Comparative Study of Deep Learning Architectures for Thermal vs. Millimeter-Wave Concealed Weapon Detection

CWD is becoming more and more essential for smart city security, while TIR and PMMW are emerging as promising sensing techniques that can be used in a privacy-respectful way to achieve the CWD objective. However, current studies focus on evaluating a single deep learning architecture with respect to a single sensor modality, raising the question of which architecture achieves the best performance on each sensor modality. This work aims to fill this gap by carrying out a systematic comparison among eight different deep learning architectures, a custom CNN, and seven transfer-learning architectures (namely, ResNet-18, ResNet-50, ResNet-152, DenseNet-121, DenseNet-201, and GoogleNet) in terms of their performance on balanced and curated sets of TIR and PMMW images, comprising respectively 686 samples for each category. The models were trained using the same training settings (Adam optimisation function, cross-entropy loss, learning rate 0.001, and batch size 32), while being evaluated with respect to accuracy, precision, recall, F1-score, inference latency, and size. The custom CNN was the only architecture to generalise well to both modalities, achieving 97.6% accuracy. On the other hand, TIR outperforms its nearest competitor on the same modality (ResNet-50, 78.5%) by 21.5 percentage points and also happens to be the most compact and computationally efficient network for this modality. This suggests that the choice of architecture for hidden weapon recognition should be modality-specific and not generic, and that specialized domain-trained architectures are worth considering for sensing modalities, which deviate significantly from natural images on which transfer learning architectures are pre-trained conventionally.

concealed weapon detection, deep learning, transfer learning

1. Bhardwaj, D., Ramamoorthy, A., & Goyal, P. (2025). DEF-YOLO: Leveraging YOLO for concealed weapon detection in thermal imaging. arXiv. https://arxiv.org/abs/2510.13326 [Google Scholar] [Crossref]

2. Cantero, D., Esnaola-González, I., Miguel-Alonso, J., & Jauregi, E. (2022). Benchmarking object detection deep learning models in embedded devices. Sensors, 22(11), Article 4205. https://doi.org/10.3390/s22114205 [Google Scholar] [Crossref]

3. Chicco, D., & Jurman, G. (2020). The advantages of the Matthews correlation coefficient (MCC) over the F1 score and accuracy in binary classification evaluation. BMC Genomics, 21, Article 6. https://doi.org/10.1186/s12864-019-6413-7 [Google Scholar] [Crossref]

4. Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009). ImageNet: A large-scale hierarchical image database. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, 248–255. https://doi.org/10.1109/CVPR.2009.5206848 [Google Scholar] [Crossref]

5. Dimanov, D., Singleton, C., Rostami, S., & Balaguer-Ballester, E. (2023). MEOW: Automatic evolutionary multi-objective concealed weapon detection. Proceedings of the Second International Conference on Automated Machine Learning, 224. https://proceedings.mlr.press/v224/dimanov23a.html [Google Scholar] [Crossref]

6. He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, 770–778. https://doi.org/10.1109/CVPR.2016.90 [Google Scholar] [Crossref]

7. Huang, G., Liu, Z., van der Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 4700–4708. https://doi.org/10.1109/CVPR.2017.243 [Google Scholar] [Crossref]

8. Khor, W., Chen, Y. K., Roberts, M., & Ciampa, F. (2024a). Automated detection and classification of concealed objects using infrared thermography and convolutional neural networks. Scientific Reports, 14, Article 8353. https://doi.org/10.1038/s41598-024-56636-8 [Google Scholar] [Crossref]

9. Khor, W., Chen, Y. K., Roberts, M., & Ciampa, F. (2024b). Non-contact, portable, and stand-off infrared thermal imager for security scanning applications. AIP Advances, 14(4), Article 045314. https://doi.org/10.1063/5.0188862 [Google Scholar] [Crossref]

10. Kingma, D. P., & Ba, J. (2015). Adam: A method for stochastic optimization. Proceedings of the 3rd International Conference on Learning Representations. https://arxiv.org/abs/1412.6980 [Google Scholar] [Crossref]

11. Muñoz, J. D., Ruiz-Santaquiteria, J., Deniz, O., & Bueno, G. (2025). Concealed weapon detection using thermal cameras. Journal of Imaging, 11(3), Article 72. https://doi.org/10.3390/jimaging11030072 [Google Scholar] [Crossref]

12. Murugan, T., Badusha, N. A. N. M., Semaihi, A. R. O. A., Alkindi, M. M. R., Alnaqbi, E. M. R., & Alketbi, G. H. T. (2025). AI-based weapon detection for security surveillance: Recent research advances (2016–2025). Electronics, 14(23), Article 4609. https://doi.org/10.3390/electronics14234609 [Google Scholar] [Crossref]

13. Pang, L., Liu, H., Chen, Y., & Miao, J. (2020). Real-time concealed object detection from passive millimeter wave images based on the YOLOv3 algorithm. Sensors, 20(6), Article 1678. https://doi.org/10.3390/s20061678 [Google Scholar] [Crossref]

14. Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: A simple way to prevent neural networks from overfitting. Journal of Machine Learning Research, 15(1), 1929–1958. [Google Scholar] [Crossref]

15. Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015). Going deeper with convolutions. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition, 1–9. https://doi.org/10.1109/CVPR.2015.7298594 [Google Scholar] [Crossref]

16. Veranyurt, O., & Sakar, C. O. (2023). Concealed pistol detection from thermal images with deep neural networks. Multimedia Tools and Applications, 82, 44259–44275. https://doi.org/10.1007/s11042-023-15358-1 [Google Scholar] [Crossref]

17. Wang, Z., Chang, T., & Cui, H.-L. (2019). Review of active millimeter wave imaging techniques for personnel security screening. IEEE Access, 7, 148336–148350. https://doi.org/10.1109/ACCESS.2019.2946736 [Google Scholar] [Crossref]

• Detecting Septoria Leaf-Spot Disease in Tomato Plants Using Shifted Window Transformer Model.