In order to realize the restoration of the blurred image by using the Generative Adversarial Networks, this paper proposes to add generator loss optimization and network depth optimization based on the generation of the Generative Adversarial Networks(GANs) with gradient penalty. This paper adds Perceptual Loss and ResNet. The perceptual loss is migrated from the image style migration network module as the second item added to the loss to the generator loss function, learning the clear image style and facilitating the correction generation. Add residual modules to the generator network to reduce network degradation while deepening network depth. The network structure model optimized in this paper shows relatively good test results in the subsequent experiments.
It is usually hard for traditional machine-learning-based classification algorithms such as Support Vector Machine (SVM) to classify similar characters in the process of license plate character recognition. In this paper, we introduced an efficient character recognition system based on a local, robust shape descriptor called the shape context to solve this problem. We also improved the matching strategy overcome shape context’s slow running speed. Experiment result shows the proposed algorithm has higher accuracy and quicker running speed compare to traditional machine- learning-based algorithms.