| 一种基于新特征的车牌检测方法 |
| |
| 引用本文： | 江林升,朱学芳.一种基于新特征的车牌检测方法[J].计算机工程与应用,2011,47(20):188-190. |
| |
| 作者姓名： | 江林升 朱学芳 |
| |
| 作者单位： | 1. 南京森林警察学院信息系,南京,210046
2. 南京大学信息管理系,南京,210093 |
| |
| 摘 要： | 车牌检测是车牌识别的关键所在,两种新的区域统计学特征能迅速排除大量的非车牌区域,在此基础上,采用增加了辅助判决的级联分类器来改进AdaBoost算法。实验表明,该算法与基于颜色特征分类器和传统的级联AdaBoost分类器相比,具有较快的检测速度、较高的检测率和较低的误检率。
|
| 关 键 词： | 特征 级联分类器 AdaBoost |
| 修稿时间： | |
Car plate detection based on new features |
| |
| JIANG Linsheng,ZHU Xuefang.Car plate detection based on new features[J].Computer Engineering and Applications,2011,47(20):188-190. |
| |
| Authors: | JIANG Linsheng ZHU Xuefang |
| |
| Affiliation: | 1.Department of Information,Nanjing Forest Police College,Nanjing 210046,China 2.Department of Information Management,Nanjing University,Nanjing 210093,China |
| |
| Abstract: | License plate detection is the key to the recognition of automatic license plates.The two new regional statistics can quickly rule out a large number of non-regional plate vehicles, based on which, a noval Adaboost with auxiliary detection is proposed in the paper.Tests show that compared with color-based classifier and traditional cascaded AdaBoost classifier, the new algorithm takes the advantages of a faster detection speed,a higher detection rate as well as fewer false detections. |
| |
| Keywords: | feature cascaded classifier AdaBoost |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《计算机工程与应用》浏览原始摘要信息 |
|
点击此处可从《计算机工程与应用》下载全文 |
|
