结合列边缘提取的PDF417条码检测方法  

Detection of PDF417 bar code based on column boundary extraction

作　　者：汪鲁才[1] 刘鑫[1] 易锡年[1] 

机构地区：[1]湖南师范大学工学院,长沙410081

出　　处：《计算机工程与应用》2013年第7期179-182,共4页Computer Engineering and Applications

基　　金：湖南省科技厅科研基金(No.2010FJ6014)

摘　　要：针对PDF417条码在复杂背景中检测定位的技术问题,提出一种基于字符间列边缘提取的定位方法。通过对PDF417码的结构特征进行分析,利用子区域的多特征分析法提取目标区域,并在此基础上提取条码的列向边缘,实现了准确定位。通过霍夫变换确定条码边界,对条码区域进行提取。实验结果表明,对于背景复杂且条码区域信息未知的情况,该定位算法具有良好的结果。An approach for PDF417 bar-code detection and localization in complicated scene is proposed. Based on analyzing the structural characteristics of bar-code, the region of interest is extracted according to the multiple characteristics analysis. Then the code is located by detecting the column separated edge. At last, the bar code borders based on Hough transformation is determined and extracted. Experimental results show that this approach has a good performance.

关 键 词：PDF417条码 定位 复杂背景 子区域 特征分析 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]