摘要
车辆牌照识别(LPR)系统是一个专用的计算机视觉系统,LPR系统的广泛应用将有助于加快我国交通管理自动化的进程。本文对车牌识别系统中的图像预处理、车牌定位、字符分割和字符识别等环节涉及到的技术、算法以及系统整体设计作了全面的论述,并与已有方案进行了比较,对部分关键算法进行了设计和改进。用采集到的40多幅汽车图片作为实验样本数据,用纯软件的方法实现了车牌字符的自动识别。
As a special computer vision system, the License Plate Recognition System （LPR）can capture a vehicle automatically and identify the plate numbers in the image. Contributing a lot to the automation of the transportation manag ment. In this paper, some methods and algorithms are introduced in such stages as preprocessing of images, license plate location, character segmentation and character recogenition. At the same time, compare the methods with the existing. Moreover, designing and improving parts of critical algorithm. Testing 40 representative vehicle license plates, I can achieve the good accuracy.
出处
《计算机科学》
CSCD
北大核心
2006年第12期207-209,213,共4页
Computer Science
基金
江苏省教育厅自然科学基金资助项目(NO.02KJB520012)。
关键词
车牌定位
竖向纹理
字符分割
字符识别
License plate location, Vertical texture, Character segmentation, Character recognition
