Abstract
Safety inspections play a crucial role in maintaining social stability and protecting the safety of public life and property. The X-ray security detector is an important scanning device in the security inspection of public transportation and express packages. However, current intelligent detection algorithms face problems such as a limited dataset of prohibited items, the imbalanced distribution of categories, variable target postures, and varying target scales, leading to the occurrence of false positives and missed detections. We propose an improved X-ray prohibited item recognition algorithm, named YOLOv5s-DAB. A deformable convolution module is designed to address the characteristics of different scales and postures of the same prohibited item in different samples. Besides, a multi-scale feature enhancement module SA-ASPP based on attention mechanism is designed, which can handle the problem of overlap** occlusion of multi-scale contraband. Experimental results in the real X-ray prohibited items dataset demonstrate that our model outperforms state-of-the-art methods in terms of detection accuracy.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Akçay, S., Kundegorski, M.E., Devereux, M., et al.: Transfer learning using convolutional neural networks for object classification within X-ray baggage security imagery. In: 2016 IEEE International Conference on Image Processing (ICIP), pp.1057–1061. IEEE (2016)
Akcay, S., Kundegorski, M.E., Willcocks, C.G., et al.: Using deep convolutional neural network architectures for object classification and detection within x-ray baggage security imagery. IEEE Trans. Inf. Forensics Secur. 13(9), 2203–2215 (2018)
Tang, H.Y., Wang, Y., Zhang, X., et al.: Feature pyramid-based algorithm for detecting hazardous materials in X-ray machines. J. **’an Post Telecommun. 25(02), 58–63 (2020)
Li, A., Zhang, J., Lv, Y., et al. : Uncertainty-aware joint salient object and camouflaged object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2021, pp. 10071–10081 (2021)
Mu, S.Q., Lin, J.J., Wang, H.Q., Wei, X.Z.: X-ray image contraband detection algorithm based on improved YOLOv4. J. Mil. Eng. 42(12), 2675–2683 (2021)
Bochkovskiy, A., Wang, C.Y., Liao, H.: YOLOv4: Optimal Speed and Accuracy of Object Detection. ar**v.2004.10934 (2020)
Miao, C., ** images. IEEE (2019)
Wang, R., Liu, J., Zhang, H.: Research on target detection method based on improved YOLOv5. In: Zhao, X., Yang, S., Wang, X., Li, J. (eds.) Web Information Systems and Applications, WISA 2022, vol. 13579. Springer, Cham (2021). https://doi.org/10.1007/978-3-031-20309-1_40
Wang, W., Zhou, Y., Shi, B., He, H., Zhang, J.W.: A multi-layer attention mechanism based algorithm for security screening hazardous materials identification. Adv. Laser Optoelectr. 59(02), 184–191 (2022)
Dai, J., Qi, H., **ong, Y., et al.: Deformable convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp.764–773 (2017)
Zhu, X., Hu, H., Lin, S., et al.: Deformable convnets v2: more deformable, better results. In:Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp.9308–9316 (2019)
Zhang, Q.L., Yang, Y.B.: Sa-net: shuffle attention for deep convolutional neural networks. In: ICASSP 2021–2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2235–2239. IEEE (2021)
Lin, T.Y., Dollar, P., Girshick, R., et al.: Feature pyramid networks for object detection. IEEE Comput. Soc. (2017)
Ren, Y., Zhang, H., Sun, H., et al.: LightRay: lightweight network for prohibited items detection in X-ray images during security inspection. Comput. Electr. Eng. 103, 108283 (2022)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Li, W., Li, X., Liu, W., Liu, Z., Jia, J., Li, J. (2023). X-ray Prohibited Items Recognition Based on Improved YOLOv5. In: Yuan, L., Yang, S., Li, R., Kanoulas, E., Zhao, X. (eds) Web Information Systems and Applications. WISA 2023. Lecture Notes in Computer Science, vol 14094. Springer, Singapore. https://doi.org/10.1007/978-981-99-6222-8_3
Download citation
DOI: https://doi.org/10.1007/978-981-99-6222-8_3
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-6221-1
Online ISBN: 978-981-99-6222-8
eBook Packages: Computer ScienceComputer Science (R0)
