On the Use of Deep Learning for the Detection of Firearms in X-ray Baggage Security Imagery

Gaus, Y.F.A.; Bhowmik, N.; Breckon, T.P.

Abstract

X-ray imagery security screening is essential to maintaining transport security against a varying profile of prohibited items. Particular interest lies in the automatic detection and classification of prohibited items such as firearms and firearm components within complex and cluttered X-ray security imagery. We address this problem by exploring various end-to-end object detection Convolutional Neural Network (CNN) architectures. We evaluate several leading variants spanning the Faster R-CNN, Mask R-CNN, and RetinaNet architectures. Overall, we achieve maximal detection performance using a Faster R-CNN architecture with a ResNet 101 classification network, obtaining 0.91 and 0.88 of mean Average Precision (mAP) for a two-class problem from varying X-ray imaging dataset. Our results offer very low false positive (FP) complimented by a high accuracy (A) $(\mathrm{FP}=0.00\%,\ \mathrm{A}=99.96\%)$ . This result illustrates the applicability and superiority of such integrated region based detection models within this X-ray security imagery context.

Citation

Gaus, Y., Bhowmik, N., & Breckon, T. (2019, November). On the Use of Deep Learning for the Detection of Firearms in X-ray Baggage Security Imagery. Presented at 2019 IEEE International Symposium on Technologies for Homeland Security, Boston, USA

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 2019 IEEE International Symposium on Technologies for Homeland Security
• Start Date: Nov 5, 2019
• End Date: Nov 6, 2019
• Acceptance Date: Aug 30, 2019
• Online Publication Date: Mar 12, 2020
• Publication Date: Nov 5, 2019
• Deposit Date: Dec 20, 2019
• Publicly Available Date: Mar 19, 2020
• Publisher: Institute of Electrical and Electronics Engineers
• Pages: 1-7
• Book Title: Proceeding of the International Symposium on Technologies for Homeland Security.
• DOI: https://doi.org/10.1109/hst47167.2019.9032917
• Public URL: https://durham-repository.worktribe.com/output/1142741