【摘要】 本文提出一种手写印刷体汉字识别方法,使用该方法无需先对汉字进行细化和平滑处理。利用汉字笔划的相关性,抽取汉字图像的结构特征.在特征抽取过程中,考虑到一些噪声的影响,因而对质量较低劣的汉字识别也有效。实验结果较满意。更多还原

【Abstract】 A proper method for the recognition of handprinted Chinese characters is presented here, without thinning the character image and smoothing it before hand. With the help of the relationship of the stroker in character, it is convenient to extract its structure features. During the feature-extracting course, we minimize the attect of some noises and varieties in the character imager. Therefore it is possible to recognize the Chinese character with lower qualities. A satisfactory experimental result is obtained.更多还原