Transferring x-ray based automated threat detection between scanners with different energies and resolution

M. Caldwell; M. Ransley; T. W. Rogers; L. D. Griffin

doi:10.1117/12.2277641

Translator Disclaimer

5 October 2017 Transferring x-ray based automated threat detection between scanners with different energies and resolution

M. Caldwell, M. Ransley, T. W. Rogers, L. D. Griffin

Author Affiliations +

Proceedings Volume 10441, Counterterrorism, Crime Fighting, Forensics, and Surveillance Technologies; 104410F (2017) https://doi.org/10.1117/12.2277641
Event: SPIE Security + Defence, 2017, Warsaw, Poland

Abstract

A significant obstacle to developing high performance Deep Learning algorithms for Automated Threat Detection (ATD) in security X-ray imagery, is the difficulty of obtaining large training datasets. In our previous work, we circumvented this problem for ATD in cargo containers, using Threat Image Projection and data augmentation. In this work, we investigate whether data scarcity for other modalities, such as parcels and baggage, can be ameliorated by transforming data from one domain so that it approximates the appearance of another. We present an ontology of ATD datasets to assess where transfer learning may be applied. We define frameworks for transfer at the training and testing stages, and compare the results for both methods against ATD where a common data source is used for training and testing. Our results show very poor transfer, which we attribute to the difficulty of accurately matching the blur and contrast characteristics of different scanners.

Citation Download Citation

M. Caldwell, M. Ransley, T. W. Rogers, and L. D. Griffin "Transferring x-ray based automated threat detection between scanners with different energies and resolution", Proc. SPIE 10441, Counterterrorism, Crime Fighting, Forensics, and Surveillance Technologies, 104410F (5 October 2017); https://doi.org/10.1117/12.2277641

ACCESS THE FULL ARTICLE