Detection of Harmful Objects Using Deep Learning Models
DOI:
https://doi.org/10.56294/piii2025523Keywords:
Harmful Objects, Deep Learning Models, convolutional neural networks, region-based CNNs, transfer learning modelsAbstract
The identification of harmful objects is vital for maintaining public safety in areas like transportation, security, and manufacturing. Conventional methods for detecting such objects often depend on manual inspection, which can be both labour-intensive and prone to errors. Recently, deep learning models have proven to be highly effective in automating object detection tasks, leveraging their capability to recognize intricate patterns and features from extensive datasets. Our dataset includes over 9,000 images spanning five categories: alcohol, blood, cigarette, gun, and knife. This document provides a detailed analysis of deep learning approaches for harmful object detection, focusing on techniques like convolutional neural networks (CNNs), region-based CNNs (R-CNN), and transfer learning models such as VGG16, while also comparing the performance across various deep learning models.
References
1. Sun, R. Y. (2020). A comprehensive review of optimization techniques in deep learning. Journal of the Operations Research Society of China, 8(2), 249-294.
2. Desai, C. (2020). Comparative study of optimization algorithms in deep neural networks. International Journal of Innovative Science and Research Technology, 5(10), 959-962.
3. Ruder, S. (2016). An overview of optimization algorithms for gradient descent. arXiv preprint arXiv:1609.04747.
4. Zhang, J. (2019). Gradient descent optimization methods for training deep learning models. arXiv preprint arXiv:1903.03614.
5. Dataset: https://github.com/poori-nuna/HOD-Benchmark-Dataset.
6. Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Deep convolutional neural networks for ImageNet classification. Advances in Neural Information Processing Systems, 25.
7. Sravani, R., & Reddy, D. V. S. (2021). Harmful object detection using deep learning techniques. International Journal of Scientific Research in Science, Engineering, and Technology, 9(2), 116-121.
8. Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986). Learning representations through error backpropagation. Nature, 323(6088), 533–536.
9. Nair, V., & Hinton, G. E. (2010). Enhancing restricted Boltzmann machines using rectified linear units. In Proceedings of the 27th International Conference on Machine Learning (pp. 807–814).
10. Bridle, J. S. (1990). Probabilistic interpretation of feedforward network outputs in relation to statistical pattern recognition. Neurocomputing, 6(1), 227–236.
11. Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You Only Look Once: A unified, real-time object detection system. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 779-788.
12. Zeng, Y., Zhang, L., Zhao, J., et al. (2021). JRL-YOLO: A novel structure for real-time hazardous object detection. Computational Intelligence and Neuroscience, 1-12.
13. Maas, A. L., Hannun, A. Y., & Ng, A. Y. (2013). Enhancing neural network acoustic models with rectifier nonlinearities. In Proceedings of the 30th International Conference on Machine Learning (pp. 3–11).
14. Meng, Z., Zhang, M., & Wang, H. (2020). CNN with pose segmentation for suspicious object detection in security images. Sensors (Basel, Switzerland), 20(17), 4974.
15. Yang, S., Sun, J., Duan, Y., Li, X., & Zhang, B. (2020). Dangerous object detection using deep learning in convolutional networks. Proceedings of SPIE 11427, 1142722.
16. Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
17. Simonyan, K., & Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. Proceedings of the International Conference on Learning Representations (ICLR).
18. Fu, Y., Lou, F., Meng, F., Tian, Z., Zhang, H., & Jiang, F. (2018). A network-based method for detecting intelligent network attacks. 2018 IEEE Third International Conference on Data Science in Cyberspace (DSC), 483-489.
19. Ma, J., Peng, Y., Long, J., & Wu, Z. (2018). Object detection using recurrent convolutional neural networks and deep reinforcement learning. IEEE Access, 6, 72118-72130.
20. Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735-1780.
21. Li, S., Li, H., Wu, Z., Bao, G., Qian, K., & Li, Y. (2021). Detection of foreign objects using LSTM for wireless power transfer systems. 2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT), 165-169.
22. Hinton, G. E., & Salakhutdinov, R. R. (2006). Reducing data dimensionality using neural networks. Science, 313(5786), 504–507.
23. Vincent, P., Larochelle, H., Bengio, Y., & Manzagol, P. A. (2008). Denoising autoencoders for robust feature extraction. In Proceedings of the 25th International Conference on Machine Learning (ICML), 1096–1103.
24. Rasmus, A., Berglund, M., Honkala, M., Valpola, H., & Raiko, T. (2015). Semi-supervised learning with ladder networks. Advances in Neural Information Processing Systems (NIPS), 28, 3546–3554.
25. Kingma, D. P., & Welling, M. (2013). Auto-Encoding Variational Bayes. arXiv preprint arXiv:1312.6114.
26. Doersch, C. (2016). Tutorial on variational autoencoders. arXiv preprint arXiv:1606.05908.
27. Zhang, K., Zuo, W., Chen, Y., Meng, D., & Zhang, L. (2017). Deep CNN for image denoising: Beyond a Gaussian denoiser. IEEE Transactions on Image Processing, 26(7), 3142–3155.
28. Luo, Y., Yang, Y., Yang, Y., Li, S., Zhang, L., Dong, J., & Huang, Q. (2018). Discriminative feature learning for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 1857–1866.
29. Joshi, T., Aarya, H., & Kumar, P. (2016). Suspicious object detection in security systems. 2016 2nd International Conference on Advances in Computing, Communication, & Automation (ICACCA), 1-6.
30. Todkari, V., Pawar, A., Shanbhag, Y., Rajput, G., & Bhoye, T. (2018). A review of suspicious object detection methods. International Journal of Advance Research and Innovative Ideas in Education, 4, 628-631.
31. Kaya, M., Karakus, B., & Karakuş, S. (2018). Criminal tool classification using CNN for forensic image analysis. 2018 International Conference on Artificial Intelligence and Data Processing (IDAP), 1-6.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Chilukuri Ganesh, Gandikota Harshavardhan, Naishadham Radha Sri Keerthi, Raj Veer Yabaji, Rajveer Yabaji, Meghana Sadhu (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
The article is distributed under the Creative Commons Attribution 4.0 License. Unless otherwise stated, associated published material is distributed under the same licence.
