基于过程神经元网络的汉字笔段提取算法研究  

Stroke extraction research on Chinese character based on procedure neuron networks

作　　者：王建平[1] 徐奇[1] 

机构地区：[1]合肥工业大学电气与自动化工程学院,合肥230009

出　　处：《计算机应用研究》2010年第5期1965-1967,共3页Application Research of Computers

摘　　要：提出一种利用过程神经元网络,对脱机手写体汉字二维图像的笔段提取方法。定义了脱机手写体汉字笔段的提取方法,给出了用于脱机手写体汉字笔段提取的过程神经网络的模型和学习算法,并对算法进行了仿真实验。该方法与其他汉字笔段提取方法相比,具有速度快、可学习、鲁棒性好的特点。经实验证明,该方法是行之有效的。This paper gave a novel method of stroke extraction on Chinese written character based on procedure neuron networks,definded the method of stroke extraction, and gave the procedure neuron networks model and the training method for the model.Accomplished simulation experiment.Compared to the other methods of stroke extraction,this method is more fast,robust and able to study.The simulation experiment result shows that the proposed method is effective and robust.

关 键 词：汉字识别 笔段提取 特征点提取 过程神经元网络 

分 类 号：TP391.43[自动化与计算机技术—计算机应用技术]