With the prosperity and development of economy and the improvement of people's consumption level, cars have become a necessity for people. With the increase of the number of vehicles and the progress of the information age, the demand for traffic control, especially the information and intelligent management of vehicles, is increasing, so license plate recognition is very important for modern intelligent traffic management. In this paper, Matlab software development environment is used to read the vehicle image and a series of image processing technologies such as image graying, license plate segmentation, license plate location, license plate character segmentation and license plate character recognition to obtain the license plate recognition results. The difficulty in this design is the license plate character segmentation and the license plate character recognition. In the aspect of license plate character segmentation, we should first find the continuous text block, and then decide whether to segment it according to the length. If the length of the found continuous text block is greater than the threshold, it means that this text block can be divided. In recognition of license plate characters, in order to improve the accuracy of license plate recognition, this paper adopts BP neural network algorithm. Finally, the license plate recognition results are displayed through the GUI design interface.
正在翻译中..