BOJXONA RENTGEN TASVIRLARINI SUN’IY INTELLEKT ASOSIDA TAHLIL QILISHNING GIBRID MODELI
Keywords:
bojxona nazorati, rentgen tasviri, nointruziv inspeksiya, sun’iy intellekt, chuqur o‘rganish, obyektni aniqlash, anomaliyani aniqlash, manifestni tekshirish, inson ishtirokidagi tizim, risklarni boshqarish.Abstract
Mazkur tadqiqotning maqsadi bojxona nazoratida olinadigan rentgen tasvirlarini sun’iy intellekt yordamida tahlil qilish bo‘yicha mavjud ilmiy va institutsional dalillarni tizimlashtirish hamda O‘zbekiston bojxona amaliyotiga mos gibrid konseptual modelni ishlab chiqishdan iborat. Tadqiqot strukturaviy integrativ adabiyotlar sharhi, o‘zbekistonlik tadqiqotchilarning ilmiy-amaliy ishlari va Hindiston bojxona xizmatining 2022–2026-yillardagi tajribasini hujjatlar asosida tahlil qilish usullariga tayandi. 2026-yil 27-iyul holatiga ko‘ra aniqlangan ilmiy nashrlar, Jahon bojxona tashkiloti, Jahon savdo tashkiloti, AQSh Milliy standartlar va texnologiyalar instituti hamda O‘zbekiston Respublikasi qonunchilik hujjatlari muvofiqlik, ishonchlilik va amaliy ahamiyat mezonlari bo‘yicha saralandi. Natijalar yuk va bagaj rentgen tasvirlaridagi obyektlarni aniqlash modellari ma’lum sinflarni lokalizatsiya qilishda foydali ekanini, biroq ularning alohida qo‘llanishi noma’lum tahdidlar, yuk deklaratsiyasiga nomuvofiqlik va turli skanerlar o‘rtasidagi domen siljishini to‘liq qamrab olmasligini ko‘rsatdi. Mahalliy tadqiqotlar CNN asosidagi tanib olish, anomaliya deteksiyasi, operator tayyorgarligi va risklarni boshqarishni birlashtirish zarurligini qo‘llab-quvvatlaydi, ammo tashqi validatsiya dalillari hali cheklangan. Shu asosda tasvir va deklaratsiya ma’lumotlarini standartlashtirish, obyektni aniqlash, anomaliyani aniqlash, manifestni avtomatik tekshirish, integratsiyalashgan risk bahosi hamda inson ishtirokidagi yakuniy qarorni birlashtiruvchi besh qatlamli model taklif qilindi. Modelni joriy etishdan oldin mahalliy ma’lumotlar to‘plamini shakllantirish, alohida skaner va postlarda tashqi validatsiya o‘tkazish, dastlab “jim rejim”da sinash va model og‘ishini doimiy monitoring qilish zarurligi asoslandi. Tadqiqot natijalari sun’iy intellektni bojxona inspektorini almashtiruvchi vosita emas, balki riskka asoslangan qarorni qo‘llab-quvvatlovchi tizim sifatida joriy etish maqsadga muvofiqligini ko‘rsatadi.
