Development of a Counterfeit Vehicle License Plate Detection System by Using Deep Learning

Abstract

In this study, a deep learning-based counterfeit plate detection system that compares and detects vehicles with the make, model, color, and license plate is designed. As known that the relevant government institutions are responsible for keeping all detailed information about all motor vehicles in their database. All registration details are stored in the database. It is possible to find unregistered vehicles by comparing database records with detected details. In general, vehicles with counterfeit license plates are used in illegal actions. Therefore, it is of great importance to detect them. Generally, license plate recognition systems successfully detect counterfeit license plates that are randomly generated. Security units typically use such systems at toll roads, bridge crossings, parking lot entrances and exits, sites, customs gates, etc. This kind of system only checks the plate is exists or not in the database. But it is unsuccessful if the vehicle uses existing plate numbers such as stolen ones. In this study, the developed system can detect not only vehicles' plate numbers but also make, model, year, and color information by using deep learning. Thus, the system can also detect randomly generated plates and stolen plates that belong to another vehicle.

Keywords

• deep learning
• convolutional neural networks (CNN)
• counterfeit plate

References

1. A. Şeker, B. Diri, and H. Balık, “Derin Öğrenme Yöntemleri ve Uygulamaları Hakkında Bir İnceleme”, Gazi Journal of Engineering Sciences, vol. 3, no. 3, 2017, pp. 47–64.
2. K. Fukushima, “Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position”, Biological Cybernetics, vol. 36, no. 4, 1980, pp. 193–202.
3. Z. Yumeng, C. Peng, F. Liuping and C. Fangfang, "Research on Pseudo-Random Noise Information Identification Technology of Printed Anti-Counterfeiting Image Based on Deep Learning", 2020 5th International Conference on Computer and Communication Systems (ICCCS), 2020, pp. 206-209.
4. Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-Based Learning Applied to Document Recognition”, Proc. of the IEEE, vol. 86, no. 11, 1998, pp. 2278-2324.
5. Y. Lecun, L.D. Jackel, B. Boser, J.S. Denker, H.P. Graf, I. Guyon. D. Henderson, R. E. Howard and W. Hubbard, “Handwritten digit recognition: applications of neural network chips and automatic learning”, IEEE Communications Magazine, vol. 27, no. 11, 1989, pp. 41-46.
6. J. L. Elman, “Finding structure in time”, Cognitive Science, vol. 14, no. 2, 1990, pp. 179–211.
7. S. Hochreiter and J. Schmidhuber, “Long Short-Term Memory”, Neural Computation, vol. 9, no. 8, 1997, pp. 1735–1780.
8. G. E. Hinton, “Reducing the Dimensionality of Data with Neural Networks”, International Encyclopedia of Education, vol. 313, no. July, 2006, pp. 468–474.

9. L. Tang, Z. Gao and L. Huang, "Plate Recognition Based on Deep Learning", 2018 12th IEEE International Conference on Anti-counterfeiting Security and Identification (ASID), 2018, pp. 116-120.
10. Ş. Abdulkadir and A. G. Yüksek, “Stacked Autoencoder Method for Fabric Defect Detection”, Cumhuriyet Science Journal, vol. 38, no. 2, 2017, pp. 342–342.
11. G. Erdemir and B. Ağgül, “Data Augmentation for a Learning-Based Vehicle Make-Model and License Plate Matching System”, European Journal of Technic, vol. 10, no. 2, 2020, pp. 331–339.
12. C. Bircanoğlu and N. Arıca, "A comparison of activation functions in artificial neural networks", 2018 26th Signal Processing and Communications Applications Conference (SIU), 2018, pp. 1-4.
13. N. Srivastava and G. Hinton, A. Krizhevsky, I. Sutskever and R. Salakhutdinov, “Dropout: A Simple Way to Prevent Neural Networks from Overfitting”, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 15, 2018, pp. 7642–7651.
14. M. M. Lau and K. H. Lim, “Review of adaptive activation function in deep neural network”, 2018 IEEE EMBS Conference on Biomedical Engineering and Sciences, IECBES 2018 - Proceedings, 2019, pp. 686–690.
15. H. H. Tan and K. H. Lim, “Vanishing Gradient Mitigation with Deep Learning Neural Network Optimization”, 2019 7th International Conference on Smart Computing and Communications (ICSCC), 2019, pp. 7–10.
16. M. Kaloev and G. Krastev, "Comparative Analysis of Activation Functions Used in the Hidden Layers of Deep Neural Networks", 2021 3rd International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA), 2021, pp. 1-5.
17. O. Sharma, “A New Activation Function for Deep Neural Network”, Proceedings of the International Conference on Machine Learning, Big Data, Cloud and Parallel Computing: Trends, Prespectives and Prospects, COMITCon, 2019, pp. 84–86.
18. H. Chung, S. J. Lee, and J. G. Park, “Deep neural network using trainable activation functions”, Proceedings of the International Joint Conference on Neural Networks, vol. 2016-October, no. l, pp. 348–352.
19. M. A. Mercioni and S. Holban, "The Most Used Activation Functions: Classic Versus Current", 2020 International Conference on Development and Application Systems (DAS), 2020, pp. 141-145.
20. B. Ağgül and G. Erdemir, “Açık Kaynak Kodlu Taşıt Renk Tespit Yazılımı Geliştirilmesi”, İstanbul Sabahattin Zaim Üniversitesi Fen Bilimleri Enstitüsü Dergisi, vol. 3, no. 1, Mar. 2021, pp. 47-50.
21. O. Kaplan, Ş. Sağıroğlu, Ö.F. Çolakoğlu, “Erciyes Üniversitesi Bilgisayar Mühendisliği Bölümü Araç Tanıma Sistemi”, 2002, pp. 2–6
22. Ş. Sağıroğlu and E. Beşdok, “A Novel Approach for Image Denoising Based on Artificial Neural Networks”, vol. 15, no. 2, 2012, pp. 71–86.
23. O. Bingöl and Ö. Kuşçu, “Bilgisayar Tabanlı Araç Plaka Tanıma Sistemi”, Bilişim Teknolojileri Dergisi, vol. 1, no. 3, 2008, p. 1-5.