基于相似度的手写汉字笔划鉴别方法实验研究  

Experiment Research on the for the Stroke of Handwritten Chinese Characters Identification Method Based on Similarity

作　　者：白晓东[1,2] 姜杰[3] 邓红静 李艺[3] 

机构地区：[1]南京师范大学计算机科学与技术学院,江苏南京210023 [2]江苏省信息安全保密技术工程研究中心,江苏南京210097 [3]南京师范大学教育科学学院,江苏南京210023

出　　处：《实验室研究与探索》2015年第12期132-136,167,共6页Research and Exploration In Laboratory

基　　金：江苏省高校哲学社会科学基金项目(2011SJB8800287);江苏省教育科学"十二五"规划项目(D/2011/01/055)

摘　　要：针对手机和平板电脑上手写汉字主流的xml存储格式,提出了一种对识别用户手写汉字笔划的算法。算法首先从三种结构特征对手写汉字进行编码,然后计算用户字笔划、模板字笔划之间不同编码集合的相似度,最后组合多种相似度识别手写汉字的笔划,并通过三种应用实验验证方法的有效性。笔顺的判别一直是手写汉字识别的难点,文章中提出的方法笔顺的识别率高达95%以上。此算法在用户字的多笔、少笔判别、笔顺判别、整字的正确性以及美观性判别等方面都有着广泛的应用。For the handwritten Chinese mainstream storage format of mobile phones and tablet PC,this paper proposes a handwritten Chinese character strokes recognition algorithms,Firstly the three structural features of handwritten Chinese characters are encoded,and then calculate the word stroke among users,templates word strokes similarity different set of encoding,and finally a combination of a variety of similarity recognize handwritten Chinese character strokes and three applications through experimental verification of the validity of the method. Stroke discrimination has been the difficulty of handwritten Chinese character recognition,and the recognition rate of the proposed method stroke up to 95%. The algorithm in user word multi pen and pen less discrimination,stroke identification,the whole character of the correctness and aesthetic judgment,etc. have a wide range of applications.

关 键 词：改进型Hausdorff距离 方位编码 VORONOI图 拓扑相似度 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]