METHOD FOR BUILDING SHADOW IMAGES OF THE INSPECTED OBJECTSUSING X-RAY SYSTEM OF AVIATION SECURITY
DOI:
https://doi.org/10.26906/SUNZ.2023.1.019Keywords:
aviation security, X-ray system, shadow images, image processing, spectral detector, Neyman-Pearson criterionAbstract
The article is devoted to the development of a method for constructing shadow images of control objects of X-ray introscopes and the analysis of its application for the recognition of dangerous and prohibited items on baggage images. It is known that aviation security is significantly determined by measures to ensure aviation security. For this, radio-electronic systems and computerized complexes of screening equipment are used. This equipment includes X-ray introscopes, metal detectors and metal detectors, body scanners, gas analyzers, etc. Screening equipment is used to detect dangerous and prohibited items from passengers and their luggage. One of the main problems with this is the high probability of false alarms when dangerous objects are detected by X-ray systems. In some cases, this probability can be as high as 0.3, which negatively affects the passenger capacity of airports. In order to eliminate this shortcoming, this article provides detailed description of new technologies for detecting dangerous objects based on the use of projection shadow images of control objects. The proposed method for constructing shadow images is based on the use of the triangle similarity rule, the Pythagorean theorem, the theorem of sines and cosines, and formulas for determining the trigonometric functions of the right triangle angles. The explanation of the method for obtaining shadow images is made on the example of control object in the cylinder form. In this case, the standard method for determining the mathematical model of the shadow in one scanning plane is first presented. Next, the developed scanning method is used, which provides for direct and inverse transition to cylindrical and Cartesian coordinate systems. The resulting mathematical models of shadow images of a simple form are used to build models of complex shape, which can be considered as models of prohibited and dangerous objects of control. The detection algorithm involves finding the spatial Fourier transform of the shadow image, followed by convolution with the spectrum of the mask of the desired forbidden or dangerous object. The article analyzes the results of modeling a detector for recognizing a handgun on luggage images. To analyze the detection efficiency, the corresponding detection characteristic is calculated. The analysis showed the effectiveness of the spectral detector in terms of statistical characteristics. In this case, when recognizing the handgun, the probability of correct detection is 0.99997, and the probability of a false alarm is 0.01. The results of the study can be used to automate the processes of screening passengers and baggage.Downloads
References
Doc 9859. Safety Management Manual. Montreal: International Civil Aviation Organization, 2018.
M. Chen, Y. Zhang and Y. Chen. Review on Civil Aviation Safety Investment Research. In 2016 11th International Conference on Reliability, Maintainability and Safety (ICRMS), 2016, pp. 1–5, doi: 10.1109/ICRMS.2016.8050113.
Annex 17 to the Convention on Int. Civil Aviation, Security, Montreal: International Civil Aviation Organization, 2006.
L. Ji and Y. Mou. Research on the Feasibility of Application of Millimeter-wave Security Screening Equipment in Civil Aviation. In 2021 IEEE 3rd International Conference on Civil Aviation Safety and Information Technology (ICCASIT), 2021, pp. 71-75. Doi: 10.1109/ICCASIT53235.2021.9633747.
Семенов О.О. Технічні засоби служби авіаційної безпеки. Київ: НАУ, 2013, 264 с.
D. Anderson. Optimising Multi-layered Security Screening. Journal of Transportation Security. Vol. 14, 2021, pp. 249–273. Doi: 10.1007/s12198-021-00237-3.
P. Gupta, Z. Sinno, J. L. Glover, N. G. Paulter and A. C. Bovik. Predicting Detection Performance on Security X-Ray Images as a Function of Image Quality. IEEE Transactions on Image Processing, Vol. 28, No. 7, 2019, pp. 3328–3342. Doi: 10.1109/TIP.2019.2896488.
S. Almazroui, W. Wangand G.Zhang. Imaging Technologies in Aviation Security. European Journal of Applied Sciences, Vol. 3, No. 4, 2015, pp. 12–27. Doi: 10.14738/aivp.34.1433.
J. Skorupski and P. Uchroński. A Human Being as a Part of the Security Control System at the Airport. Procedia Engineering, Vol. 134, 2016, pp. 291–300. Doi: 10.1016/j.proeng.2016.01.010.
M. Zaliskyi. Reliability parameters estimation in case of aviation radio electronic devices technical state deterioration. Electronics and Control Systems, 2015, № 3 pp. 18–22.
R. Gesick, C. Saritac and C.-C. Hung. Automatic Image Analysis Process for the Detection of Concealed Weapons. In Proceedings of the 5th Annual Workshop on Cyber Security and Information Intelligence Research Cyber Security and Information Intelligence Challenges and Strategies, 2009, pp. 1–12. Doi: 10.1145/1558607.1558630.
V. Riffo and D. Mery. Automated Detection of Threat Objects Using Adapted Implicit Shape Model. IEEE Transactions on Systems, Man, and Cybernetics Systems, Vol. 46, No. 4, 2016, pp. 472–482. Doi: 10.1109/TSMC.2015.2439233.
S. Akçay, M. E. Kundegorski, M. Devereux and T. P. Breckon. Transfer Learning Using Convolutional Neural Networks for Object Classification within X-ray Baggage Security Imagery. In 2016 IEEE International Conference on Image Processing (ICIP), 2016, pp. 1057–1061. Doi: 10.1109/ICIP.2016.7532519.
B. Gu, R. Ge, Y. Chen, L. Luo and G. Coatrieux. Automatic and Robust Object Detection in X-Ray Baggage Inspection Using Deep Convolutional Neural Networks. IEEE Transactions on Industrial Electronics, Vol. 68, No. 10, 2021, pp.10248–10257. Doi: 10.1109/TIE.2020.3026285.
Y. F. A. Gaus, N. Bhowmik, S. Akçay, P. M. Guillén-Garcia, J. W. Barker and T. P. Breckon. Evaluation of a Dual Convolutional Neural Network Architecture for Object-wise Anomaly Detection in Cluttered X-ray Security Imagery. In 2019 International Joint Conference on Neural Networks (IJCNN), 2019, pp. 1–8. Doi: 10.1109/IJCNN.2019.8851829.
J. Zhang, X. Song, J. Feng and J. Fei. X-Ray Image Recognition Based on Improved Mask R-CNN Algorithm. Mathematical Problems in Engineering, Vol. 2021, pp. 1–14, doi: 10.1155/2021/6544325.
A. K. Shukla. Medical Imaging Methods: Theory and Applications. Boca Raton: CRC Press, 2022, 200 p.
R. Alberts. Modeling and Control of Image Processing for Interventional X-Ray. Eindhoven: Technische Universiteit Eindhoven, 2010, 202 p.
