Feature Fusion Using Deep Learning Algorithms in Image Classification for Security Purposes by Random Weight Network
Source abstract
Abstract
Automated threat detection in X-ray security imagery is a critical yet challenging task, where conventional deep learning models often struggle with low accuracy and overfitting. This study addresses these limitations by introducing a novel framework based on feature fusion. The proposed method extracts features from multiple and diverse deep learning architectures and classifies them using a Random Weight Network (RWN), whose hyperparameters are optimized for maximum performance. The results show substantial improvements at each stage: while the best standalone deep learning model achieved a test accuracy of 83.55%, applying the RWN to a single feature set increased accuracy to 94.82%. Notably, the proposed feature fusion framework achieved a state-of-the-art test accuracy of 97.44%. These findings demonstrate that a modular approach combining multi-model feature fusion with an efficient classifier is a highly effective strategy for improving the accuracy and generalization capability of automated threat detection systems.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Machine Learning and ELM · Face and Expression Recognition · Brain Tumor Detection and Classification
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Computer Engineering, Faculty of Computer and Information Sciences, Konya Technical University, Konya 42250, Türkiye
Department of Software Engineering, Faculty of Engineering and Natural Sciences, Gümüşhane University, Gümüşhane 29100, Türkiye
Department of Software Engineering, Faculty of Computer and Information Sciences, Konya Technical University, Konya 42250, Türkiye
College of Computer Science and Software Engineering, Shenzhen University, Shenzhen 518060, China
References (58)
Show source-provided references
1. X-Ray Image Analysis for Explosive Circuit Detection using Deep Learning Algorithms
2. Wikipedia (2022, August 26). X-Ray. Available online: https://en.wikipedia.org/wiki/X-ray.
3. Explosives detection systems (EDS) for aviation security10.1016/S0165-1684(02)00391-2 ↗
4. Mery, D., Riffo, V., Zuccar, I., and Pieringer, C. (2013, January 23–28). Automated X-ray object recognition using an efficient search algorithm in multiple views. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Portland, OR, USA.10.1109/CVPRW.2013.62 ↗
5. Schmidt-Hackenberg, L., Yousefi, M.R., and Breuel, T.M. (2012, January 11–15). Visual cortex inspired features for object detection in X-ray images. Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012), Tsukuba, Japan.
6. Akçay, S., Kundegorski, M.E., Devereux, M., and Breckon, T.P. (2016, January 25–28). Transfer learning using convolutional neural networks for object classification within x-ray baggage security imagery. Proceedings of the 2016 IEEE International Conference on Image Processing (ICIP), Phonix, AZ, USA.10.1109/ICIP.2016.7532519 ↗
7. Jaccard, N., Rogers, T.W., Morton, E.J., and Griffin, L.D. (2016, January 19–20). Tackling the X-ray cargo inspection challenge using machine learning. Proceedings of the Anomaly Detection and Imaging with X-Rays (ADIX), Baltimore, MD, USA.10.1117/12.2222765 ↗
8. Modern computer vision techniques for x-ray testing in baggage inspection10.1109/TSMC.2016.2628381 ↗
9. Detection of concealed cars in complex cargo X-ray imagery using deep learning
10. Rogers, T.W., Jaccard, N., and Griffin, L.D. (2017, January 12–13). A deep learning framework for the automated inspection of complex dual-energy X-ray cargo imagery. Proceedings of the Anomaly Detection and Imaging with X-Rays (ADIX) II, Anaheim, CA, USA.10.1117/12.2262662 ↗
11. Caldwell, M., Ransley, M., Rogers, T.W., and Griffin, L.D. (2017, January 11–14). Transferring x-ray based automated threat detection between scanners with different energies and resolution. Proceedings of the Counterterrorism, Crime Fighting, Forensics, and Surveillance Technologies, Warsaw, Poland.
