| 基于支持向量机和核主成分分析的车牌字符识别 |
| |
| 引用本文： | 潘石柱,殳伟群,王令群.基于支持向量机和核主成分分析的车牌字符识别[J].电子科技,2006(10):59-61,67. |
| |
| 作者姓名： | 潘石柱 殳伟群 王令群 |
| |
| 作者单位： | 同济大学,控制理论与控制工程学院,上海,200092 |
| |
| 摘 要： | 给出了一种结合核主成分分析(KPCA)和支持向量机(SVM)进行车牌字符识别的新方法.该算法通过KPCA进行字符的特征提取,并利用SVM分类器完成字符的识别.实验证明,KPCA在高维空间具有较强的特征选择能力,SVM的识别率也明显高于BP神经网络.
|
| 关 键 词： | 支持向量机(SVM) 核主成分分析(KPCA)车牌字符识别 |
| 收稿时间： | 2006-01-11 |
| 修稿时间： | 2006-01-11 |
License Plate Character Recognition Based on SVM and KPCA |
| |
| Pan Shizhu,Shu Weiqun,Wang Lingqun.License Plate Character Recognition Based on SVM and KPCA[J].Electronic Science and Technology,2006(10):59-61,67. |
| |
| Authors: | Pan Shizhu Shu Weiqun Wang Lingqun |
| |
| Affiliation: | Department of Control Theory and Control Engineering, Tongji Universary, Shanghai 200092, China |
| |
| Abstract: | This paper presents a new method of combining KPCA with SVM for recognizing license plate characters. First, the kernel principal component analysis is used to extract the features of a character, and then the SVM is selected to recognize the character. Experiments show that the KPCA has a strong ability to extract features and that the SVM has better performance than BPNN. |
| |
| Keywords: | support vector machine(SVM) kernel principal component analysis (KPCA) license plate character recognition |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
