Evaluating a Dual Convolutional Neural Network Architecture for Object-wise Anomaly Detection in Cluttered X-ray Security Imagery

Gaus, Y.F.A.; Bhowmik, N.; Akcay, A.; Guillen-Garcia, P.M.; Barker, J.W; Breckon, T.P.

Abstract

X-ray baggage security screening is widely used to maintain aviation and transport secure. Of particular interestis the focus on automated security X-ray analysis for particular classes of object such as electronics, electrical items and liquids. However, manual inspection of such items is challenging when dealing with potentially anomalous items. Here we present a dual convolutional neural network (CNN) architecture for automatic anomaly detection within complex security X-ray imagery. We leverage recent advances in region-based (R-CNN), mask-based CNN (Mask R-CNN) and detection architectures such as RetinaNet to provide object localisation variants for specific object classes of interest. Subsequently, leveraging a range of established CNN object and fine-grained category classification approaches we formulate within object anomaly detection as a two-class problem (anomalous or benign). Whilst the best performing object localisation method is able to perform with 97.9% mean average precision (mAP) over a six-class X-ray object detection problem, subsequent two-class anomaly/benign classification is able to achieve 66% performance for within object anomaly detection. Overall, this performance illustrates both the challenge and promise of object-wise anomaly detection within the context of cluttered X-ray security imagery.

Citation

Gaus, Y., Bhowmik, N., Akcay, A., Guillen-Garcia, P., Barker, J., & Breckon, T. (2019, July). Evaluating a Dual Convolutional Neural Network Architecture for Object-wise Anomaly Detection in Cluttered X-ray Security Imagery. Presented at Proc. Int. Joint Conference on Neural Networks, Budapest, Hungary

• Presentation Conference Type: Conference Paper (published)
• Conference Name: Proc. Int. Joint Conference on Neural Networks
• Acceptance Date: Mar 7, 2019
• Online Publication Date: Jul 14, 2019
• Publication Date: 2019
• Deposit Date: Apr 2, 2019
• Publicly Available Date: Nov 13, 2019
• Series ISSN: 2161-4407
• Book Title: 2019 International Joint Conference on Neural Networks (IJCNN) ; proceedings.
• DOI: https://doi.org/10.1109/ijcnn.2019.8851829
• Public URL: https://durham-repository.worktribe.com/output/1144416