Computer Engineering and Applications ›› 2007, Vol. 43 ›› Issue (30): 190-192.

• 工程与应用 • Previous Articles     Next Articles

Normalized background directional feature for off-line handwritten Chinese character recognition

WANG Xian-mei,WANG Hong,WANG Fen-hua   

  1. Department of Electronic Information Engineering,University of Science and Technology Beijing,Beijing 100083,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-10-21 Published:2007-10-21
  • Contact: WANG Xian-mei

基于归一化背景方向特征的脱机手写汉字识别

王先梅,王 宏,王粉花   

  1. 北京科技大学 电子信息工程系,北京 100083
  • 通讯作者: 王先梅

Abstract: This paper presents an improved background directional feature extraction method.Compares to the traditional one,the new method extends the scanning directions from 4 to 8 which can detail the concavity configurations among the foreground pixels and the background pixels.Moreover,in order to reduce the influence of the stroke thickness,a normalization process is also given.Experiments on off-line handwritten Chinese amount in words show that the proposed method is more superior to the older one.

摘要: 对4方向背景方向特征进行了改进,提出了8方向背景特征描述方法。与4方向背景方向特征描述方法相比,改进后的特征描述方法可以从0°、45°、90°、135°、180°、225°、270°、315°共8个方向来对汉字图像进行考察,从而进一步提高描述的精度。此外,为了消除笔划粗细的影响,还对背景方向特征进行了归一化处理。实验结果表明改进后的归一化8方向背景方向特征具有更高的识别精度。