首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于HSV颜色空间和SVM的车牌提取算法
引用本文:黄社阳,刘智勇,阮太元.基于HSV颜色空间和SVM的车牌提取算法[J].计算机系统应用,2014,23(8):150-153.
作者姓名:黄社阳  刘智勇  阮太元
作者单位:五邑大学 信息工程学院, 江门 529020;五邑大学 信息工程学院, 江门 529020;江门职业技术学院, 江门 529020;江门职业技术学院, 江门 529020
摘    要:为了克服HSV算法在车牌提取中存在与车牌颜色相近的类似车牌区域的干扰,提出一种基于HSV颜色空间和 SVM 相结合的车牌提取算法,该方法能够较好的对多种车牌实现精确定位与提取。首先根据字符的边界特征和HSV颜色空间分别对蓝色和黄色车牌进行粗定位,获得几个车牌候选区;然后使用训练好的SVM分类器进行字符与非字符分类;最后根据车牌特征实现定位与提取。实验表明,该方法取得了良好的效果。

关 键 词:HSV颜色空间  连通区域  车牌候选区  车牌提取  SVM  字符分类  多种车牌
修稿时间:2/7/2014 12:00:00 AM

Algorithm of License Extraction Based on HSV Clor Space and SVM
HUANG She-Yang,LIU Zhi-Yong and RUAN Tai-Yuan.Algorithm of License Extraction Based on HSV Clor Space and SVM[J].Computer Systems& Applications,2014,23(8):150-153.
Authors:HUANG She-Yang  LIU Zhi-Yong and RUAN Tai-Yuan
Institution:School of Information Engineering, Wuyi University, Jiangmen 529020, China;School of Information Engineering, Wuyi University, Jiangmen 529020, China;Jiangmen Polytechnic, Jiangmen 529020, China;Jiangmen Polytechnic, Jiangmen 529020, China
Abstract:In order to overcome the drawbacks from the disturbance such as the color area similar to the vehicle plate, a new method of license plate extraction based on HSV and SVM is presented in this paper, which can locate and extract some kinds of plate perfectly. Firstly it caculates the coarse positioning of the blue and yellow plates based on the edge characteristics and HSV color space to get Several candidate regions. Then a pre-trained SVM is used to classify character and non character. Finally the plate was precisely located and extracted through the characteristics of the plate. Experimental results show that the proposed method has a good performance.
Keywords:web information extraction  knowledge presentation  data intensive web pages  ontology-based keyword library
本文献已被 维普 等数据库收录!
点击此处可从《计算机系统应用》浏览原始摘要信息
点击此处可从《计算机系统应用》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号