Hostname: page-component-7bb8b95d7b-5mhkq Total loading time: 0 Render date: 2024-10-01T12:14:54.378Z Has data issue: false hasContentIssue false

DefectNet – A Deep Convolutional Neural Network for Semantic Segmentation of Crystallographic Defects in Advanced Microscopy Images

Published online by Cambridge University Press:  05 August 2019

Graham Roberts
Affiliation:
Nuclear Sciences Division, Pacific Northwest National Laboratory, Richland, WA 99352, USA
Rajat Sainju
Affiliation:
Department of Materials Science and Engineering, Institute of Materials Science, University of Connecticut, Storrs, CT 06269, USA
Brian Hutchinson
Affiliation:
Computer Science Department, Western Washington University, Bellingham, WA 98225, USA Computing & Analytics Division, Pacific Northwest National Laboratory, Richland, WA 99352, USA
Mychailo B. Toloczko
Affiliation:
Nuclear Sciences Division, Pacific Northwest National Laboratory, Richland, WA 99352, USA
Danny J. Edwards
Affiliation:
Nuclear Sciences Division, Pacific Northwest National Laboratory, Richland, WA 99352, USA
Yuanyuan Zhu*
Affiliation:
Nuclear Sciences Division, Pacific Northwest National Laboratory, Richland, WA 99352, USA Department of Materials Science and Engineering, Institute of Materials Science, University of Connecticut, Storrs, CT 06269, USA
*
*Corresponding author: yuanyuan.2.zhu@uconn.edu

Abstract

Image of the first page of this content. For PDF version, please use the ‘Save PDF’ preceeding this image.'
Type
Data Acquisition Schemes, Machine Learning Algorithms, and Open Source Software Development for Electron Microscopy
Copyright
Copyright © Microscopy Society of America 2019 

References

[1]Roberts, G, Haile, SY, Sainju, R, Patel, D, Edwards, DJ, Hutchinson, B and Zhu, Y. in preparationGoogle Scholar
[2]Zhu, Y, Ophus, C, Toloczko, MB and Edwards, DJ, Ultramicroscopy, 193(2018) 12-23.Google Scholar
[3]Authors thank Dr. Colin Ophus, Mr. Deep Patel and Mr. Simon Y. Haile for supporting image labeling and CNN training. We acknowledge funding from the U.S. DOE Office of Fusion Energy Sciences under contract DE-AC05-76RL01830, Office of Nuclear Energy's Nuclear Energy Enabling Technologies program project CFA 16-10570, PNNL Research Computing program and the Nvidia Corporation for the GPUs used in this research.Google Scholar