Improved CNN license plate image recognition based on shark odor optimization algorithm

The recent development in the domestic economy has increased the number of private vehicles leading to the issue of road congestions and traffic accidents. The diversity and severity of traffic problems leads to the requirements of modern intelligent transportation systems. In case of vehicle license identification, plate positioning plays a very vital role and this is the key factor affecting the accuracy of the system. In order to alleviate traffic pressure, solve the problem of road congestion, this paper is based on Convolutional Neural Network (CNN) license plate character identification. This article adopts the license plate character identification employing the CNN model and uses the neural network optimization principles for the improved construction. By adopting neural network principles, it is improved, and the license plate identification model is constructed. The results show that based on CNN-based license plate character identification model, the identification of license plate characters is completed, and the license plate recognition has been significantly improved, accurate rate of 99%.