首页 | 本学科首页   官方微博 | 高级检索  
     

基于笔画平面和模糊隶属度的手写体汉字识别
引用本文:王正群,侯艳平,刘风,马波. 基于笔画平面和模糊隶属度的手写体汉字识别[J]. 扬州大学学报(自然科学版), 2008, 11(4)
作者姓名:王正群  侯艳平  刘风  马波
作者单位:扬州大学,信息工程学院,江苏,扬州,225009
基金项目:国家自然科学基金,江苏省高校自然科学基金 
摘    要:基于笔画平面抽取和动态网格划分,提出一种笔画平面与模糊隶属度相结合的手写体汉字特征提取方法,该方法克服了汉字特征抽取过程中因笔画粗细不均、笔画长短变形等引起的特征抽取不稳定问题.其基本思想是:用动态网格将汉字图像分别划分为横、竖、撇、捺4个笔画平面,并赋予每个网格中的点模糊隶属度,针对每个网格求加权累积直方图,最终获得汉字特征.基于南京理工大学NUST603HW手写汉字库的实验结果表明,该汉字特征抽取方法是有效的.

关 键 词:笔画平面  模糊隶属度  特征抽取

Handwritten Chinese character recognition based on stroke plane and fuzzy membership
WANG Zheng-qun,HOU Yan-ping,LIU Feng,MA Bo. Handwritten Chinese character recognition based on stroke plane and fuzzy membership[J]. Journal of Yangzhou University(Natural Science Edition), 2008, 11(4)
Authors:WANG Zheng-qun  HOU Yan-ping  LIU Feng  MA Bo
Affiliation:WANG Zheng-qun,HOU Yan-ping,LIU Feng,MA Bo(Sch of Inf Engin,Yangzhou Univ,Yangzhou 225009,China)
Abstract:Based on stroke plane extraction and dynamic meshing partition,a new method for Chinese character feature extraction is proposed.This method combines stroke plane with fuzzy membership to improve the unstable problem,which is caused by the distortion of stroke.The basic idea is to divide the Chinese character image into four different stroke planes by dynamic meshing,allocate the fuzzy membership for each meshing,then compute the weighted accumulation histogram aimed for obtaining the feature for each meshi...
Keywords:stroke plane  fuzzy membership  feature extraction  
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号