Computer Engineering and Applications ›› 2006, Vol. 42 ›› Issue (6): 10-.

• 博士论坛 • Previous Articles     Next Articles

A Method for Effectively Improving Offline Handwritten Character Recognition Based on Semantic Analysis


  1. 北京科技大学
  • Received:2005-11-09 Revised:1900-01-01 Online:2006-02-21 Published:2006-02-21



  1. 北京科技大学
  • 通讯作者: 李莉 liliustb liliustb

Abstract: In this paper, we discussed a new method to effectively improve offline handwritten character recognition through semantic analysis. Seeing from the process of recognition, this method was at post-processing stage based on context. We introduced SE(Semantic Element), SER(Semantic Element Representation), SER-tree, SER-Set, SER-treeSet and discussed this new method of pruning on the SER-treeSet in details.

Key words: Semantic Analysis, Offline Handwritten Character Recognition, Semantic Language

摘要: 本文讨论一种通过自然语言语义层次的理解来协助提高脱机手写体识别率的方法。从识别的过程来看,这种方法是一种基于上下文关系的识别“后处理”方法。在文中,我们介绍了语义单元、语义单元表示、语义单元表示树、语义单元表示集、语义单元表示树集,并且具体讨论了通过语义单元表示树集的剪枝来提高识别正确率的方法。

关键词: 语义分析, 脱机手写体识别, 语义语言