Abstract
This research work explores the utility of deep learning algorithms in enhancing the accuracy of weapon detection, specifically guns, within x-ray images of travel bags. Utilizing Faster R-CNN as a baseline model, the research aims to augment detection metrics including accuracy, precision, and recall, thereby fortifying security screening procedures. A comparative study was executed between the Faster R-CNN model and a hybrid model that integrated the Segment Anything (SAM) algorithm with Faster R-CNN. Evidently, the hybrid model displayed an edge in performance with the highest accuracy rate of 86.34%, a marked increase from the 72.02% accuracy of Faster R-CNN alone. The fusion model demonstrated superior precision, signaling a decrease in false positive instances, although it faced a higher rate of false negatives, as revealed by its recall rate. This study also unearths data limitations that could potentially be inhibiting maximum model performance, given the discrepancy between available training data and the sheer volume of the comprehensive SIXray dataset. The research concludes by charting avenues for future investigation which include data augmentation, SAM model pre-training, and expansion of detection capabilities to encompass a broader array of weapons. This body of work establishes a framework for advancing security measures through the application of artificial intelligence.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs12198-023-00270-4/MediaObjects/12198_2023_270_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs12198-023-00270-4/MediaObjects/12198_2023_270_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs12198-023-00270-4/MediaObjects/12198_2023_270_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs12198-023-00270-4/MediaObjects/12198_2023_270_Fig4_HTML.png)
Similar content being viewed by others
Data availability
The data availability for our study was augmented by accessing the SIXray dataset, which was obtained from the online platform Roboflow. The SIXray dataset (Miao et al. 2019), available at https://universe.roboflow.com/siewchinyip-outlook-my/ sixray, offered a comprehensive collection of x-ray images for baggage inspection. This dataset facilitated our analysis and experimentation, providing a rich resource for training and evaluating our model. The availability of the SIXray dataset from Roboflow significantly contributed to the success and reliability of our research outcomes.
References
Bay H, Tuytelaars T, Gool LV (2006) SURF: Speeded Up Robust Features. In: European Conference on Computer Vision (ECCV). https://doi.org/10.1007/1174402332
Bhattacharya D (2020) Analysis of the factors affecting violent crime rates in the us. Int J Eng Manage Res 10:106–109. https://doi.org/10.31033/ijemr.10.5.18
Fang C, Liu J, Han P, Chen M, Liao D (2023) Fsvm: A few-shot threat detection method for x-ray security images. Sensors 23(8). https://doi.org/10.3390/s23084069
Gao Q, Hong R, Zhu X, Liu X (2021) An x-ray image enhancement algorithm for dangerous goods in airport security inspection. In: Asia-Pacific Conference on Communications Technology and Computer Science (ACCTCS). https://doi.org/10.1109/ACCTCS52002.2021.00017
Hassan T, Akcay S, Bennamoun M, Khan S, Werghi N (2023) Unsupervised anomaly instance segmentation for baggage threat recognition. J Ambient Intell Human Comput 14:1607–1618. https://doi.org/10.1007/s12652-021-03383-7
Huang Y, Fu X, Zeng Y (2022) Anchor-free weapon detection for x-ray baggage security images. IEEE Access 10:97843–97855. https://doi.org/10.1109/ACCESS.2022.3205593
Jenga K, Catal C, Kar G (2023) Machine learning in crime prediction. J Ambient Intell Humaniz Comput 14(3):2887–2913. https://doi.org/10.1007/s12652-023-04530-y
Kayalvizhi R, Amit kumar, Malarvizhi S, Topkar A, Vijayakumar P (2022) Raw data processing techniques for material classification of objects in dual energy xray baggage inspection systems. Radiat Phys Chem 193:109512. https://doi.org/10.1016/j.radphyschem.2021.109512
Kirillov A, Mintun E, Ravi N, Mao H, Rolland C, Gustafson L, Xiao T, Whitehead S, Berg AC, Lo W-Y, Doll´ar P, Girshick R (2023) Segment Anything. arXiv. https://arxiv.org/abs/2304.02643. Accessed 1 Jul 2023
Lowe DG (1999) Object recognition from local scale-invariant features. In: International Conference on Computer Vision (ICCV) 2:1150–1157. https://doi.org/10.1109/ICCV.1999.790410
Mery D, Riffo V, Zscherpel U, Mondrag´on G, Lillo I, Zuccar I, Lobel H, Carrasco M (2015) Gdxray: The database of x-ray images for nondestructive testing. J Nondestruct Eval 34. 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: Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/CVPR.2019.00222
Ren S, He K, Girshick R, Sun J (2017) Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell (PAMI) 39(6). https://doi.org/10.1109/TPAMI.2016.2577031
Tao R, Wei Y, Jiang X, Li H, Qin H, Wang J, Ma Y, Zhang L, Liu X (2021) Towards real-world x-ray security inspection: A high-quality benchmark and lateral inhibition module for prohibited items detection. In: International Conference on Computer Vision (ICCV). https://doi.org/10.1109/ICCV48922.2021.01074
U.S. Department of Justice (2019) Federal Bureau of Investigation: Violent crime. visited on 2023–06–24. https://ucr.fbi.gov/crime-in-the-u.s/2019/crime-in-the-u.s.-2019/topic-pages/violent-crime. Accessed 2023–06–24
UNWTO (2023) Tourism on track for full recovery as new data shows strong start TO 2023. visited on 2023–06–24. https://www.unwto.org/news/tourism-on-track-for-full-recovery-as-new-data-shows-strong-start-to-2023. Accessed 2023–06–24
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):1–20. https://doi.org/10.1371/journal.pone.0272961
Wang B, Zhang L, Wen L, Liu X, Wu Y (2021) Towards real-world prohibited item detection: A large-scale x-ray benchmark. In: International Conference on Computer Vision (ICCV). https://doi.org/10.1109/ICCV48922.2021.00536
WCO news (2021) The challenges of X-ray image analysis and the value of training. https://mag.wcoomd.org/magazine/wco-news-96/the-challenges-of-x-ray-image-analysis-and-the-value-of-training. Accessed 2023–06–24
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. arXiv. https://arxiv.org/abs/2004.08656. Accessed 1 Jul 2023
Wu J, Xu X, Yang J (2023) Object detection and x-ray security imaging: A survey. IEEE Access 11:45416–45441. https://doi.org/10.1109/ACCESS.2023.3273736
Zhang Y, Jiao R (2023) How segment anything model (SAM) boost medical image segmentation: a survey. arXiv. https://arxiv.org/abs/2305.03678. Accessed 1 Jul 2023
Funding
None.
Author information
Authors and Affiliations
Contributions
W. Sarai conducted literature review in X-ray datasets and SAM, prepared the dataset, and implemented SAM-related experimental models. N. Monbut implemented CNN-related experimental codes and analyzed the results of Faster R-CNN. N. Youngchoay implemented experimental codes with Faster R-CNN and SAM. N. Phookriangkrai conducted the literature review and was a major contributor in writing the manuscript. T. Sattabun conducted the literature review and implemented experimental codes. T. Siriborvornratanakul supervised the whole research (from topic selection, experimental methods, evaluation, and manuscript writing) and was a major contributor to manuscript revision as well as a corresponding author responsible for this submission. All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Conflicts of interest
No conflict of interest to declare.
Additional information
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Sarai, W., Monbut, N., Youngchoay, N. et al. Enhancing baggage inspection through computer vision analysis of x-ray images. J Transp Secur 17, 1 (2024). https://doi.org/10.1007/s12198-023-00270-4
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s12198-023-00270-4