References
Andrews, J. T. A., Jaccard, N., Rogers, T. W., & Griffin, L. D. (2017). Representation-learning for anomaly detection in complex X-ray cargo imagery. Proceedings of SPIE, 10187, 101870E. https://doi.org/10.1117/12.2261101
Asilova, G. A., & Dilshodbekov, T. D. (2019). Davlat bojxona qo‘mitasining Bojxona institutida mustaqil ta’limni tashkil etish va o‘tkazish bo‘yicha uslubiy tavsiyanoma. DBQ Bojxona instituti. https://portfolio.afu.uz/storage/documents/iC30yRJx1dwSRTq8saXkjmDmYTii8NKlChvLJmVW.pdf
Farxodov, F., & Sherboboyev, D. (2025). Bojxona organlarida xavfni boshqarish tizimining bugungi kunda tutgan o‘rni va uning ahamiyati. Raqamli iqtisodiyot va sun’iy intellekt texnologiyalarining jamiyat rivojlanishidagi ahamiyati, 1(1), 3–7. https://doi.org/10.71337/inlibrary.uz.risitjra.68570
Gaikwad, B., Patra, A., Crawford, C. R., & Miller, E. L. (2025). Self-supervised anomaly detection and localization for X-ray cargo images: Generalization to novel anomalies. Engineering Applications of Artificial Intelligence, 140, 109675. https://doi.org/10.1016/j.engappai.2024.109675
He, C., Mu, T., Ren, W., & Zhao, B. (2023). LPIXray: A large-scale logistics prohibited item X-ray dataset for the application of deep learning in security inspection. In 2023 IEEE International Conference on Image Processing and Artificial Intelligence. https://doi.org/10.1109/CIPAE60493.2023.00097
Isaac-Medina, B. K. S., Yucer, S., Bhowmik, N., & Breckon, T. P. (2023). Seeing through the data: A statistical evaluation of prohibited item detection benchmark datasets for X-ray security screening. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (pp. 524–533). https://doi.org/10.1109/CVPRW59228.2023.00059
Jaccard, N., Rogers, T. W., Morton, E. J., & Griffin, L. D. (2016). Tackling the X-ray cargo inspection challenge using machine learning. Proceedings of SPIE, 9847, 98470N. https://doi.org/10.1117/12.2222765
Mery, D., Riffo, V., Zscherpel, U., Mondragón, G., Lillo, I., Zuccar, I., Lobel, H., & Carrasco, M. (2015). GDXray: The database of X-ray images for nondestructive testing. Journal of Nondestructive Evaluation, 34, Article 42. https://doi.org/10.1007/s10921-015-0315-7
Miao, C., Xie, L., Wan, F., Su, C., Liu, H., Jiao, J., & Ye, Q. (2019). SIXray: A large-scale security inspection X-ray benchmark for prohibited item discovery in overlapping images. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. https://doi.org/10.1109/CVPR.2019.00222
O‘zbekiston Respublikasi Prezidenti. (2025a, 25-mart). Davlat bojxona xizmati organlarining faoliyati samaradorligini oshirish bo‘yicha chora-tadbirlar to‘g‘risida (PF-57-son Farmon). Lex.uz. https://lex.uz/uz/docs/-7451997
O‘zbekiston Respublikasi Prezidenti. (2025b, 17-dekabr). Bojxona ma’muriyatchiligi va tashqi savdo tartibotlarini yanada soddalashtirish va samaradorligini oshirish chora-tadbirlari to‘g‘risida (PF-250-son Farmon). Lex.uz. https://lex.uz/docs/7934915
Press Information Bureau. (2025, September 16). Indigenous drive-through cargo scanner to revolutionize security at Jawaharlal Nehru Custom House, Nhava Sheva. Government of India. https://www.pib.gov.in/PressReleasePage.aspx?PRID=2167314
Rapiscan Systems. (n.d.). Gemini 7555 X-ray inspection system. Retrieved July 27, 2026, from https://www.rapiscansystems.com/en/products/gemini-7555
Ramesh, M., & Vijayakumar, S. (2023, October 18). How Indian Customs leverages data analytics for efficient risk management. WCO News, 102. https://mag.wcoomd.org/magazine/wco-news-102-issue-3-2023/how-indian-customs-leverages-data-analytics-for-efficient-risk-management/
Rogers, T. W., Jaccard, N., Morton, E. J., & Griffin, L. D. (2017). Automated X-ray image analysis for cargo security: Critical review and future promise. Journal of X-Ray Science and Technology, 25(1), 33–56. https://doi.org/10.3233/XST-160606
