计算机应用 ›› 2011, Vol. 31 ›› Issue (01): 50-52.

• 第八届中国计算机图形学大会优秀论文 • 上一篇    下一篇

改进的基于信息熵的手写图文判别方法

邢佑路1,冯桂焕2   

  1. 1. 江苏省南京市汉口路22号南京大学南园20舍
    2. 南京大学
  • 收稿日期:2010-07-12 修回日期:2010-08-27 发布日期:2011-01-12 出版日期:2011-01-01
  • 通讯作者: 冯桂焕

Separation method for handwritten shape and text based on improved stroke entropy

  • Received:2010-07-12 Revised:2010-08-27 Online:2011-01-12 Published:2011-01-01

摘要: 由于图形和文字的笔画构成复杂程度存在差异,通过计算组成图形和文字笔画的信息熵值度量该差异性,进行图文类型判别;自适应重采样解决了固定间距重采样机制可能导致的信息熵值随文档笔画尺寸变化而出现较大变化的问题,使方法能够适应不同用户的书写习惯;基于对称性检验的后处理可解决笔画构成等价导致信息熵值十分接近的图形和文字的判别。实验结果验证了所提方法的有效性。

关键词: 图文类型判别, 笔画信息熵, 自适应重采样, 对称性检验

Abstract: As the stroke constitutional complexity of shapes and texts is different, this paper proposed a shape and text separation method based on the calculation of the entropy of the strokes. Because the entropy of a document may vary with stroke size, adaptive resampling was introduced to handle different writing stroke sizes. In addition, the paper employed a symmetrical judgement mechanism to handle the separation of texts and shapes with equivalent stroke constitutions. The experimental results demonstrate the effectiveness of the proposed method.

Key words: shape and text separation, adaptive resampling, stroke entropy, symmetry judgment