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

TL;DR

This study evaluates various CNN architectures for detecting threat objects in X-ray security images, demonstrating high transferability across different scanners and exploring adversarial detection capabilities.

Contribution

It compares multiple CNN models for threat detection in X-ray images, highlighting the effectiveness of Faster R-CNN with ResNet101 and analyzing adversarial discrimination.

Findings

Faster R-CNN with ResNet101 achieves 0.88 mAP for threat detection.

Models generalize well across different X-ray scanners with mAP of 0.87.

Adversarial dataset testing shows low false positive rates (~5%).

Abstract

X-ray imagery security screening is essential to maintaining transport security against a varying profile of threat or prohibited items. Particular interest lies in the automatic detection and classification of weapons such as firearms and knives within complex and cluttered X-ray security imagery. Here, 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 to explore the transferability of such models between varying X-ray scanners with differing 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-scanner generalisation may exist over a multiple class detection problem. Overall, we achieve maximal detection performance using a Faster R-CNN architecture with a ResNet$_{101}$ classification network, obtaining 0.88 and 0.86 of mean Average Precision (mAP) for a three-class and two class item from varying X-ray imaging sources. Our results exhibit a remarkable degree of generalisability in terms of cross-scanner performance (mAP: 0.87, firearm detection: 0.94 AP). In addition, we examine the inherent adversarial discriminative capability of such networks using a specifically generated adversarial dataset for firearms detection - with a variable low false positive, as low as 5%, this shows both the challenge and promise of such threat detection within X-ray security imagery.