汽车牌照定位与识别系统设计

Design of Location and Recognition System of License Plate

车牌自动识别系统对于智能交通的发展至关重要。针对国内较多的蓝底白字车牌和黄底单行黑字车牌汽车图像,分别从车牌定位、字符分割和字符识别三个模块出发,提出基于颜色定位、边缘检测和支撑向量机相结合的方法实现车牌区域的准确定位;采用字符轮廓寻找法及人工神经网络法实现字符分割及字符识别,可有效识别比较复杂环境下的车牌颜色和车牌号码。基于C++平台设计了一种汽车牌照自动定位和识别系统。大量实验结果表明,三个模块和整体系统的总体识别率都能达到92%以上甚至更高,并且通用于蓝牌小轿车和黄牌单行字符的大轿车。

Automatic license plate recognition system is crucial to the development of intelligent transportation. In view of many domestic vehicle images with white letters on a blue background and black letters on a yellow background, starting from the three modules of license plate location, character segmentation and character recognition, a method based on the combination of color location,edge detection and support vector machine is proposed to realize the accurate location of the license plate area;The character contour search method and artificial neural network method are used to realize character segmentation and character recognition, which can effectively recognize the color and number of the license plate in a relatively complex environment. A vehicle license plate automatic location and recognition system is designed based on C++platform. A large number of experimental results show that the overall recognition rate of the three modules and the whole system can reach more than 92% or even higher, and it is applicable to blue car and yellow car with single-line characters.