On the impact of using X-ray energy response imagery for object detection via Convolutional Neural Networks
This work addresses the challenge of improving object detection accuracy and generalizability for X-ray baggage security screening, which is incremental as it builds on prior methods by incorporating new imagery types.
The study tackled the problem of detecting prohibited items in X-ray security imagery by evaluating the impact of using variant X-ray energy response imagery (high, low, and effective-z) alongside traditional rgb imagery with deep convolutional neural networks, achieving a maximal detection performance of 0.7 mAP for a six-class problem and demonstrating strong cross-scanner transferability with AP scores of 0.835/0.611 for a one-class problem.
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.