skip to main content
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

This content will become publicly available on October 1, 2020

Title: Data-driven high-fidelity 2D microstructure reconstruction via non-local patch-based image inpainting

Abstract

Microstructure reconstruction problems are usually limited to the representation with finitely many number of phases, e.g. binary and ternary. However, images of microstructure obtained through experimental, for example, using microscope, are often represented as a RGB or grayscale image. Because the phase-based representation is discrete, more rigid, and provides less flexibility in modeling the microstructure, as compared to RGB or grayscale image, there is a loss of information in the conversion. In this paper, a microstructure reconstruction method, which produces images at the fidelity of experimental microscopy, i.e. RGB or grayscale image, is proposed without introducing any physics-based microstructure descriptor. Furthermore, the image texture is preserved and the microstructure image is represented with continuous variables (as in RGB or grayscale images), instead of binary or categorical variables, which results in a high-fidelity image of microstructure reconstruction. The advantage of the proposed method is its quality of reconstruction, which can be applied to any other binary or multiphase 2D microstructure. The proposed method can be thought of as a subsampling approach to expand the microstructure dataset, while preserving its image texture. Moreover, the size of the reconstructed image is more flexible, compared to other machine learning microstructure reconstruction method, where themore » size must be fixed beforehand. In addition, the proposed method is capable of joining the microstructure images taken at different locations to reconstruct a larger microstructure image. A significant advantage of the proposed method is to remedy the data scarcity problem in materials science, where experimental data is scare and hard to obtain. The proposed method can also be applied to generate statistically equivalent microstructures, which has a strong implication in microstructure-related uncertainty quantification applications. The proposed microstructure reconstruction method is demonstrated with the UltraHigh Carbon Steel micrograph DataBase (UHCSDB).« less

Authors:
ORCiD logo [1];  [2]
  1. Sandia National Lab. (SNL-CA), Livermore, CA (United States)
  2. Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
Publication Date:
Research Org.:
Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
Sponsoring Org.:
USDOE National Nuclear Security Administration (NNSA)
OSTI Identifier:
1559517
Alternate Identifier(s):
OSTI ID: 1564177
Report Number(s):
SAND2019-9514J
Journal ID: ISSN 1359-6454; 678480
Grant/Contract Number:  
AC04-94AL85000; AC05-00OR22725
Resource Type:
Accepted Manuscript
Journal Name:
Acta Materialia
Additional Journal Information:
Journal Volume: 178; Journal Issue: C; Journal ID: ISSN 1359-6454
Publisher:
Elsevier
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING

Citation Formats

Tran, Anh, and Tran, Hoang. Data-driven high-fidelity 2D microstructure reconstruction via non-local patch-based image inpainting. United States: N. p., 2019. Web. doi:10.1016/j.actamat.2019.08.007.
Tran, Anh, & Tran, Hoang. Data-driven high-fidelity 2D microstructure reconstruction via non-local patch-based image inpainting. United States. doi:10.1016/j.actamat.2019.08.007.
Tran, Anh, and Tran, Hoang. Tue . "Data-driven high-fidelity 2D microstructure reconstruction via non-local patch-based image inpainting". United States. doi:10.1016/j.actamat.2019.08.007.
@article{osti_1559517,
title = {Data-driven high-fidelity 2D microstructure reconstruction via non-local patch-based image inpainting},
author = {Tran, Anh and Tran, Hoang},
abstractNote = {Microstructure reconstruction problems are usually limited to the representation with finitely many number of phases, e.g. binary and ternary. However, images of microstructure obtained through experimental, for example, using microscope, are often represented as a RGB or grayscale image. Because the phase-based representation is discrete, more rigid, and provides less flexibility in modeling the microstructure, as compared to RGB or grayscale image, there is a loss of information in the conversion. In this paper, a microstructure reconstruction method, which produces images at the fidelity of experimental microscopy, i.e. RGB or grayscale image, is proposed without introducing any physics-based microstructure descriptor. Furthermore, the image texture is preserved and the microstructure image is represented with continuous variables (as in RGB or grayscale images), instead of binary or categorical variables, which results in a high-fidelity image of microstructure reconstruction. The advantage of the proposed method is its quality of reconstruction, which can be applied to any other binary or multiphase 2D microstructure. The proposed method can be thought of as a subsampling approach to expand the microstructure dataset, while preserving its image texture. Moreover, the size of the reconstructed image is more flexible, compared to other machine learning microstructure reconstruction method, where the size must be fixed beforehand. In addition, the proposed method is capable of joining the microstructure images taken at different locations to reconstruct a larger microstructure image. A significant advantage of the proposed method is to remedy the data scarcity problem in materials science, where experimental data is scare and hard to obtain. The proposed method can also be applied to generate statistically equivalent microstructures, which has a strong implication in microstructure-related uncertainty quantification applications. The proposed microstructure reconstruction method is demonstrated with the UltraHigh Carbon Steel micrograph DataBase (UHCSDB).},
doi = {10.1016/j.actamat.2019.08.007},
journal = {Acta Materialia},
number = C,
volume = 178,
place = {United States},
year = {2019},
month = {10}
}

Journal Article:
Free Publicly Available Full Text
This content will become publicly available on October 1, 2020
Publisher's Version of Record

Save / Share: