摘要： 提出了一种从手写体汉字骨骼图像上提取分叉点的改进算法。采用新的骨骼图像分析技术提取新的候选特征点集，并且证明了骨骼上所有的分叉点都可以用该特征点集中的元素表示。实验表明新特征点集中元素的数量较以前大大减少。

关键词: 手写体汉字；骨骼；特征点；分叉点；完整性。

Abstract: An improvement to the algorithm for extracting fork points from skeleton images of handwritten Chinese characters is proposed. A new trick is taken to extract a set of candidate feature points from skeleton image, and it is proved that all fork points on the skeleton can be represented by the elements of the new candidate set. Experiment shows that the number of elements in the set is markedly reduced

Key words: Handwritten Chinese character; Skeleton; Feature point; Fork point; Completeness