Search Menu
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information
Search Scholarly Publications

Title: Interactive volumetric segmentation for textile micro-tomography data using wavelets and nonlocal means

Abstract

This work addresses segmentation of volumetric images of woven carbon fiber textiles from micro-tomography data. We propose a semi-supervised algorithm to classify carbon fibers that requires sparse input as opposed to completely labeled images. The main contributions are: (a) design of effective discriminative classifiers, for three-dimensional textile samples, trained on wavelet features for segmentation; (b) coupling of previous step with nonlocal means as simple, efficient alternative to the Potts model; and (c) demonstration of reuse of classifier to diverse samples containing similar content. We evaluate our work by curating test sets of voxels in the absence of a complete ground truth mask. The algorithm obtains an average 0.95 F1 score on test sets and average F1 score of 0.93 on new samples. Finally, we conclude with discussion of failure cases and propose future directions toward analysis of spatiotemporal high-resolution micro-tomography images.

Authors:
ORCiD logo [1];  [2];  [3];  [3];  [4];  [4]
+ Show Author Affiliations
  1. Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
  2. Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); Univ. of California, Berkeley, CA (United States)
  3. NASA Ames Research Center, Moffett Field, CA (United States)
  4. Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States). Advanced Light Source (ALS)
Publication Date:
Research Org.:
Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
Sponsoring Org.:
USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR)
OSTI Identifier:
1597715
Alternate Identifier(s):
OSTI ID: 1527203
Grant/Contract Number:  
AC02-05CH11231; AC02‐05CH11231
Resource Type:
Accepted Manuscript
Journal Name:
Statistical Analysis and Data Mining
Additional Journal Information:
Journal Volume: 12; Journal Issue: 4; Journal ID: ISSN 1932-1864
Publisher:
Wiley
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING; 3D image processing; 3D segmentation; 3D woven carbon fiber; composites; machine learning; microCT; neural networks

Citation Formats

MacNeil, J. Michael L., Ushizima, Daniela M., Panerai, Francesco, Mansour, Nagi N., Barnard, Harold S., and Parkinson, Dilworth Y. Interactive volumetric segmentation for textile micro-tomography data using wavelets and nonlocal means. United States: N. p., 2019. Web. doi:10.1002/sam.11429.
Copy to clipboard
MacNeil, J. Michael L., Ushizima, Daniela M., Panerai, Francesco, Mansour, Nagi N., Barnard, Harold S., & Parkinson, Dilworth Y. Interactive volumetric segmentation for textile micro-tomography data using wavelets and nonlocal means. United States. https://doi.org/10.1002/sam.11429
Copy to clipboard
MacNeil, J. Michael L., Ushizima, Daniela M., Panerai, Francesco, Mansour, Nagi N., Barnard, Harold S., and Parkinson, Dilworth Y. Thu . "Interactive volumetric segmentation for textile micro-tomography data using wavelets and nonlocal means". United States. https://doi.org/10.1002/sam.11429. https://www.osti.gov/servlets/purl/1597715.
Copy to clipboard
@article{osti_1597715,
title = {Interactive volumetric segmentation for textile micro-tomography data using wavelets and nonlocal means},
author = {MacNeil, J. Michael L. and Ushizima, Daniela M. and Panerai, Francesco and Mansour, Nagi N. and Barnard, Harold S. and Parkinson, Dilworth Y.},
abstractNote = {This work addresses segmentation of volumetric images of woven carbon fiber textiles from micro-tomography data. We propose a semi-supervised algorithm to classify carbon fibers that requires sparse input as opposed to completely labeled images. The main contributions are: (a) design of effective discriminative classifiers, for three-dimensional textile samples, trained on wavelet features for segmentation; (b) coupling of previous step with nonlocal means as simple, efficient alternative to the Potts model; and (c) demonstration of reuse of classifier to diverse samples containing similar content. We evaluate our work by curating test sets of voxels in the absence of a complete ground truth mask. The algorithm obtains an average 0.95 F1 score on test sets and average F1 score of 0.93 on new samples. Finally, we conclude with discussion of failure cases and propose future directions toward analysis of spatiotemporal high-resolution micro-tomography images.},
doi = {10.1002/sam.11429},
journal = {Statistical Analysis and Data Mining},
number = 4,
volume = 12,
place = {United States},
year = {Thu Jun 20 00:00:00 EDT 2019},
month = {Thu Jun 20 00:00:00 EDT 2019}
}
Copy to clipboard
Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record
https://doi.org/10.1002/sam.11429
Copyright Statement
Other availability
Search WorldCat Search WorldCat to find libraries that may hold this journal
Citation Metrics:
Cited by: 5 works
Citation information provided by
Web of Science

