车牌定位中缩小搜索范围的方法研究与实现  

Research and Realization of Shrinking Searching-area Method in Licence Plate Location

作　　者：陈箫枫[1] 潘保昌[1] 郑胜林[1] 赵全友[1] 梁坚[1] 

机构地区：[1]广东工业大学信息工程学院,广东广州510006

出　　处：《电视技术》2008年第3期88-90,共3页Video Engineering

基　　金：国家自然科学基金项目(60572078)

摘　　要：提出了三点平均平滑曲线的方法。用灰度直方图的缩小曲线来辨别白天和夜晚的车牌图像,用纵向差分、二值化、纵向投影、三点平均平滑、曲线放大等方法突出车身的横直线,查找车身左右边界,排除地面背景和缩小车牌搜索范围,由此设计了一个应用于高速公路超速监控的车牌识别系统。The method of three-point average smooth carve is proposed in this paper. The shrinked curve of grey histogram is used to distinguish the licence images at day and night. And with the methods of vertical difference, binaryzation, vertical projection, three-point average and curve magnification ,the horizontal lines of vehicle body is extruded ,the left and right borders of the vehicle body are searched , the floor background is excluded,and searching area of the licence is reduced. And thus, the licence recognition system is designed and applied to the overspeed supervision in freeway.

关 键 词：车牌识别 车牌定位 三点平均平滑曲线 范围缩小 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]