Share Email Print

Proceedings Paper

Adaptation of self-tuning spectral clustering and CNN texture model for detection of threats in volumetric CT images
Author(s): Samuel M. Song; Namho Kim; Jongkyu Lee; Matthew Wood; Simon Bedford; Douglas P. Boyd
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

We report on the performance improvement in Automatic Threat Recognition (ATR) algorithm through the incorporation of self-tuning spectral clustering and a convolutional neural network texture model (CNN). The self-tuning clustering algorithm shows the ability to vastly reduce the amount of bleedout in threat objects resulting in better segmentation and classification. The CNN texture model shows improved detection and classification of textured threats. These additions have markedly improved the ATR. The tests performed using actual CT data of passenger bags show excellent performance characteristics.

Paper Details

Date Published: 14 May 2019
PDF: 7 pages
Proc. SPIE 10999, Anomaly Detection and Imaging with X-Rays (ADIX) IV, 109990A (14 May 2019); doi: 10.1117/12.2520015
Show Author Affiliations
Samuel M. Song, TeleSecurity Sciences, Inc. (United States)
Namho Kim, TeleSecurity Sciences, Inc. (United States)
Jongkyu Lee, TeleSecurity Sciences, Inc. (United States)
Matthew Wood, TeleSecurity Sciences, Inc. (United States)
Simon Bedford, TeleSecurity Sciences, Inc. (United States)
Douglas P. Boyd, TeleSecurity Sciences, 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?