Comparative Study on License Plate Recognition using Deep Learning

International Journal of Computer Science (IJCS) Published by SK Research Group of Companies (SKRGC)

Abstract

Automatic License Plate Recognition (ALPR) plays a crucial role in criminal cases, traffic accident cases and many other cases. A generalized algorithm cannot be designed since each country has different style of license plates. ALPR suffers from illumination problem, unconstrained scenario problem etc. This paper compares three recent deep learning models that are designed for ALPR. All the three models are tested on Chinese City Parking Dataset (CCPD). Experimental results are compared in terms of accuracy. It is also analysed by dividing the dataset into set of images. It is observed that VSNet achieves higher accuracy of 99.5% than other two models.

References

[1] Lum, Cynthia, et al, “License plate reader (LPR) police patrols in crime hot spots: an experimental evaluation in two adjacent jurisdictions,” Journal of Experimental Criminology, vol. 7, no. 4, pp. 321-345, 2011.

[2] Anagnostopoulos, Christosnikolaos, et al, “A License Plate Recognition Algorithm for Intelligent Transportation System Applications,” IEEE Transactions on Intelligent Transportation Systems, vol. 7, no. 3, pp. 377-392, 2006.

[3] Sanyuan, Zhang, Zhang Mingli, and Ye Xiuzi, “Car plate character extraction under complicated environment,” systems, man and cybernetics, pp. 4722-4726, 2004.

[4] P.Praveena, “A Deep Learning Perspective of Computer Vision Algorithms”, International Journal of Computer Science, Volume 10, Issue 1, No 1, 2022, pp. 2657-2667.

[5] J. Hsieh, S. Yu, and Y. Chen, ‘‘Morphology-based license plate detection from complex scenes,’’ presented at the Int. Conf. Pattern Recognit., 2002, doi: 10.1109/ICPR.2002.1047823.

[6] Rakhshani, S., Rashedi, E. and Nezamabadi-pour, H., 2019. License plate recognition using deep learning. Journal of Machine Vision and Image Processing, 6(1), pp.31-46.

[7] Sowmyayani, S. and Rani, P., 2022. Salient object based visual sentiment analysis by combining deep features and handcrafted features. Multimedia Tools and Applications, 81(6), pp.7941-7955.

[8] Sutar, G.T., Lohar, A.M. and Jadhav, P.M., 2019. Number plate recognition using an improved segmentation. LAP LAMBERT Academic Publishing.

[9] Liu, J., Zheng, F., van Zuylen, H.J. and Li, J., 2020. A dynamic OD prediction approach for urban networks based on automatic number plate recognition data. Transportation Research Procedia, 47, pp.601-608.

[10] Akhtar, Z. and Ali, R., 2020. Automatic number plate recognition using random forest classifier. SN Computer Science, 1(3), pp.1-9.

[11] Agrawal, R., Agarwal, M. and Krishnamurthi, R., 2020, March. Cognitive number plate recognition using machine learning and data visualization techniques. In 2020 6th international conference on signal processing and communication (ICSC) (pp. 101-107). IEEE.

[12] Qi, X., Ji, Y., Li, W. and Zhang, S., 2021. Vehicle trajectory reconstruction on urban traffic network using automatic license plate recognition data. IEEE Access, 9, pp.49110-49120.

[13] Zhang, Y., Qiu, M., Ni, Y. and Wang, Q., 2020, October. A Novel Deep Learning Based Number Plate Detect Algorithm under Dark Lighting Conditions. In 2020 IEEE 20th International Conference on Communication Technology (ICCT) (pp. 1412-1417). IEEE.

[14] Weihong, W. and Jiaoyang, T., 2020. Research on license plate recognition algorithms based on deep learning in complex environment. IEEE Access, 8, pp.91661-91675.

[15] Pustokhina, I.V., Pustokhin, D.A., Rodrigues, J.J., Gupta, D., Khanna, A., Shankar, K., Seo, C. and Joshi, G.P., 2020. Automatic vehicle license plate recognition using optimal K-means with convolutional neural network for intelligent transportation systems. Ieee Access, 8, pp.92907-92917.

[16] Henry, C., Ahn, S.Y. and Lee, S.W., 2020. Multinational license plate recognition using generalized character sequence detection. IEEE Access, 8, pp.35185-35199.

[17] Liu, Y., Yan, J. and Xiang, Y., 2020, September. Research on license plate recognition algorithm based on ABCNet. In 2020 IEEE 3rd International Conference on Information Systems and Computer Aided Education (ICISCAE) (pp. 465-469). IEEE.

[18] Silva, S.M. and Jung, C.R., 2021. A flexible approach for automatic license plate recognition in unconstrained scenarios. IEEE Transactions on Intelligent Transportation Systems.

[19] Wang, T., Zhu, Y., Jin, L., Luo, C., Chen, X., Wu, Y., Wang, Q. and Cai, M., 2020, April. Decoupled attention network for text recognition. In Proceedings of the AAAI conference on artificial intelligence (Vol. 34, No. 07, pp. 12216-12224).

[20] Zhang, L., Wang, P., Li, H., Li, Z., Shen, C. and Zhang, Y., 2020. A robust attentional framework for license plate recognition in the wild. IEEE Transactions on Intelligent Transportation Systems, 22(11), pp.6967-6976.

[21] Wang, Y., Bian, Z.P., Zhou, Y. and Chau, L.P., 2021. Rethinking and designing a high-performing automatic license plate recognition approach. IEEE Transactions on Intelligent Transportation Systems.

[22] Zhenbo Xu, Wei Yang, Ajin Meng, Nanxue Lu, Huan Huang, Changchun Ying, and Liusheng Huang, “Towards end-to-end license plate detection and recognition: A large dataset and baseline,” in Proceedings of the European Conference on Computer Vision, 2018, pp. 255–271.

Keywords

Convolutional Neural Network, Character Recognition, Segmentation