基于书写规则的书法字笔画及笔顺提取

Calligraphy′s strokes and orders extraction based on the rules of writing

提出了一种针对篆书和隶书等多类别书法字图像笔画及笔顺信息的提取算法。算法通过使用书法字骨架图与轮廓图相结合的方式,使用针对交叉处轮廓点角度聚类及该点与交叉中心欧氏距离相结合的聚类准则,完成交叉处笔画的信息补全、处理,并根据书写规则提取书法字的笔顺信息。最后,针对楷体、隶书、篆书三类书法字图像做笔画以及笔顺信息的提取,实验结果表明本文所提出的方法对多类别书法字图像笔画提取取得了较好的效果。

This paper proposes a novel stroke and the orders extraction algorithm adopted to multiple classes of the Chinese calligraphy. In order to process the region of fork strokes, the paper proposes a new cluster method which combine the skeleton image and the contour image. The rules of clustering is based on the angle of the contour points and the Euclid distance of the point to the fork region′s center point. And then completing the stroke′s missing information in the fork region, extracting the orders of the stroke based on the rules of writing. Finally, the strokes of three types Chinese calligraphy are extracted with this algorithm.Experimental results show that the proposed algorithm achieves a better effect.