基于粗糙集理论和模糊SVM的车牌识别技术研究
    点此下载全文
引用本文:贺光,李永忠.基于粗糙集理论和模糊SVM的车牌识别技术研究[J].计算技术与自动化,2010,(4):86-89
摘要点击次数: 1655
全文下载次数: 244
作者单位
贺光,李永忠 (江苏科技大学 计算机科学与工程学院江苏 镇江212003) 
中文摘要:针对传统的SVM多分类存在不可分区域,提出一种粗糙FSVM识别算法。该算法根据粗糙集理论对训练样本进行建立决策表、离散决策表、约简决策表、提取分类规则等推理过程设计。不但有效改善训练时间,而且解决了传统的SVM多分类存在不可分区域的问题。实验表明,将该识别算法应用于车牌字符识别,取得在相同的条件下比支持向量机方法更为理想的识别效果。
中文关键词:粗糙集  模糊SVM  车牌识别
 
The Research of License Plate Recognition Based on Rough Set and Fuzzy SVM
Abstract:Aiming at the problem of unclassifiable regions in multi-class support vector machines, this paper presents a recognition algorithm based on rough FSVM. The method was designed according to the reasoning process of the rough set theory, including building up, dispersing and reducing the decision table of training samples. Not only improve the training time, but also solve the problem of unclassifiable regions in multi-class support vector machines. Simulation results indicate that this recognition algorithm is applied to license plate recognition, made even better result than the SVM recognition under the same conditions.
keywords:rough set  fuzzy SVM  license plate recognition
查看全文   查看/发表评论   下载pdf阅读器