基于亚像素大津法的二维条码分割  

2D BARCODE SEGMENTATION BASED ON SUB-PIXEL AND OTSU METHOD

作　　者：袁军[1] 王俊峰[1] 唐鹏[2] 

机构地区：[1]四川大学计算机学院,四川成都610064 [2]西南交通大学电气工程学院,四川成都610031

出　　处：《计算机应用与软件》2013年第4期22-25,28,共5页Computer Applications and Software

基　　金：国家自然科学基金项目(11102124);四川省应用基础研究项目(2010JY0013);教育部新世纪优秀人才支持计划项目(NCET-10-0604);教育部博士点基金项目(20090181110053)

摘　　要：在低分辨率的情况下,基于像素的条码分割方法很容易造成二维条码的深色模块和浅色模块分割错误,导致条码不能被正确识别。为解决该问题,提出一种基于亚像素大津法的二维条码分割方法。首先进行基于插值算法的亚像素处理来提高条码图像的分辨率,为此提出了一种改进的基于边缘的自适应插值算法。然后用基于分块的大津法分割条码图像的深色模块和浅色模块。实验结果表明该方法能够有效地消除低分辨率对条码识别的影响。In the situation of low resolution,black modules and white modules of 2D barcode are very easy to be segmented wrongly with the method of pixel-based barcode segmentation,which results in the barcode can not be recognized correctly.To solve this problem,a 2D barcode segmentation method based on sub-pixel and Otsu method is proposed in this paper.First,the resolution of the barcode image is improved by sub-pixel processing which is based on an improved edge-based adaptive interpolation algorithm.Then the dark and light modules of the barcode image are segmented with block-based Otsu method.Experimental results demonstrate that the method can eliminate the impact of low resolution on barcode recognition effectively.

关 键 词：亚像素 分块大津法 条码分割 分辨率 插值算法 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]