DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

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

Journal Article · · Statistical Analysis and Data Mining
DOI: https://doi.org/10.1002/sam.11429 · OSTI ID:1597715
ORCiD logo [1];  [2];  [3];  [3];  [4];  [4]
  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)

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.

Research Organization:
Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
Sponsoring Organization:
USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR)
Grant/Contract Number:
AC02-05CH11231; AC02‐05CH11231
OSTI ID:
1597715
Alternate ID(s):
OSTI ID: 1527203
Journal Information:
Statistical Analysis and Data Mining, Vol. 12, Issue 4; ISSN 1932-1864
Publisher:
WileyCopyright Statement
Country of Publication:
United States
Language:
English
Citation Metrics:
Cited by: 5 works
Citation information provided by
Web of Science

References (34)

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
Real-time quantitative imaging of failure events in materials under load at temperatures above 1,600 °C journal December 2012
Convex Optimization book January 2004
Random Forests journal January 2001
Fast Cartoon + Texture Image Filters journal August 2010
User interactive segmentation with partially growing random forest conference September 2015
Describing Textures in the Wild conference June 2014
PuMA: the Porous Microstructure Analysis software journal January 2018
Reverse image search for scientific data within and beyond the visible spectrum journal November 2018
Geodesic star convexity for interactive image segmentation
  • 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 https://doi.org/10.1109/CVPR.2010.5540073
conference June 2010
TomoPy: a framework for the analysis of synchrotron tomographic data journal August 2014
A convolutional neural network-based screening tool for X-ray serial crystallography journal April 2018
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
A Survey and Comparison of Discrete and Continuous Multi-label Optimization Approaches for the Potts Model journal April 2013
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
A convex relaxation approach for computing minimal partitions conference June 2009
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
The sketchy database: learning to retrieve badly drawn bunnies journal July 2016
Interactive Texture Segmentation using Random Forests and Total Variation conference January 2009
Fiji: an open-source platform for biological-image analysis journal June 2012
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
miRNALoc: predicting miRNA subcellular localizations based on principal component scores of physico-chemical properties and pseudo compositions of di-nucleotides journal September 2020
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
"GrabCut": interactive foreground extraction using iterated graph cuts conference January 2004
Describing Textures in the Wild preprint January 2013

Figures / Tables (18)