基于数字结构的中长跑比赛自动计圈技术研究

Study on Auto-counting for Middle-distance Race Based on Digit Frame

为了识别号码布图像中的三个数字,基于数字结构特征建立了数字0～9的Fisher线性判别模型。基于图像处理从号码布图像中提取数字二值图像。用直线切割数字区域获取切割区域特征和切割线特征简单、稳定、不重复,可以代表数字的基本形状,对数字的区分度较好。Bayes判别分析结果表明:所建模型经内部验证对数字0～9的识别率达100%。基于数字的结构识别运动员号码是可行的,为研制中长跑自动计圈系统提供了方法。

In order to distinguish three digits from a number cloth image,Bayes-criterion-based linear discrimination models of 0 through 9 were developed based on their frame.A digit binary image was extracted from a number cloth image based on image processing.Digit frame features,including cut regions and cut lines,are easy,steady,non-repetitious and separable to the digits from 0 to 9 for their shape,which were obtained by using lines cutting digit region.Bayes-based discrimination results show that discrimination models of 0 through 9 were developed with an accuracy of 100% based on re-substitution.It is feasible to recognize athlete number based on digital frame,which helps to develop auto-counting system for middle-distance race.