脱机手写体汉字识别研究综述

脱机手写体汉字识别是汉字识别领域中最难的课题。该文对目前脱机手写体汉字识别在预处理、特征提取、分类识别及后处理四个阶段主要采用的方法做了简要介绍,阐述了各种方法的优缺点,并提出了一种将支持向量机有效地用于解决多分类问题的策略。最后根据目前的研究状况,指出今后研究中需要注意的问题和研究的发展方向。

A Survey of Off-line Handwritten Chinese Character Recognition

Off-line handwritten Chinese character recognition is the most difficult problem in character recognition.This paper surveys the main techniques in four phases:pre -processing,feature extracting,classification and recognition,and post-processing.Also,it analyzes the strongpoint and shortcoming of every method and proposes a new idea,by which SVM can be effectively used to solve the multi-class classification problem.In the end,some problems that should be pay more attention and some useful research orientations are proposed.