基于霍夫变换和弹性网格的手写汉字识别方法

特征提取是手写体汉字识别的关键环节.弹性网格特征是一种较好的手写体汉字特征,但是无法体现汉字的整体结构信息,为此提出了一种采用复合特征进行手写体汉字识别的方法.该方法采用霍夫变换提取汉字图像的全局特征,并把这些全局特征与用弹性网格方法提取出的局部特征联合起来,这样得到的混合特征完整地反映了汉字全局特征和局部特征.最后通过实验证明,在进行大类别手写体汉字识别时,在特征值维数相同的情况下,采用这种复合特征的识别率明显高于单一的弹性网格特征,因此该方法是行之有效的.

Handwritten Chinese Character Recognition Based on Hough Transformation and Elastic Mesh

Feature extraction is the key part of handwrittten chinese character recognition.Elastic Mesh is a major method to get character feature,but can not indicate the holistic structure of character.In this paper,a novel method of chinese handwritten character recognition using complex feature is proposed.The complex feature is composed of the global feature extracted by Hough transformation and the local feature extracted by elastic mesh technique,so the com- plex feature presents both character's global featur...