2021 IEEE International Conference on Image Processing

19-22 September 2021 • Anchorage, Alaska, USA

Imaging Without Borders

2021 IEEE International Conference on Image Processing

19-22 September 2021 • Anchorage, Alaska, USA

Login Paper Search My Schedule Paper Index Help

My ICIP 2021 Schedule

Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
  1. Create a login based on your email (takes less than one minute)
  2. Perform 'Paper Search'
  3. Select papers that you desire to save in your personalized schedule
  4. Click on 'My Schedule' to see the current list of selected papers
  5. Click on 'Printable Version' to create a separate window suitable for printing (the header and menu will appear, but will not actually print)

Paper Detail

Paper IDSS-CIMM.6
Paper Title 3D AUTOENCODERS FOR FEATURE EXTRACTION IN X-RAY TOMOGRAPHY
Authors Aniket Tekawade, Zhengchun Liu, Peter Kenesei, Tekin Bicer, Francesco De Carlo, Rajkumar Kettimuthu, Ian Foster, Argonne National Laboratory, United States
SessionSS-CIMM: Special Session: Computational Imaging for Materials and Microscopy
LocationArea B
Session Time:Monday, 20 September, 13:30 - 15:00
Presentation Time:Monday, 20 September, 13:30 - 15:00
Presentation Poster
Topic Special Sessions: Computational Imaging for Materials and Microscopy
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Abstract Real-time steering of time-resolved or in-situ X-ray tomography requires capturing changes in morphological descriptors in a sample (e.g., porosity, particle size, and crack width) during continuous data acquisition. Image segmentation (2D or 3D) followed by quantitative measurement is the conventional method for tracking changes in these descriptors with respect to a previous time-step or a 3D search in a volume. However, image segmentation is expensive. As a faster and unsupervised alternative, we propose a feature-extraction approach using a convolutional autoencoder, where the latent space of the encoder responds to relative changes in morphology without prior knowledge of the morphological descriptors. To test this approach in parametric experiments, we used a digital twin for micro-CT to generate realistic datasets of porous materials. We show that for some configurations of the autoencoder, its n-dimensional latent space encodes the sample's local porosity metrics while disregarding contrast information (relative proportion of absorption and phase contrast) determined by the imaging modality and not the sample. Through dimensionality reduction, the vector’s response is visualized in 2D space to find clusters of data with similar porosity metrics. Our approach can extract features from grayscale tomographic data more than 4x faster than a segmentation + pore analysis workflow.