12. Morris, T., Chien, T., and Goodman, E. (2018, January 17–20). Convolutional neural networks for automatic threat detection in security X-Ray images. Proceedings of the 17th IEEE International Conference on Machine Learning and Applications (ICMLA), Orlando, FL, USA.10.1109/ICMLA.2018.00049 ↗
13. Akcay, S., and Breckon, T.P. (2017, January 17–20). An evaluation of region based object detection strategies within X-ray baggage security imagery. Proceedings of the IEEE International Conference on Image Processing (ICIP), Beijing, China.10.1109/ICIP.2017.8296499 ↗
14. Using deep convolutional neural network architectures for object classification and detection within x-ray baggage security imagery10.1109/TIFS.2018.2812196 ↗
15. Petrozziello, A., and Jordanov, I. (2019, January 24–29). Automated deep learning for threat detection in luggage from X-ray images. Proceedings of the International Symposium on Experimental Algorithms, Kalamata, Greece.10.1007/978-3-030-34029-2_32 ↗
16. X-YOLO: An Efficient Detection Network of Dangerous Objects in X-ray Baggage Images10.1109/LSP.2024.3451311 ↗
17. EslaXDET: A new X-ray baggage security detection framework based on self-supervised vision transformers10.1016/j.engappai.2023.107440 ↗
18. Wang, S., Wang, S., and Xiao, Z. (2025, January 13–15). Feature extraction method with efficient edge information enhancement for detecting dangerous objects in security x-ray images. Proceedings of the International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID 2024), Nanchang, China.10.1117/12.3061270 ↗
19. Data augmentation for X-ray prohibited item images using generative adversarial networks10.1109/ACCESS.2019.2902121 ↗
20. In-depth analysis of automated baggage inspection using simulated X-ray images of 3D models10.1007/s00521-024-10159-5 ↗
21. Limits on transfer learning from photographic image data to X-ray threat detection
22. Material classification in X-ray images based on multi-scale CNN10.1007/s11760-021-01859-9 ↗
23. A binary sparrow search algorithm for feature selection on classification of X-ray security images10.1016/j.asoc.2024.111546 ↗
24. Network intrusion detection using feature fusion with deep learning10.1186/s40537-023-00834-0 ↗
25. Baby cry recognition by BCRNet using transfer learning and deep feature fusion10.1109/ACCESS.2023.3330789 ↗
26. Wu, X., Shi, H., and Zhu, H. (2023). Fault Diagnosis for Rolling Bearings Based on Multiscale Feature Fusion Deep Residual Networks. Electronics, 12.10.3390/electronics12030768 ↗
27. Liu, H., Hou, C.-J., Tang, J.-L., Sun, L.-T., Lu, K.-F., Liu, Y., and Du, P. (2023). Deep learning and ultrasound feature fusion model predicts the malignancy of complex cystic and solid breast nodules with color Doppler images. Sci. Rep., 13.10.1038/s41598-023-37319-2 ↗
28. Patil, S., and Kirange, D. (2023). An Optimized Deep Learning Model with Feature Fusion for Brain Tumor Detection. Int. J. Next-Gener. Comput., 14.10.47164/ijngc.v14i1.1032 ↗
29. Fruit type classification using deep learning and feature fusion10.1016/j.compag.2023.107990 ↗
30. Deng, T., Wang, H., He, D., Xiong, N., Liang, W., and Wang, J. (2023). Multi-Dimensional Fusion Deep Learning for Side Channel Analysis. Electronics, 12.10.3390/electronics12234728 ↗
31. Al-Timemy, A.H., Alzubaidi, L., Mosa, Z.M., Abdelmotaal, H., Ghaeb, N.H., Lavric, A., Hazarbassanov, R.M., Takahashi, H., Gu, Y., and Yousefi, S. (2023). A Deep Feature Fusion of Improved Suspected Keratoconus Detection with Deep Learning. Diagnostics, 13.10.3390/diagnostics13101689 ↗
32. Lung lobe segmentation in computed tomography images based on multi-feature fusion and ensemble learning framework10.1002/ima.22910 ↗
