skip to main content

DOE PAGESDOE PAGES

Title: Automated defect analysis in electron microscopic images

Electron microscopy and defect analysis are a cornerstone of materials science, as they offer detailed insights on the microstructure and performance of a wide range of materials and material systems. Building a robust and flexible platform for automated defect recognition and classification in electron microscopy will result in the completion of analysis orders of magnitude faster after images are recorded, or even online during image acquisition. Automated analysis has the potential to be significantly more efficient, accurate, and repeatable than human analysis, and it can scale with the increasingly important methods of automated data generation. Herein, an automated recognition tool is developed based on a computer vison–based approach; it sequentially applies a cascade object detector, convolutional neural network, and local image analysis methods. We demonstrate that the automated tool performs as well as or better than manual human detection in terms of recall and precision and achieves quantitative image/defect analysis metrics close to the human average. The proposed approach works for images of varying contrast, brightness, and magnification. Furthermore, these promising results suggest that this and similar approaches are worth exploring for detecting multiple defect types and have the potential to locate, classify, and measure quantitative features for a rangemore » of defect types, materials, and electron microscopic techniques.« less
Authors:
ORCiD logo [1] ; ORCiD logo [2] ; ORCiD logo [1]
  1. Univ. of Wisconsin, Madison, WI (United States)
  2. Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
Publication Date:
Grant/Contract Number:
AC05-00OR22725
Type:
Accepted Manuscript
Journal Name:
npj Computational Materials
Additional Journal Information:
Journal Volume: 4; Journal Issue: 1; Journal ID: ISSN 2057-3960
Publisher:
Nature Publishing Group
Research Org:
Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
Sponsoring Org:
USDOE
Country of Publication:
United States
Language:
English
Subject:
47 OTHER INSTRUMENTATION
OSTI Identifier:
1462882

Li, Wei, Field, Kevin G., and Morgan, Dane. Automated defect analysis in electron microscopic images. United States: N. p., Web. doi:10.1038/s41524-018-0093-8.
Li, Wei, Field, Kevin G., & Morgan, Dane. Automated defect analysis in electron microscopic images. United States. doi:10.1038/s41524-018-0093-8.
Li, Wei, Field, Kevin G., and Morgan, Dane. 2018. "Automated defect analysis in electron microscopic images". United States. doi:10.1038/s41524-018-0093-8. https://www.osti.gov/servlets/purl/1462882.
@article{osti_1462882,
title = {Automated defect analysis in electron microscopic images},
author = {Li, Wei and Field, Kevin G. and Morgan, Dane},
abstractNote = {Electron microscopy and defect analysis are a cornerstone of materials science, as they offer detailed insights on the microstructure and performance of a wide range of materials and material systems. Building a robust and flexible platform for automated defect recognition and classification in electron microscopy will result in the completion of analysis orders of magnitude faster after images are recorded, or even online during image acquisition. Automated analysis has the potential to be significantly more efficient, accurate, and repeatable than human analysis, and it can scale with the increasingly important methods of automated data generation. Herein, an automated recognition tool is developed based on a computer vison–based approach; it sequentially applies a cascade object detector, convolutional neural network, and local image analysis methods. We demonstrate that the automated tool performs as well as or better than manual human detection in terms of recall and precision and achieves quantitative image/defect analysis metrics close to the human average. The proposed approach works for images of varying contrast, brightness, and magnification. Furthermore, these promising results suggest that this and similar approaches are worth exploring for detecting multiple defect types and have the potential to locate, classify, and measure quantitative features for a range of defect types, materials, and electron microscopic techniques.},
doi = {10.1038/s41524-018-0093-8},
journal = {npj Computational Materials},
number = 1,
volume = 4,
place = {United States},
year = {2018},
month = {7}
}

Works referenced in this record:

Rapid object detection using a boosted cascade of simple features
conference, January 2001
  • Viola, P.; Jones, M.
  • Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001
  • DOI: 10.1109/CVPR.2001.990517