SEM via Non-local Patch-Based Image Inpainting

Anh Tran, Hoang Tran

Data Analysis and Machine Learning

Sandia National Laboratories, New Mexico

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Scopus citations

Abstract

Microstructure reconstruction is a long-standing problem in experimental and computational materials science, for which numerous attempts have been made to solve. However, the majority of approaches often treats microstructure as discrete phases, which, in turn, reduces the quality of the resulting microstructures and limits its usage to the computational level of fidelity, but not the experimental level of fidelity. In this work, we applied our previously proposed approach [41] to generate synthetic microstructure images at the experimental level of fidelity for the UltraHigh Carbon Steel DataBase (UHCSDB) [13].

Original language	English
Title of host publication	TMS 2021 150th Annual Meeting and Exhibition Supplemental Proceedings
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	495-506
Number of pages	12
ISBN (Print)	9783030652609
DOIs	https://doi.org/10.1007/978-3-030-65261-6_45
State	Published - 2021
Event	150th Annual Meeting and Exhibition of The Minerals, Metals and Materials Society, TMS 2021 - Pittsburgh, United States Duration: Mar 15 2021 → Mar 18 2021

Publication series

Name	Minerals, Metals and Materials Series
Volume	5
ISSN (Print)	2367-1181
ISSN (Electronic)	2367-1696

Conference

Conference	150th Annual Meeting and Exhibition of The Minerals, Metals and Materials Society, TMS 2021
Country/Territory	United States
City	Pittsburgh
Period	03/15/21 → 03/18/21

Bibliographical note

Publisher Copyright:
© 2021, The Minerals, Metals & Materials Society.

Keywords

Image inpainting
Image processing
Micrograph
Microstructure reconstruction
SEM

Access to Document

10.1007/978-3-030-65261-6_45

Cite this

@inproceedings{28a6ddea756e44fea7f8a85f2c8baf62,

title = "2D Microstructure Reconstruction for SEM via Non-local Patch-Based Image Inpainting",

abstract = "Microstructure reconstruction is a long-standing problem in experimental and computational materials science, for which numerous attempts have been made to solve. However, the majority of approaches often treats microstructure as discrete phases, which, in turn, reduces the quality of the resulting microstructures and limits its usage to the computational level of fidelity, but not the experimental level of fidelity. In this work, we applied our previously proposed approach [41] to generate synthetic microstructure images at the experimental level of fidelity for the UltraHigh Carbon Steel DataBase (UHCSDB) [13].",

keywords = "Image inpainting, Image processing, Micrograph, Microstructure reconstruction, SEM",

author = "Anh Tran and Hoang Tran",

note = "Publisher Copyright: {\textcopyright} 2021, The Minerals, Metals & Materials Society.; 150th Annual Meeting and Exhibition of The Minerals, Metals and Materials Society, TMS 2021 ; Conference date: 15-03-2021 Through 18-03-2021",

year = "2021",

doi = "10.1007/978-3-030-65261-6_45",

language = "English",

isbn = "9783030652609",

series = "Minerals, Metals and Materials Series",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "495--506",

booktitle = "TMS 2021 150th Annual Meeting and Exhibition Supplemental Proceedings",

}

Tran, A & Tran, H 2021, 2D Microstructure Reconstruction for SEM via Non-local Patch-Based Image Inpainting. in TMS 2021 150th Annual Meeting and Exhibition Supplemental Proceedings. Minerals, Metals and Materials Series, vol. 5, Springer Science and Business Media Deutschland GmbH, pp. 495-506, 150th Annual Meeting and Exhibition of The Minerals, Metals and Materials Society, TMS 2021, Pittsburgh, United States, 03/15/21. https://doi.org/10.1007/978-3-030-65261-6_45

2D Microstructure Reconstruction for SEM via Non-local Patch-Based Image Inpainting. / Tran, Anh; Tran, Hoang.
TMS 2021 150th Annual Meeting and Exhibition Supplemental Proceedings. Springer Science and Business Media Deutschland GmbH, 2021. p. 495-506 (Minerals, Metals and Materials Series; Vol. 5).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - 2D Microstructure Reconstruction for SEM via Non-local Patch-Based Image Inpainting

AU - Tran, Anh

AU - Tran, Hoang

PY - 2021

Y1 - 2021

N2 - Microstructure reconstruction is a long-standing problem in experimental and computational materials science, for which numerous attempts have been made to solve. However, the majority of approaches often treats microstructure as discrete phases, which, in turn, reduces the quality of the resulting microstructures and limits its usage to the computational level of fidelity, but not the experimental level of fidelity. In this work, we applied our previously proposed approach [41] to generate synthetic microstructure images at the experimental level of fidelity for the UltraHigh Carbon Steel DataBase (UHCSDB) [13].

AB - Microstructure reconstruction is a long-standing problem in experimental and computational materials science, for which numerous attempts have been made to solve. However, the majority of approaches often treats microstructure as discrete phases, which, in turn, reduces the quality of the resulting microstructures and limits its usage to the computational level of fidelity, but not the experimental level of fidelity. In this work, we applied our previously proposed approach [41] to generate synthetic microstructure images at the experimental level of fidelity for the UltraHigh Carbon Steel DataBase (UHCSDB) [13].

KW - Image inpainting

KW - Image processing

KW - Micrograph

KW - Microstructure reconstruction

KW - SEM

UR - http://www.scopus.com/inward/record.url?scp=85104380685&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-65261-6_45

DO - 10.1007/978-3-030-65261-6_45

M3 - Conference contribution

AN - SCOPUS:85104380685

SN - 9783030652609

T3 - Minerals, Metals and Materials Series

SP - 495

EP - 506

BT - TMS 2021 150th Annual Meeting and Exhibition Supplemental Proceedings

PB - Springer Science and Business Media Deutschland GmbH

T2 - 150th Annual Meeting and Exhibition of The Minerals, Metals and Materials Society, TMS 2021

Y2 - 15 March 2021 through 18 March 2021

ER -