摘要
弹性网格和方向线素特征已广泛应用于许多手写汉字识别系统中,并认为是目前较成熟和有效的手写体汉字特征。本文将传统弹性网格特征和方向线素特征相结合然后运用BP神经网络对其进行识别。实验证明,本文特征提取方法在识别率上优于传统的弹性网格方法。
The elastic meshes feature and the directional line element feature of handwrtitten Chinese character have been widely used in many Chinese handwriting recognition systems, and are considered as mature and effective features of Chinese handwriting character. In this paper, the elastic meshes feature and the directional line element feature are combined so as to be recognized by BP neural network. The experimental results show that the proposed feature extraction method is superior to the traditional elastic grid method in recognition rate.
出处
《辽宁省交通高等专科学校学报》
2008年第1期38-39,共2页
Journal of Liaoning Provincial College of Communications
关键词
脱机手写汉字识别
弹性网格
方向线素
特征提取
handwrtitten Chinese character recongnition
elastic meshes
feature extraction
