VEGA: An AI-Based Software Framework for CT and X-Ray Luggage Threat Detection
Article Sidebar
Main Article Content
The rapid growth of air travel and global logis- tics has intensified the need for efficient and reliable security screening systems. Conventional baggage inspection relies heavily on human interpretation of Computed Tomography (CT) and X-ray images, which is time-consuming and prone to fatigue- related errors. This paper presents VEGA, an AI-based software framework that enhances luggage threat detection by intelligently analyzing the output of existing CT and X-ray scanners. Instead of focusing on scanning hardware or radiation physics, VEGA applies deep learning techniques to pre-captured scan images to identify and classify objects within luggage. The system performs multi-dimensional image analysis, highlights suspicious regions, and assigns threat confidence scores to assist security operators. Experimental results demonstrate improved detection accuracy and reduced false alarms compared to manual screening. VEGA offers a scalable and cost-effective solution for integrating AI into modern airport, border, and logistics security workflows.
Downloads
References
A. R. Girshick, J. Donahue, T. Darrell, and J. Malik, “Rich feature hierarchies for accurate object detection and semantic segmentation,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 38, no. 2, pp. 317–329, Feb. 2016.
M. Bas¸tan, M. R. Yousefi, and T. M. Breuel, “Visual words on baggage X-ray images,” in Proc. IEEE Int. Conf. Comput. Vis., 2011, pp. 584–591.
S. Akc¸ay and T. Breckon, “Towards automatic threat detection: A survey of advances of X-ray baggage imaging,” IEEE Trans. Inf. Forensics Security, vol. 16, pp. 371–388, 2021.
J. Zhang, H. Zhang, and J. Zhang, “Automatic detection of pro- hibited items in X-ray baggage images,” IEEE Access, vol. 7, pp. 110859–110869, 2019.
K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2016,
pp. 770–778.
Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, May 2015.
S. Ren, K. He, R. Girshick, and J. Sun, “Faster R-CNN: Towards real- time object detection,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 39, no. 6, pp. 1137–1149, Jun. 2017.
M. Kundegorski, S. Akc¸ay, M. Devereux, A. Mouton, and T. Breckon, “On using deep learning for X-ray baggage threat detection,” in Proc. Int. Conf. Image Anal. Recognit., 2016, pp. 205–212.
N. Singh and M. Kaur, “CT image-based automatic explosive detection using deep learning,” IEEE Access, vol. 8, pp. 144864–144873, 2020.
T. Mery, D. Saavedra, and M. Prasad, “X-ray baggage inspection with computer vision: A survey,” IEEE Access, vol. 8, pp. 145688–145708, 2020.
H. Chen, Q. Dou, L. Yu, and P. A. Heng, “VoxResNet: Deep voxelwise residual networks for 3D medical image segmentation,” Neurocomput- ing, vol. 238, pp. 424–433, 2017.
S. Akc¸ay, M. Kundegorski, M. Devereux, and T. Breckon, “Transfer learning using CNNs for object detection in X-ray baggage security imagery,” in Proc. IEEE Int. Conf. Image Process., 2016, pp. 1057–1061.
A. Mouton and T. Breckon, “Materials-based detection of concealed objects in baggage X-ray images,” in Proc. IEEE Int. Conf. Image Process., 2015, pp. 4436–4440.
M. Bas¸tan and T. Breuel, “Object recognition in multi-view dual energy X-ray images,” Machine Vision and Applications, vol. 27, no. 7, pp. 1045–1060, 2016.
S. Akc¸ay, M. Kundegorski, and T. Breckon, “Using deep convolutional neural networks for automatic object detection in X-ray baggage security imagery,” IEEE Trans. Inf. Forensics Security, vol. 13, no. 9, pp. 2203–2214, Sep. 2018.
S. Akcay, M. E. Kundegorski, C. G. Willcocks, and T. P. Breckon, ”Using deep convolutional neural network architectures for object clas- sification and detection within X-ray baggage security imagery,” IEEE Trans. Inf. Forensics Security, vol. 13, no. 9, pp. 2203–2215, Sept. 2018.
J. Redmon and A. Farhadi, ”YOLOv3: An incremental improvement,” arXiv preprint arXiv:1804.02767, 2018.
M. E. Kundegorski, S. Akcay, M. Devereux, and T. P. Breckon, ”On using feature descriptors as visual words for object detection within X- ray baggage security screening,” in Proc. IEEE Int. Conf. Imaging for Crime Detection and Prevention, 2016.
T. P. Breckon, ”Advances in X-ray baggage screening,” IEEE Aerospace and Electronic Systems Magazine, vol. 31, no. 12, pp. 10–19, 2016.
A. Mouton, S. Akcay, and T. P. Breckon, ”3D object classification in baggage security CT imagery using deep learning,” in Proc. IEEE Int. Conf. Image Processing (ICIP), 2019, pp. 1–5.
S. Akcay and T. P. Breckon, ”Towards automatic threat detection in baggage screening using deep learning,” in Proc. IEEE Int. Conf. Image Processing, 2017.
A. Mery et al., ”Computer vision for X-ray testing: Status, challenges and promises,” IEEE Trans. Industrial Informatics, vol. 12, no. 6, pp. 2083–2093, Dec. 2016.
G. Flitton, T. Breckon, and N. Megherbi, ”A comparison of 3D interest point descriptors with application to baggage object detection in complex CT imagery,” Pattern Recognition, vol. 46, no. 9, pp. 2429–2442, 2013.
J. Zhang, Y. Wu, and W. Zhang, ”3D convolutional neural networks for baggage threat detection in CT images,” IEEE Access, vol. 7, pp. 126–135, 2019.
S. Akcay et al., ”Evaluation of deep learning architectures for object detection within X-ray baggage security imagery,” in Proc. IEEE Int. Conf. Imaging Systems and Techniques, 2017.
A. Mery and D. Saavedra, ”Automated detection of threats in X- ray cargo images using anomaly detection,” IEEE Trans. Industrial Informatics, vol. 11, no. 3, pp. 601–609, June 2015.
M. Carrasco, A. Mery, and D. Saavedra, ”Adaptive learning for object detection in X-ray baggage inspection,” IEEE Trans. Neural Networks and Learning Systems, vol. 30, no. 7, pp. 2100–2112, July 2019.
This work is licensed under a Creative Commons Attribution 4.0 International License.
All articles published in our journal are licensed under CC-BY 4.0, which permits authors to retain copyright of their work. This license allows for unrestricted use, sharing, and reproduction of the articles, provided that proper credit is given to the original authors and the source.