精密曲线轮廓字模的生成方法研究

A Research for Obtaining Precise Curvilinear Outline Matrixes

本文介绍了一种精密曲线轮廓字模生成方法．这种方法运用图象处理技术，对字符的点阵进行部件分离、边缘发现、边缘跟踪、边缘修改，以便得到精确的字符边界轮廓．然后，运用本文设计的新的邻边加权平均样条曲线量化方法，生成高精密度、高压缩比的曲线轮廓字模．实验结果表明，本文设计的方法较好地保留了字符的特征，具有较高的压缩比和较快的还原速度．该方法还可以对其它任意二值图象进行曲线量化。

n this paper,a new method of obtaining precise curvilinear outline matrixes is proposed. By employing image processing techniques, this method is adopted to realise component segmentation, edge detection, edge tracing and edge modification for character Point lattices so as to abstract accurate edges of characters. Then curvilinear outline matrixes of high precision and a high compressing ratio is obtained by using a new local cubic spline interpolation curvilinearization of adjacent boundary weighted averaging presented in this paper. Experiments show that this method satisfactorily preserves the characteristics of characters with a high compressing ratio and a fast restoring Speed. The method can also be used to curvilinearise other arbitrary binary images.