Design of License Plate Recognition System Based on OpenCV

With the continuous improvement of people's living standards, the number and types of motor vehicles are increasing, and it is more and more difficult to manage these vehicles. The most important part of vehicle management information is the license plate of each motor vehicle. They are the identity cards of motor vehicles, so a license plate recognition system that can accurately identify is indispensable. Manual recognition has been difficult to cope with the growing demand for license plate recognition. The traditional license plate recognition system has been overwhelmed. They can not cope with a variety of cars and their license plates, especially the emergence of new energy license plates with green as the background color, resulting in a significant decrease in the accuracy of the traditional license plate recognition system. Therefore, it is necessary to introduce more accurate and efficient technologies in the license plate recognition system, such as widely used machine learning. In this paper, Python as the building language, based on OpenCV library to build a license plate recognition system. The system mainly uses the display function in CV2 and the Gaussian filter grayscale processing function to complete the image display and denoising grayscale processing. Locating the license plate is based on the results of the previous step to extract the corresponding mathematical and color features to complete, and then segment the license plate area of continuous strings, the use of neural networks based on kears framework to identify a single character. Through the test set test of the license plate recognition system, the accuracy of the system to identify the license plate is 93.33 %.