基于组件合并的手写体汉字串分割

Segmentation of Handwritten Chinese Character String Based on Merging of Elements

人们对孤立的手写体汉字字符的离线识别做了大量的研究工作 ,而走向实用化的进展并不快 .除了单字识别率不理想以外 ,从文本中正确分割出单个汉字字符也是一个主要难题 ,因为字符的识别离不开正确分割 .利用汉字的基本结构特征 ,根据两个组件之间的上下、左右和包围关系 ,对组件进行合并形成完整的汉字图像 .对整个汉字字符串中组件的宽度和相邻组件的间距进行分析 ,有助于左右关系组件的合并 .实验结果表明 ,该方法对手写体汉字字符串具有理想的分割效果 .

A number of papers concerning the off line recognition of handwritten Chinese characters have been published in the recent years, and almost all of them focus on the recognition of isolated characters. However, off line recognition of handwritten Chinese characters is not satisfactory. One reason is that the recognition rate is low, the other is that the segmentation of handwritten Chinese characters is a difficult problem because recognition of characters relies on correct segmentation of characters. In this paper, according to structural features of Chinese characters, elements are merged based on their topological relations, viz., upper bottom, left right and inside outside. The width of elements and the spacing between neighboring elements in the whole handwritten Chinese character string are analyzed to guide the merging of left right elements. Experimental results show that the method has satisfactory performance for segmenting handwritten Chinese character string.