基于ANN和HMM的联机手写体汉字识别系统

ANN and HMM Based Online Handwritten Chinese Character Recognition System

为了解决联机手写体汉字笔划顺序、笔划数目及笔划形状变化问题,提出了一种新的联机手写体汉字识别方法:人工神经网络(ANN)和隐马尔可夫模型(HMM)相结合的汉字识别方法,首先通过BP神经网络进行笔划识别,再通过笔划类型和笔划间位置关系的隐马尔可夫模型进行整字识别。实验证明,该联机手写体汉字识别系统具有较高地识别准确率。

In order to cope with stroke order variations , stroke number variations and large shape variations, a new online handwritten Chinese character recognition method is presented.It integrates artifitial neural network with hiddeff markov model , accomplishs stroke recognition by BP neural network and Chinese character recognition by hidden markov model of stroke type and stroke position relation.Experiment indicates that this method has better recognition accuracy.