摘要
以快速准确识别汽车牌照号码为目的,在充分利用数学形态学与多特征组合分析相结合分析的基础上,运用灰度变换、边缘检测、Radon变换、投影特征等图像处理方法,分车牌检测、字符分割、字符识别三步实现汽车牌照的识别,处理过程中考虑并解决了现实拍摄图像中存在的牌照倾斜等不利条件,用MATLAB软件对这些算法进行仿真,经过对多幅图像的处理实验表明,该系统识别速度快,识别率高。
This paper studied vehicle License Plate Recognition System(LPRS) algorithms model to promote recognition speed and precision.A new method was proposed for car license plate location by combining morphology and multiple features.Characters on license plate were segmented by projection and pre-known knowledge of the character size and the space between characters in plate. For character recognition,an improved BP neural network is used to carry out the recognition of letters and numbers in the license plate.The experimental result showed that the method used in this paper can improve the recognition speed and precision.
出处
《上海公路》
2009年第4期75-79,共5页
Shanghai Highways
关键词
车牌识别系统
车牌定位
字符分割
字符识别
License plate recognition system
License plate location
Character segmentation
Character recognition
