汉字笔迹鉴别中预处理算法实现

Preprocessing algorithms for Chinese handwriting recognition

针对自由格式的手写体汉字,提出一套系统完整的笔迹图像预处理算法,其中我们将汉字宽度的统计特性与高斯分布的特性结合进行粘连字的滤除,然后根据粘连字的投影图中波谷点的位置,选择某一阈值作为最佳切分点将其分割开来,从而很容易实现了字符大小的归一化、汉字的任意拼接和行倾斜的校正.该算法使得整个预处理子系统更加稳定与完善,为后续的笔迹鉴别提供了可靠的保证.

A series of complete and systematic algorithms on preprocessing of a handwritten image is proposed for free-fommt handwritten Chinese characters. The connected character removal is carried out by combining statistical characteristic of character width with the Gauss distribution. According to the location of the valley point on projecting images, a threshold value is selected as the best division point resulting in the easy realization of size normalizing and character mosaic and line slope correction. The proposed methods make the whole preprocessing subsystem more stable and perfect, which lays a dependable foundation for subsequent handwriting recognition.