Figures / Tables:

FIGURE 1 FIGURE 1: Investigation of image analysis workflows for X-ray microCT data: white boxes indicate common steps among approaches, gray indicates points of pipeline divergence. Each color implies a specific machine learning classifier used to create a different segmentation of warp and weft partitions; orange: RF1 with Gabor+Hessian, magenta: RF2 withmore » LBP, and the modules of the proposed method in blue: NN with NLM.« less
All figures and tables (18 total)
Save / Share:
Export Metadata
Save to My Library
You must Sign In or Create an Account in order to save documents to your library.

Works referenced in this record:

Automating cell detection and classification in human brain fluorescent microscopy images using dictionary learning and sparse coding
journal, April 2017

Towards a coherent statistical framework for dense deformable template estimation
journal, February 2007

  • Allassonnière, S.; Amit, Y.; Trouvé, A.
  • Journal of the Royal Statistical Society: Series B (Statistical Methodology), Vol. 69, Issue 1
  • DOI: 10.1111/j.1467-9868.2007.00574.x

Real-time quantitative imaging of failure events in materials under load at temperatures above 1,600 °C
journal, December 2012

  • Bale, Hrishikesh A.; Haboub, Abdel; MacDowell, Alastair A.
  • Nature Materials, Vol. 12, Issue 1
  • DOI: 10.1038/nmat3497

Convex Optimization
book, January 2004

Random Forests
journal, January 2001

Fast Cartoon + Texture Image Filters
journal, August 2010

  • Buades, Antoni; Le, Triet M.; Morel, Jean-Michel
  • IEEE Transactions on Image Processing, Vol. 19, Issue 8
  • DOI: 10.1109/TIP.2010.2046605

User interactive segmentation with partially growing random forest
conference, September 2015

  • Choi, Jongwon; Choi, Jin Young
  • 2015 IEEE International Conference on Image Processing (ICIP)
  • DOI: 10.1109/ICIP.2015.7350968

Describing Textures in the Wild
conference, June 2014

  • Cimpoi, Mircea; Maji, Subhransu; Kokkinos, Iasonas
  • 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • DOI: 10.1109/CVPR.2014.461

PuMA: the Porous Microstructure Analysis software
journal, January 2018

Reverse image search for scientific data within and beyond the visible spectrum
journal, November 2018

  • Araujo, Flavio H. D.; Silva, Romuere R. V.; Medeiros, Fatima N. S.
  • Expert Systems with Applications, Vol. 109
  • DOI: 10.1016/j.eswa.2018.05.015

Geodesic star convexity for interactive image segmentation
conference, June 2010

  • Gulshan, Varun; Rother, Carsten; Criminisi, Antonio
  • 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • DOI: 10.1109/CVPR.2010.5540073

TomoPy: a framework for the analysis of synchrotron tomographic data
journal, August 2014

  • Gürsoy, Dogˇa; De Carlo, Francesco; Xiao, Xianghui
  • Journal of Synchrotron Radiation, Vol. 21, Issue 5
  • DOI: 10.1107/S1600577514013939

A convolutional neural network-based screening tool for X-ray serial crystallography
journal, April 2018

  • Ke, Tsung-Wei; Brewster, Aaron S.; Yu, Stella X.
  • Journal of Synchrotron Radiation, Vol. 25, Issue 3, p. 655-670
  • DOI: 10.1107/S1600577518004873

Insights from in-situ X-ray computed tomography during axial impregnation of unidirectional fiber beds
journal, April 2018

Spatially Varying Color Distributions for Interactive Multilabel Segmentation
journal, May 2013

  • Nieuwenhuis, Claudia; Cremers, Daniel
  • IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 35, Issue 5
  • DOI: 10.1109/TPAMI.2012.183

A Survey and Comparison of Discrete and Continuous Multi-label Optimization Approaches for the Potts Model
journal, April 2013

  • Nieuwenhuis, Claudia; Töppe, Eno; Cremers, Daniel
  • International Journal of Computer Vision, Vol. 104, Issue 3
  • DOI: 10.1007/s11263-013-0619-y

Evaluation of the anisotropic radiative conductivity of a low-density carbon fiber material from realistic microscale imaging
journal, April 2016

