Share Email Print

Proceedings Paper

Material classification using convolution neural network (CNN) for x-ray based coded aperture diffraction system
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Transmission x-ray systems rely on the measured photon attenuation coefficients for material imaging and classification. While this approach provides high quality imaging capabilities and satisfactory object discrimination in most situations, it lacks material-specific information. For airport security, this can be a significant issue as false alarms require additional time to be resolved by human operators, which impacts bag throughput and airport operations. Orthogonal techniques such as X-ray Diffraction Tomography (XRDT) using a coded aperture provide complementary chemical/molecular signatures that can be used to identify a target material. The combination of noisy signals, variability in the XRD form factors for the same material, and the lack of a comprehensive material library limits the classification performance of the correlation based methods. Using simulated data to train a 1D Convolution Neural Network (CNN), we found relative improvements in classification accuracy compared to the correlation based approach we used previously. These improvement gains were cross-validated using the simulated data, and provided satisfactory detection results against real experimental data collected on a laboratory prototype.

Paper Details

Date Published: 12 June 2019
PDF: 9 pages
Proc. SPIE 10999, Anomaly Detection and Imaging with X-Rays (ADIX) IV, 109990B (12 June 2019); doi: 10.1117/12.2519983
Show Author Affiliations
Kris Brumbaugh, Smiths Detection Inc. (United States)
C. Royse, Duke Univ. (United States)
C. Gregory, Smiths Detection Inc. (United States)
K. Roe, Smiths Detection Inc. (United States)
J. A. Greenberg, Duke Univ. (United States)
S. O. Diallo, Smiths Detection Inc. (United States)

Published in SPIE Proceedings Vol. 10999:
Anomaly Detection and Imaging with X-Rays (ADIX) IV
Amit Ashok; Joel A. Greenberg; Michael E. Gehm, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?