手写汉字识别的非线性动态部件模板  

Nonlinear Active Radical Modeling for Handwritten Chinese Character Recognition

作　　者：石大明[1] 刘家锋[2] 唐降龙[2] 舒文豪[2] 

机构地区：[1]南洋理工大学计算机工程学院,新加坡639798 [2]哈尔滨工业大学计算机科学与工程系,哈尔滨150001

出　　处：《自动化学报》2004年第3期390-399,共10页Acta Automatica Sinica

摘　　要：对以前提出的非线性动态手写模板加以改进并用于手写汉字的部件识别.在训练阶段,核-主元分析用来捕捉非线性的手写变化.于是,只需改变少量的形状参数就可获得动态变形的模板.在识别阶段,遗传算法取代了原始的动态通道算法去寻找最优的形状参数.我们对覆盖2154个汉字类别的200个部件进行了实验,对不同人书写的430,800个测试样本的部件识别率达97.4%.与现有的代表性部件方法比较也显示本文的方法效果最好.This paper improves the authors previously proposed nonlinear active handwriting models and applies them into radical extraction for handwritten Chinese character recognition. In the training phase, kernel principal component analysis is used to capture nonlinear handwriting variations. Then deformable models can be generated by varying a small number of shape parameters. In the recognition phase, genetic algorithms, rather than dynamic tunneling algorithm in the original version, are employed to search for the optimal shape parameters. Experiments are conducted on 200 radicals covering 2154 character categories. The correct matching rate is 97.4% on 430, 800 loosely-constrained characters. Comparison with existing representative radical approaches shows that our method achieves superior performance.

关 键 词：手写汉字识别 动态手写模板 核-主元分析 遗传算法 

分 类 号：TP391.43[自动化与计算机技术—计算机应用技术]