33. A deep reinforcement learning hyper-heuristic with feature fusion for online packing problems10.1016/j.eswa.2023.120568 ↗
34. Automobile Component Recognition Based on Deep Learning Network with Coarse-Fine-Grained Feature Fusion10.1155/2023/1903292 ↗
35. Identification based on feature fusion of multimodal biometrics and deep learning
36. Ma, J., Zhang, Y., Li, Y., Zhou, L., Qin, L., Zeng, Y., Wang, P., and Lei, Y. (2021). Deep dual-side learning ensemble model for Parkinson speech recognition. Biomed. Signal Process. Control, 69.10.1016/j.bspc.2021.102849 ↗
37. Alzubaidi, L., Salhi, A., A. Fadhel, M., Bai, J., Hollman, F., Italia, K., Pareyon, R., Albahri, A., Ouyang, C., and Santamaría, J. (2024). Trustworthy deep learning framework for the detection of abnormalities in X-ray shoulder images. PLoS ONE, 19.10.1371/journal.pone.0299545 ↗
38. Agarwal, S., Arya, K., and Meena, Y.K. (2024). Multifusionnet: Multilayer multimodal fusion of deep neural networks for chest x-ray image classification. arXiv.10.21203/rs.3.rs-2443352/v1 ↗
39. Li, J., Shan, H.-J., and Yu, X.-W. (2025). Fracture detection of distal radius using deep-learning-based dual-channel feature fusion algorithm. Chin. J. Traumatol., 1–13.10.1016/j.cjtee.2024.10.006 ↗
40. A literature review on deep learning algorithms for analysis of X-ray images10.1007/s13042-023-01961-z ↗
41. Sani, S., Wiratunga, N., and Massie, S. (2017, January 26–28). Learning deep features for kNN-based human activity recognition. Proceedings of the ICCBR 2017 Workshops, Trondheim, Norway.
42. Singh, J., Thakur, D., Ali, F., Gera, T., and Kwak, K.S. (2020). Deep feature extraction and classification of android malware images. Sensors, 20.10.3390/s20247013 ↗
43. Multi-features extraction based on deep learning for skin lesion classification10.1016/j.tice.2021.101701 ↗
44. Functional-link net computing: Theory, system architecture, and functionalities10.1109/2.144401 ↗
45. Schmidt, W.F., Kraaijveld, M.A., and Duin, R.P. (September, January 30). Feed forward neural networks with random weights. Proceedings of the International Conference on Pattern Recognition, The Hague, The Netherlands.
46. Huang, G.-B., Zhu, Q.-Y., and Siew, C.-K. (2004, January 25–29). Extreme learning machine: A new learning scheme of feedforward neural networks. Proceedings of the IEEE international Joint Conference on Neural Networks (IEEE Cat. No. 04CH37541), Budapest, Hungary.
47. Extreme learning machine: Theory and applications10.1016/j.neucom.2005.12.126 ↗
48. Dorogush, A.V., Ershov, V., and Gulin, A. (2018). CatBoost: Gradient boosting with categorical features support. arXiv.
49. Quinlan, J.R. (2014). C4.5: Programs for Machine Learning, Elsevier.
50. Mitchell, T.M., and Mitchell, T.M. (1997). Machine Learning, McGraw-Hill.
51. Natekin, A., and Knoll, A. (2013). Gradient boosting machines, a tutorial. Front. Neurorobot., 7.10.3389/fnbot.2013.00021 ↗
52. Nearest neighbor pattern classification10.1109/TIT.1967.1053964 ↗
53. Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., and Liu, T.-Y. (2017). Lightgbm: A highly efficient gradient boosting decision tree. Adv. Neural Inf. Process. Syst., 30.
54. The regression analysis of binary sequences10.1111/j.2517-6161.1958.tb00292.x ↗
55. Random forests10.1023/A:1010933404324 ↗
56. Ridge regression: Biased estimation for nonorthogonal problems10.1080/00401706.1970.10488634 ↗
57. Cortes, C., and Vapnik, V. (1995). Support-Vector Networks. Machine Learning, Springer.10.1023/A:1022627411411 ↗
58. Chen, T., and Guestrin, C. (2016, January 13–17). Xgboost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.10.1145/2939672.2939785 ↗