This paper adopts the method of two level classfications to carry out recognition , by which we put forward a kind of method based on unit circle projection to class approximately and use texture feature based on gray level run length matrix to class accurately and gives the last output 本文采取两级分类识别的方法:其中提出了一种基于单位圆投影的方法将待选字进行粗分,并结合基于游程矩阵提取纹理特征的技术进行细分并识别。
Input method of compound character : decide the left upper part of a character belongs to which feature , and input the character features . then choose the component most similar to the left part of the character , and select the right feature most similar to the right part . a number of characters will pop up for your choice 分体字的输入方法是：先判断文字的左上方属于哪一种特徵，按下该特徵后再判别该部份与哪个部件最近似，按下该部件后再判别右上方字形与哪个特徵最近似，按下该特徵后便可以选字。