Micro-tomography based analysis of thermal conductivity, diffusivity and oxidation behavior of rigid and flexible fibrous insulators
journal, May 2017

A mixed-scale dense convolutional neural network for image analysis
journal, December 2017

  • Pelt, Daniël M.; Sethian, James A.
  • Proceedings of the National Academy of Sciences, Vol. 115, Issue 2
  • DOI: 10.1073/pnas.1715832114

A convex relaxation approach for computing minimal partitions
conference, June 2009

  • Pock, T.; Chambolle, A.; Cremers, D.
  • 2009 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • DOI: 10.1109/CVPRW.2009.5206604

Globally optimal stitching of tiled 3D microscopic image acquisitions
journal, April 2009

Learning a classification model for segmentation
conference, January 2003

"GrabCut": interactive foreground extraction using iterated graph cuts
journal, August 2004

  • Rother, Carsten; Kolmogorov, Vladimir; Blake, Andrew
  • ACM Transactions on Graphics, Vol. 23, Issue 3
  • DOI: 10.1145/1015706.1015720

The sketchy database: learning to retrieve badly drawn bunnies
journal, July 2016

  • Sangkloy, Patsorn; Burnell, Nathan; Ham, Cusuh
  • ACM Transactions on Graphics, Vol. 35, Issue 4
  • DOI: 10.1145/2897824.2925954

Interactive Texture Segmentation using Random Forests and Total Variation
conference, January 2009

  • Santner, Jakob; Unger, Markus; Pock, Thomas
  • Procedings of the British Machine Vision Conference 2009
  • DOI: 10.5244/C.23.66

Fiji: an open-source platform for biological-image analysis
journal, June 2012

  • Schindelin, Johannes; Arganda-Carreras, Ignacio; Frise, Erwin
  • Nature Methods, Vol. 9, Issue 7
  • DOI: 10.1038/nmeth.2019

IDEAL: Images Across Domains, Experiments, Algorithms and Learning
journal, September 2016

Stochastic characterisation methodology for 3-D textiles based on micro-tomography
journal, August 2017

Shape prior segmentation of multiple objects with graph cuts
conference, June 2008

  • Vu, Nhat; Manjunath, B. S.
  • 2008 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • DOI: 10.1109/CVPR.2008.4587450

miRNALoc: predicting miRNA subcellular localizations based on principal component scores of physico-chemical properties and pseudo compositions of di-nucleotides
journal, September 2020

  • Meher, Prabina Kumar; Satpathy, Subhrajit; Rao, Atmakuri Ramakrishna
  • Scientific Reports, Vol. 10, Issue 1
  • DOI: 10.1038/s41598-020-71381-4

Convex Multi-Class Image Labeling by Simplex-Constrained Total Variation
text, January 2008

TomoPy: A framework for the analysis of synchrotron tomographic data
conference, September 2014

  • Gürsoy, Doğa; De Carlo, Francesco; Xiao, Xianghui
  • SPIE Optical Engineering + Applications, SPIE Proceedings
  • DOI: 10.1117/12.2061373

"GrabCut": interactive foreground extraction using iterated graph cuts
conference, January 2004

  • Rother, Carsten; Kolmogorov, Vladimir; Blake, Andrew
  • ACM SIGGRAPH 2004 Papers on - SIGGRAPH '04
  • DOI: 10.1145/1186562.1015720

Describing Textures in the Wild
preprint, January 2013

    Sort by:
    [ × clear filter / sort ]

    Figures / Tables found in this record:

    FIGURE 1 (p. 4)figure
    FIGURE 2 (p. 4)figure
    FIGURE 3 (p. 5)figure
    FIGURE 4 (p. 7)figure
    TABLE 1 (p. 8)table
    FIGURE 5 (p. 9)figure
    TABLE 2 (p. 9)table
    TABLE 3 (p. 10)table
    TABLE 4 (p. 10)table
    FIGURE 6 (p. 11)figure
    TABLE 10 (p. 12)table
    TABLE 5 (p. 12)table
    TABLE 6 (p. 12)table
    TABLE 7 (p. 12)table
    TABLE 8 (p. 12)table
    TABLE 9 (p. 12)table
    FIGURE 7 (p. 13)figure
    FIGURE 8 (p. 14)figure
      [ × clear filter / sort ]
      Figures/Tables have been extracted from DOE-funded journal article accepted manuscripts.

      Similar Records in DOE PAGES and OSTI.GOV collections: