Joint Sub-component Level Segmentation and Classification for Anomaly Detection within Dual-Energy X-Ray Security Imagery

TL;DR

This paper presents a deep learning approach for joint segmentation and classification of sub-components in dual-energy X-ray images to improve anomaly detection in baggage security screening, achieving high accuracy and low false positives.

Contribution

It introduces a novel joint segmentation and classification method using CNNs for sub-components in dual-energy X-ray imagery, enhancing anomaly detection performance.

Findings

Achieved approximately 99% true positive rate.

Reduced false positives to around 5%.

Effective in cluttered, complex electrical items.

Abstract

X-ray baggage security screening is in widespread use and crucial to maintaining transport security for threat/anomaly detection tasks. The automatic detection of anomaly, which is concealed within cluttered and complex electronics/electrical items, using 2D X-ray imagery is of primary interest in recent years. We address this task by introducing joint object sub-component level segmentation and classification strategy using deep Convolution Neural Network architecture. The performance is evaluated over a dataset of cluttered X-ray baggage security imagery, consisting of consumer electrical and electronics items using variants of dual-energy X-ray imagery (pseudo-colour, high, low, and effective-Z). The proposed joint sub-component level segmentation and classification approach achieve ~99% true positive and ~5% false positive for anomaly detection task.