| 摘要: |
| 手写汉字切分是根据输入笔迹的空间位置关系进行汉字部件的合并切分,形成完整的汉字笔划以便进行识别处理.综合利用了汉字部件的结构位置关系和笔划的空间位置关系,根据笔划的最小生成树(minimal spanningtree,简称MST)对联机连续手写输入汉字进行切分,取得了较好的切分结果.切分的准确率超过91.6%. |
| 关键词: 字符切分 手写汉字 部件结构 联机识别 |
| DOI： |
| 分类号: |
| 基金项目:Supported bythe National Natural Science Foundation of China under Grant Nos.60033020,60373030(国家自然科学基金);the National Grand Fundamental Research 973 Program of China under Grant No.2002CB312103(国家重点基础研究发展规划(973));the Foundation of Beijing Jiaotong University under Grant No.2004SM013(北京交通大学基金) |
|
| Using MST in Handwritten Chinese Characters Segmentation |
|
HAN Yong,XU De,DAI Guo-Zhong
|
| Abstract: |
| Handwritten Chinese characters segmentation is to process strokes based on its spatial relations to form character elements for recognition. This paper introduces a method to segment Chinese characters according to the topological relations of Chinese component and minimal span tree of strokes. The experiment shows that this new method can achieve good performance. The accuracy of segmentation is over 91.6%. |
| Key words: character segmentation handwritten Chinese character component structure online recognition |
