关键词: 数字识别, Hopfield神经网络, 高斯白噪声, 联想记忆, 信息还原

Abstract: Focused on the issue that the increasing traffic pressure on the highway, the efficiency of car management is getting lower and lower, A method of intelligent figure recognition of car license plate is proposed. The method utilizes the associative memory function of discrete Hopfield neural networks(DHNN), firstly, the figure lattice with complete information is input into the discrete Hopfield neural network, and the network is trained; Secondly, the interference encountered in the process of identifying the real car license plate is simulated by using rotation, covering and Gaussian white noise; Finally, the incomplete information affected by interference is input into the neural network, and it is associated and memorized by the network. Simulation results of these three figure identifications show that discrete Hopfield neural network can restore information very well, in addition, convergence speed of DHNN is very fast. Therefore, we can use the network to intelligently identify car licence plate and the management efficiency of car will be improved.

Key words: figure identification, Hopfield neural network, Gaussian white noise, associative memory, information restoration