手写体笔迹单笔划提取算法  

Stroke Extraction Algorithm for Handwriting Chinese Characters

作　　者：赵建平[1] 车丹[1] 

机构地区：[1]长春理工大学计算机科学技术学院,长春130022

出　　处：《长春理工大学学报（自然科学版）》2005年第4期66-70,共5页Journal of Changchun University of Science and Technology(Natural Science Edition)

摘　　要：汉字笔划提取在笔迹鉴别研究中具有重要的意义,一旦汉字笔划提取在正确率和速度上取得突破,汉字笔迹鉴别乃至汉字的识别都将产生重大的突破。本文借助图像压缩技术中的游程长度编码技术,以计算像素点的方向游程长度为基础,通过计算待拆分汉字笔划厚度的方法来定义像素点方向游程长度的阈值。利用游程长度的阈值对像素点的方向游程长度进行分类,处理笔划交叉问题。该算法可对书写工整的汉字进行有效笔划提取。Handwritten Chinese characters stroke extraction has the important research meaning in handwriting distinguishing, once the handwritten Chinese characters stroke extraction obtains the breakthrough on the correctness and speeds, the Chinese characters handwriting distinguishing and recognition will produce important breakthrough. This paper asks for help the pixel direction distance length in the picture compression technique, with the calculation that pixel direction distance length as foundation, defines the threshold value of the pixel direction distance length according to calculate the Chinese characters brush stroke thickness, and classifies the pixel direction distance length by the threshold value. This algorithm can extract handwritten Chinese characters stroke for formal Chinese characters.

关 键 词：笔迹辨伪 笔迹特征 笔划提取 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]