Saidov, A. A., Khakimova, F. A., & Rustamov, I. A. (2026). Tashqi savdo yuklari rentgen tasvirlarida anomaliya holatlarini aniqlash muammolari va yechimlari: CNN asosida tovar tasvirini tanib olish usuli. Raqamli iqtisodiyot, (14). https://cyberleninka.ru/article/n/tash-i-savdo-yuklari-rentgen-tasvirlarida-anomaliya-olatlarini-ani-lash-muammolari-va-echimlari-cnn-asosida-tovar-tasvirini-tanib
Tabassi, E. (2023). Artificial Intelligence Risk Management Framework (AI RMF 1.0) (NIST AI 100-1). National Institute of Standards and Technology. https://doi.org/10.6028/NIST.AI.100-1
Tuszynski, J., Briggs, J. T., & Kaufhold, J. (2013). A method for automatic manifest verification of container cargo using radiography images. Journal of Transportation Security, 6(4), 339–356. https://doi.org/10.1007/s12198-013-0121-3
U.S. Department of Homeland Security. (2025). AI-enabled paradigms for non-intrusive screening. https://www.dhs.gov/sites/default/files/2025-02/25_0211_st_ai-enabled_paradigms_for_non-intrusive_screening.pdf
Usmanaliyev, F. (2022). Raqamli bojxona tushunchasi va bojxonani raqamli transformatsiya qilishning o‘ziga xos jihatlari. Scientific Progress, 3(3), 854–860. https://cyberleninka.ru/article/n/raqamli-bojxona-tushunchasi-va-bojxonani-raqamli-transformatsiya-qilishning-o-ziga-xos-jihatlari
Utpat, H., Dhamanikar, S., & Vijayakumar, S. (2026, March 2). Artificial intelligence-based X-ray image analytics solution: India’s experience and key takeaways. WCO News, 109. https://mag.wcoomd.org/magazine/wco-news-109-issue-1-2026/artificial-intelligence-based-x-ray-image-analytics-solution-indias-experience-and-key-takeaways/
Velayudhan, D., Hassan, T., Damiani, E., & Werghi, N. (2023). Recent advances in baggage threat detection: A comprehensive and systematic survey. ACM Computing Surveys, 55(8), Article 165. https://doi.org/10.1145/3549932
Vijayakumar, S. (2025). Technology-centric and data-driven customs risk management for supply chain security. World Customs Journal, 19(1). https://www.worldcustomsjournal.org/article/131745-technology-centric-and-data-driven-customs-risk-management-for-supply-chain-security
Viriyasaranon, T., Chae, S.-H., & Choi, J.-H. (2022). MFA-net: Object detection for complex X-ray cargo and baggage security imagery. PLOS ONE, 17(9), e0272961. https://doi.org/10.1371/journal.pone.0272961
Visser, W., Schwaninger, A., Hardmeier, D., Flisch, A., Costin, M., Vienne, C., Sukowski, F., Hassler, U., Dorion, I., Marciano, A., Koomen, G., Slegt, M., & Canonica, A. (2016). Automated comparison of X-ray images for cargo scanning. In 2016 International Carnahan Conference on Security Technology. https://doi.org/10.1109/CCST.2016.7815714
Wang, H., Jia, T., Ma, B., Chen, D., & Deng, S. (2024). Delving into cluttered prohibited item detection for security inspection system. IEEE Transactions on Industrial Informatics, 20, 11825–11834. https://doi.org/10.1109/TII.2024.3413316
Wei, Y., Tao, R., Wu, Z., Ma, Y., Zhang, L., & Liu, X. (2020). Occluded prohibited items detection: An X-ray security inspection benchmark and de-occlusion attention module. In Proceedings of the 28th ACM International Conference on Multimedia (pp. 138–146). https://doi.org/10.1145/3394171.3413828
World Customs Organization. (2025a). Guidelines for the procurement and deployment of scanning/non-intrusive inspection equipment. https://www.wcoomd.org/-/media/wco/public/global/pdf/topics/facilitation/instruments-and-tools/tools/safe-package/nii-guidelines-2025/nii-guidelines-en_june-2025.pdf
World Customs Organization. (2025b). Annual report 2024–2025. https://www.wcoomd.org/-/media/wco/public/global/pdf/about-us/annual-reports/annual-report-2024_2025.pdf
World Customs Organization, & World Trade Organization. (2022). WCO/WTO study report on disruptive technologies. World Trade Organization. https://www.wto.org/english/res_e/publications_e/wco-wto22_e.htm
Wu, J., Xu, X., & Yang, J. (2023). Object detection and X-ray security imaging: A survey. IEEE Access, 11. https://doi.org/10.1109/ACCESS.2023.3273736
