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

Title: Machine vision-driven automatic recognition of particle size and morphology in SEM images

Abstract

Scanning Electron Microscopy (SEM) images provide a variety of structural and morphological information of the nanomaterials. In the material informatics domain, automatic recognition and quantitative analysis of SEM images in a high-throughput manner are critical, but challenges still remain due to the complexity and the diversity of the image configurations in both shape and size. In this paper, we present a generally applicable approach using computer vision and machine learning techniques to quantitatively extract particle size, size distribution and morphology information in SEM images. The proposed pipeline offers automatic, high-throughput measurements even when overlapping nanoparticles, rod-shapes, and core-shell nanostructures are present. We demonstrate effectiveness of the proposed approach by performing experiments on SEM images of nanoscale materials and structures with different shapes and sizes. The proposed approach shows promising results (Spearman coefficients of 0.91 and 0.99 using the fully automated and semi-automated processes, respectively) when compared with manually measured sizes.

Authors:
ORCiD logo [1]; ORCiD logo [2]; ORCiD logo [2]
  1. Center for Applied Scientific Computing, Lawrence Livermore National Laboratory, USA
  2. Materials Science Division, Lawrence Livermore National Laboratory, USA
Publication Date:
Research Org.:
Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
Sponsoring Org.:
USDOE National Nuclear Security Administration (NNSA); USDOE Laboratory Directed Research and Development (LDRD) Program
OSTI Identifier:
1664530
Alternate Identifier(s):
OSTI ID: 1651192
Report Number(s):
LLNL-JRNL-809488
Journal ID: ISSN 2040-3364; NANOHL
Grant/Contract Number:  
16-ERD-019; 19-SI-001; AC52-07NA27344
Resource Type:
Journal Article: Published Article
Journal Name:
Nanoscale
Additional Journal Information:
Journal Name: Nanoscale Journal Volume: 12 Journal Issue: 37; Journal ID: ISSN 2040-3364
Publisher:
Royal Society of Chemistry (RSC)
Country of Publication:
United Kingdom
Language:
English
Subject:
High-throughput pipeline; Nanoparticle structure recognition; Size measurement; Shape recognition; Morphology recognition; SEM; Machine learning; Computer vision; Machine vision

Citation Formats

Kim, Hyojin, Han, Jinkyu, and Han, T. Yong-Jin. Machine vision-driven automatic recognition of particle size and morphology in SEM images. United Kingdom: N. p., 2020. Web. doi:10.1039/D0NR04140H.
Kim, Hyojin, Han, Jinkyu, & Han, T. Yong-Jin. Machine vision-driven automatic recognition of particle size and morphology in SEM images. United Kingdom. doi:10.1039/D0NR04140H.
Kim, Hyojin, Han, Jinkyu, and Han, T. Yong-Jin. Thu . "Machine vision-driven automatic recognition of particle size and morphology in SEM images". United Kingdom. doi:10.1039/D0NR04140H.
@article{osti_1664530,
title = {Machine vision-driven automatic recognition of particle size and morphology in SEM images},
author = {Kim, Hyojin and Han, Jinkyu and Han, T. Yong-Jin},
abstractNote = {Scanning Electron Microscopy (SEM) images provide a variety of structural and morphological information of the nanomaterials. In the material informatics domain, automatic recognition and quantitative analysis of SEM images in a high-throughput manner are critical, but challenges still remain due to the complexity and the diversity of the image configurations in both shape and size. In this paper, we present a generally applicable approach using computer vision and machine learning techniques to quantitatively extract particle size, size distribution and morphology information in SEM images. The proposed pipeline offers automatic, high-throughput measurements even when overlapping nanoparticles, rod-shapes, and core-shell nanostructures are present. We demonstrate effectiveness of the proposed approach by performing experiments on SEM images of nanoscale materials and structures with different shapes and sizes. The proposed approach shows promising results (Spearman coefficients of 0.91 and 0.99 using the fully automated and semi-automated processes, respectively) when compared with manually measured sizes.},
doi = {10.1039/D0NR04140H},
journal = {Nanoscale},
issn = {2040-3364},
number = 37,
volume = 12,
place = {United Kingdom},
year = {2020},
month = {10}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record at 10.1039/D0NR04140H

Save / Share:

Works referenced in this record:

High-Throughput, Algorithmic Determination of Nanoparticle Structure from Electron Microscopy Images
journal, October 2015

  • Laramy, Christine R.; Brown, Keith A.; O’Brien, Matthew N.
  • ACS Nano, Vol. 9, Issue 12
  • DOI: 10.1021/acsnano.5b05968

Advanced Steel Microstructural Classification by Deep Learning Methods
journal, February 2018


Survey over image thresholding techniques and quantitative performance evaluation
journal, January 2004

  • Sankur, Bu¨lent
  • Journal of Electronic Imaging, Vol. 13, Issue 1
  • DOI: 10.1117/1.1631315

A Machine Learning-Based Design Representation Method for Designing Heterogeneous Microstructures
journal, May 2015

  • Xu, Hongyi; Liu, Ruoqian; Choudhary, Alok
  • Journal of Mechanical Design, Vol. 137, Issue 5
  • DOI: 10.1115/1.4029768

Neural Network for Nanoscience Scanning Electron Microscope Image Recognition
journal, October 2017


RACE-Net: A Recurrent Neural Network for Biomedical Image Segmentation
journal, May 2019

  • Chakravarty, Arunava; Sivaswamy, Jayanthi
  • IEEE Journal of Biomedical and Health Informatics, Vol. 23, Issue 3
  • DOI: 10.1109/JBHI.2018.2852635

ICDAR 2015 competition on Robust Reading
conference, August 2015

  • Karatzas, Dimosthenis; Gomez-Bigorda, Lluis; Nicolaou, Anguelos
  • 2015 13th International Conference on Document Analysis and Recognition (ICDAR)
  • DOI: 10.1109/ICDAR.2015.7333942

Resolution enhancement in scanning electron microscopy using deep learning
journal, August 2019


An Overview of Watershed Algorithm Implementations in Open Source Libraries
journal, October 2018


NIH Image to ImageJ: 25 years of image analysis
journal, June 2012

  • Schneider, Caroline A.; Rasband, Wayne S.; Eliceiri, Kevin W.
  • Nature Methods, Vol. 9, Issue 7
  • DOI: 10.1038/nmeth.2089

Application of Image Processing to Determine Size Distribution of Magnetic Nanoparticles
journal, September 2013


High-throughput, algorithmic determination of pore parameters from electron microscopy
journal, January 2020


Shape and aspect ratio analysis of anisotropic magnetic nanochains based on TEM micrographs
journal, August 2018


A new method for measuring nanoparticle diameter from a set of SEM images using a remarkable point
journal, December 2019


Deep Learning Techniques for Medical Image Segmentation: Achievements and Challenges
journal, May 2019

  • Hesamian, Mohammad Hesam; Jia, Wenjing; He, Xiangjian
  • Journal of Digital Imaging, Vol. 32, Issue 4
  • DOI: 10.1007/s10278-019-00227-x