摘要
运用松弛匹配方法的基本思想，给出了用汉字轮廓点的差分作为轮廓跟踪及折断点选择的算法，提高了轮廓折线化速度；分类按汉字四周的外轮廓线分三级进行匹配，提出了动态有序弹性匹配方法，使全域松弛匹配得以在局部区域进行，从而有效地提高了匹配速度；在进行第一级初分类时，采用多个模块，有效地提高了按偏旁位置分布进行分类的正确率；最后利用内轮廓折线与字典逐字匹配，达到对离线手写印刷体汉字识别的目的．
Based on the relaxation matching method, this paper gives a algorithm of tracing the contour and selecting the turning points by using the distances between points on the contour of Chinese characters, therefore, the speed of extracting the turning strokes is greatly improved. According to the out-contour turning strokes of Chinese characters, the matching is classified three levels, and then the relaxation matching in full domain is changed into partial domain relaxation matching, which is called dynamicsequential-flexible matching approach. As a result, the matching speed is raised efficiently. In the first level classification, we adopt several models, and increase efficiently the correction rate of classifying by the positions of radicals. At last, the off-line hand-printed Chinese characters are recognized by using the intercontour turning strokes.
出处
《襄樊学院学报》
2000年第5期59-62,共4页
Journal of Xiangfan University
关键词
手写印刷体汉字识别
松弛匹配法
动态有序弹性匹配法
匹配速度
汉字轮廓点
轮廓折线化
折断点选择
Hand-printed Chinese characters recognition, Direction combinational similarity method
Relaxation matching method, Dynamic-sequential-flexible matching approach
