Research of license plate recognition based on improved BP neural network

The paper considers a new design of BP neural network for license plate recognition. The primary contribution of the paper is in proposing an improved neural network structure, which combines the nowadays-new license plate features with the existing license plate recognition based on BP neural network. Furthermore the back propagation-learning rate and recognition rate of the BP neural network are improved; consequently study time is reduced. The experimental result shows that the new network structure can yield robustness and effectiveness on character recognition.