On the impact of using X-ray energy response imagery for object detection via Convolutional Neural Networks

TL;DR

This study investigates how different X-ray energy response images affect CNN-based object detection in security scans, demonstrating improved detection accuracy and transferability across scanners by combining multiple imaging modalities.

Contribution

It introduces the use of combined X-ray energy response imagery for training CNNs, enhancing detection performance and generalization in security screening applications.

Findings

CARAFE achieved the highest detection performance with 0.7 mAP.

Combining multiple X-ray modalities improves cross-scanner transferability.

Model generalizes well across different imaging geometries and material profiles.

Abstract

Automatic detection of prohibited items within complex and cluttered X-ray security imagery is essential to maintaining transport security, where prior work on automatic prohibited item detection focus primarily on pseudo-colour (rgb}) X-ray imagery. In this work we study the impact of variant X-ray imagery, i.e., X-ray energy response (high, low}) and effective-z compared to rgb, via the use of deep Convolutional Neural Networks (CNN) for the joint object detection and segmentation task posed within X-ray baggage security screening. We evaluate state-of-the-art CNN architectures (Mask R-CNN, YOLACT, CARAFE and Cascade Mask R-CNN) to explore the transferability of models trained with such 'raw' variant imagery between the varying X-ray security scanners that exhibits differing imaging geometries, image resolutions and material colour profiles. Overall, we observe maximal detection performance using CARAFE, attributable to training using combination of rgb, high, low, and effective-z X-ray imagery, obtaining 0.7 mean Average Precision (mAP) for a six class object detection problem. Our results also exhibit a remarkable degree of generalisation capability in terms of cross-scanner transferability (AP: 0.835/0.611) for a one class object detection problem by combining rgb, high, low, and effective-z imagery.