UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Representation-learning for anomaly detection in complex x-ray cargo imagery

Andrews, JTA; Jaccard, N; Rogers, TW; Griffin, LD; (2017) Representation-learning for anomaly detection in complex x-ray cargo imagery. In: Anomaly Detection and Imaging with X-Rays (ADIX) II. (pp. 101870E-1). SPIE Green open access

[thumbnail of 101870E.pdf]
Preview
Text
101870E.pdf - Published Version

Download (1MB) | Preview

Abstract

Existing approaches to automated security image analysis focus on the detection of particular classes of threat. However, this mode of inspection is ineffectual when dealing with mature classes of threat, for which adversaries have refined effective concealment techniques. Furthermore, these methods may be unable to detect potential threats that have never been seen before. Therefore, in this paper, we investigate an anomaly detection framework, at X-ray image patch-level, based on: (i) image representations, and (ii) the detection of anomalies relative to those representations. We present encouraging preliminary results, using representations learnt using convolutional neural networks, as well as several contributions to a general-purpose anomaly detection algorithm based on decision-tree learning.

Type: Proceedings paper
Title: Representation-learning for anomaly detection in complex x-ray cargo imagery
Event: SPIE Defense + Commercial Sensing 2017
Location: Anaheim, California, United States
Dates: 09 April 2017 - 13 April 2017
ISBN-13: 9781510608757
Open access status: An open access version is available from UCL Discovery
DOI: 10.1117/12.2261101
Publisher version: http://doi.org/10.1117/12.2261101
Language: English
Additional information: © 2017 SPIE. This version is the version of record. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: Anomaly detection, representation-learning, machine learning, deep learning, cargo screening, X-ray imaging, security imaging
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery.ucl.ac.uk/id/eprint/10024872
Downloads since deposit
280Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item