An Algorithm of License Plate Recognition Based on Improved PSO-BP Network

Abstract:

Aiming at the problems of BP network algorithm easily falling into local minimum point, slow converging and the problem that generalization ability can not be guaranteed, a method to improve the PSO is proposed. This method of improved PSO can strengthen the parameters of BP network. Based on this, a license plate recognition algorithm is designed. Some conclusions can be drawn from the experiments: (1) the improved PSO-BP network is stable and robust which can avoid falling into flat areas and local minimum point. (2) the performance and efficiency of license plate recognition based on the improved PSO-BP network is pretty good.

• Periodical: Applied Mechanics and Materials (Volumes 427-429)
• Pages: 1714-1717
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.427-429.1714
• Online since: September 2013
• Authors: Zuo Jun Liu*, Li Hong Li
• Keywords: BP Network, License Plate Recognition, Particle Swarm Optimization (PSO)

References

[1] ZENG Xiao-qin. Particle Swarm Optimization Algorithm and Its Application in Neural Networks, Electric Drive Automation, 2009. 31(5).

[2] Kennedy J, Eberhart R C. Particle Swarm Optimization. Perth: Proceedings of the IEEE International Conference on Neural Networks. Piscataway: IEEE Press, 1995(11): 1942-(1948).

[3] GAO Yuelin. An Adaptive Particle Swarm Optimization Algorithm with New Random Inertia Weight [J]. Communications in computer and Information Science, 2007(3): 342-350.

DOI: 10.1007/978-3-540-74282-1_39

[4] XU Jun. The Study on Short-term Electric Load Forecasting Based on PSO-BP. the Master Thesis of Wuhan University of Technology, 2007. 11.

[5] HUANG Li-jun, GUO Wen-zhong. BP Neural Network Forecasting Method and Its Application Based on Particle Swarm Optimization. Journal of Zhangzhou Normal University (Nat. Sci. ), 2008. 1.