| 特征融合用于手写体汉字识别研究 |
| |
| 引用本文： | 居琰,汪同庆,彭建,刘建胜,袁祥辉.特征融合用于手写体汉字识别研究[J].电子科技大学学报(社会科学版),2002(3). |
| |
| 作者姓名： | 居琰 汪同庆 彭建 刘建胜 袁祥辉 |
| |
| 作者单位： | 重庆大学光电工程学院 重庆400044
(居琰，汪同庆，彭建，刘建胜)，重庆大学光电工程学院 重庆400044(袁祥辉) |
| |
| 摘 要： | 分析了手写汉字特征的提取方法,提取具有一定互补性的轮廓方向特征和方向距离分布特征,并进行K-L变换降维处理,用多特征合成一个区分能力更强的新特征。讨论了RBF网络分类器特性,结合特征融合方法和模块RBF神经网络结构有机地构建一个小类别手写体汉字识别系统。实验表明,该系统可行和有效。
|
| 关 键 词： | 特征融合 K-L变换 模块RBF网络 手写体汉字识别 |
Research on Handwritten Chinese Character Recognition Using Feature Fusion and Modular RBF Classifier |
| |
| Ju Yan,Wang Tongqing,Peng Jian,Wang Guixin,Liu Jiansheng,Yuan Xianghui.Research on Handwritten Chinese Character Recognition Using Feature Fusion and Modular RBF Classifier[J].Journal of University of Electronic Science and Technology of China(Social Sciences Edition),2002(3). |
| |
| Authors: | Ju Yan Wang Tongqing Peng Jian Wang Guixin Liu Jiansheng Yuan Xianghui |
| |
| Abstract: | This paper analysis the feature extraction method of handwritten Chinese character. The contour direction feature(CDF)and directional distance distributions feature(DDDF) are extracted from Chinese character image as a pair of feature vectors having good complementarity. After dimensions reduction of original feature using Karhunen-Loeve transform, these two feature vectors are combined to produce a new feature vector has high discriminating powers. Basing on the characteristic of RBFNN classifier, a novel architecture which integrates feature fusion and modular RBF neural networks classifier approaches into a small set handwritten Chinese character recognition system is presented. Experiments show that the system has achieved impressive performance and the results are informing. |
| |
| Keywords: | feature fusion karhunen-loeve transform modular radial basis function neural network handwritten chinese character recognition |
| 本文献已被 CNKI 等数据库收录！ |
