English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

X-ray imagery security screening is essential to maintaining transportsecurity against a varying profile of threat or prohibited items. Particularinterest lies in the automatic detection and classification of weapons such asfirearms and knives within complex and cluttered X-ray security imagery. Here,we address this problem by exploring various end-to-end object detectionConvolutional Neural Network (CNN) architectures. We evaluate several leadingvariants spanning the Faster R-CNN, Mask R-CNN, and RetinaNet architectures toexplore the transferability of such models between varying X-ray scanners withdiffering imaging geometries, image resolutions and material colour profiles.Whilst the limited availability of X-ray threat imagery can pose a challenge,we employ a transfer learning approach to evaluate whether such inter-scannergeneralisation may exist over a multiple class detection problem. Overall, weachieve maximal detection performance using a Faster R-CNN architecture with aResNet$_{101}$ classification network, obtaining 0.88 and 0.86 of mean AveragePrecision (mAP) for a three-class and two class item from varying X-ray imagingsources. Our results exhibit a remarkable degree of generalisability in termsof cross-scanner performance (mAP: 0.87, firearm detection: 0.94 AP). Inaddition, we examine the inherent adversarial discriminative capability of suchnetworks using a specifically generated adversarial dataset for firearmsdetection - with a variable low false positive, as low as 5%, this shows boththe challenge and promise of such threat detection within X-ray securityimagery.

Evaluating the Transferability and Adversarial Discrimination of  Convolutional Neural Networks for Threat Object Detection and Classification  within X-Ray Security Imagery