| 多分类器组合研究 |
| |
| 引用本文： | 王正群,孙兴华,杨静宇.多分类器组合研究[J].计算机工程与应用,2002,38(20):84-85,102. |
| |
| 作者姓名： | 王正群 孙兴华 杨静宇 |
| |
| 作者单位： | 南京理工大学计算机科学系,南京,210094 |
| |
| 摘 要： | 文章提出了一种多分类器的组合方法,它利用了参与组合的分类器提供的度量层次上的两类信息:对训练样本的决策信息;对待识样本的决策信息。首先对这两类信息进行集成,进而给出了组合分类器的判定规则。用该方法对手写体汉字作分类识别,实验结果显示,较之其它几种方法,它有更高的正确识别率。
|
| 关 键 词： | 分类器 多分类器组合 相似度 先验知识矩阵 |
| 文章编号： | 1002-8331-(2002)20-0084-02 |
Study on Multiple Classifiers Combination |
| |
| Wang Zhengqun Sun Xinghua Yang Jingyu.Study on Multiple Classifiers Combination[J].Computer Engineering and Applications,2002,38(20):84-85,102. |
| |
| Authors: | Wang Zhengqun Sun Xinghua Yang Jingyu |
| |
| Abstract: | This paper presents a combination method of multiple classifiers,which applies two kinds of decision information provided by the applied classifiers,one is for training samples,and the other is for unknown samples.Those two kinds of information are integrated to produce the decision rule of combined classifier.This method is applied to classify and recognize the handwriting Chinese characters,and the experimental results show that this method is superior to the other method in terms of the recognition rate. |
| |
| Keywords: | Classifier Multiple classifiers combination Similarity Prior knowledge matrix |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
