数显数字字符图像特征提取算法的研究与实现

Study and Realization for Numeral Instrument Image Feature Extraction Method

由于数显数字字符有其自身特点,相对于其它类型字符识别存在着新的难点,针对此类数显数字字符采用将细化后的字符图像看作是一幅连通图,选择闭合曲线作为其整体特征对十个数字字符进行初次分类,将笔画端点所处字符图像中四个子区域的位置作为主要的细节特征,对字符进行识别。测试结果表明该算法是可行、有效的。

A thirmed image is viewed as a graph. In the procession of image recognition of numeral instrument,the author of the paper selects closed curves as integrate features of those character images,makes the sub region where the end of last drawing of numbers locate of the character images as the major specific features,and then recognizes the character of numeral instrument. The experiment results shows that the proposed approach is practical and effective.