Operationalizing Convolutional Neural Network Architectures for Prohibited Object Detection in X-Ray Imagery

TL;DR

This paper evaluates two CNN architectures, Cascade R-CNN and FreeAnchor, for prohibited object detection in X-ray images, demonstrating that FreeAnchor with ResNet50 offers high accuracy, speed, and resilience to image compression.

Contribution

It introduces an operational framework for CNN-based prohibited object detection, highlighting FreeAnchor's superior performance and robustness to lossy compression in security screening.

Findings

FreeAnchor with ResNet50 achieves 87.7 mAP on OPIXray.

FreeAnchor runs at ~13 fps, faster than prior models.

Models show only 1.1% mAP decrease at JPEG compression level 50.

Abstract

The recent advancement in deep Convolutional Neural Network (CNN) has brought insight into the automation of X-ray security screening for aviation security and beyond. Here, we explore the viability of two recent end-to-end object detection CNN architectures, Cascade R-CNN and FreeAnchor, for prohibited item detection by balancing processing time and the impact of image data compression from an operational viewpoint. Overall, we achieve maximal detection performance using a FreeAnchor architecture with a ResNet50 backbone, obtaining mean Average Precision (mAP) of 87.7 and 85.8 for using the OPIXray and SIXray benchmark datasets, showing superior performance over prior work on both. With fewer parameters and less training time, FreeAnchor achieves the highest detection inference speed of ~13 fps (3.9 ms per image). Furthermore, we evaluate the impact of lossy image compression upon detector performance. The CNN models display substantial resilience to the lossy compression, resulting in only a 1.1% decrease in mAP at the JPEG compression level of 50. Additionally, a thorough evaluation of data augmentation techniques is provided, including adaptions of MixUp and CutMix strategy as well as other standard transformations, further improving the detection accuracy.