Research and Design of Automatic License Plate Recognition System Based on Android Platform

Abstract

In order to facilitate the staff to use the mobile phone to quickly and accurately obtain vehicle information to complete the vehicle inspection, based on the research of digital image processing technology and convolutional neural network theory, an automatic vehicle license plate recognition system which uses the open source computer vision library Opencv and the deep neural network framework Tensorflow based on the Android platform is developed. This system completes the tasks of finding the position of the license plate of the vehicle, segmenting and recognizing the characters of the license plate. Experiment results show that this system has a certain adaptability and a good license plate recognition effect.