一种基于SVG的在线连续手写汉字多步分割方法  

Multi-step segmentation method of online handwritten Chinese characters based on SVG

作　　者：李昕岩 陈联[1] 

机构地区：[1]中国科学院成都计算机应用研究所,成都610041 [2]成都远策数码科技有限公司,成都610041

出　　处：《计算机应用研究》2017年第11期3364-3366,3372,共4页Application Research of Computers

基　　金：国家科技部科技支撑计划资助项目(2013BAH72B01)

摘　　要：为了对基于可伸缩矢量图SVG的在线连续手写汉字进行有效的分割,提出一种基于图论的在线连续手写汉字多步分割方法。该方法以SVG格式存储的手写汉字为基本研究对象,根据汉字笔画间的坐标位置关系对手写笔画序列构建无向图模型,并利用图的广度优先搜索将原笔画序列分割为互不连通的笔画部件,使偏旁部首分离较远、非粘连汉字得到正确分割;然后利用改进的Tarjan算法对部件中的粘连字符进行分割;最后基于笔画部件间距,利用二分类迭代算法对间距进行分类,找出全局最佳分割位置,对过分割的部件进行重组合并。实验结果表明,该方法对于在线手写汉字的分割是有效可行的。In order to segment the online continuous handwritten Chinese characters based on scalable vector graph （SVG） effectively, this paper presented a method of online continuous handwritten Chinese character multi-step segmentation based on graph theory. This method used the handwritten Chinese characters stored in SVG format as the basic research objects. Firstly, this method constructed an undirected graph model of the sequence of handwritten strokes based on the coordinate position relations among Chinese characters. In order to let that radical separation of radical far, non-adhesive Chinese characters get right segmentation, it used the breadth-first search of the graph to divide the original stroke sequence into non-connected stroke parts. Secondly it used the improved Tarjan algorithm to segment this sticky characters in the parts. Finally, based on the spacing between stroke parts, it used the two-class iterative algorithm to classify the spacies, and found the best split positions to recombine and merge those over-segmented components. Experimental results show that this method is effective for the segmentation Of online handwritten Chinese characters.

关 键 词：在线手写汉字分割 无向图 广度优先搜索 Tarjan算法 二分类迭代算法 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]