机构地区: 华南理工大学电子与信息学院
出 处: 《自动化学报》 2008年第5期597-600,共4页
摘 要: 为提高二维条码自动检测定位的效率,提出了一种利用小波多分辨率分析进行PDF417二维条码自动检测定位的新方法。该方法在高频子图基于特征向量利用纹理相似性原理,采用区域增长法产生二维条码数据区域的候选子区域集合,然后在低频子图利用二维条码的起始符、终止符及其边界特征对候选子区域进行验证,最后得到二维条码在图像中的位置.实验证明该方法能准确定位受到不同污损程度的二维条码图像,特别在污损程度高的情况下,该方法具有独特的优势. To improve the efficiency of detecting and locating PDF417 two-dimensional barcode, an automatic detecting and locating approach based on wavelet multi-resolution analysis is presented, in which the regional growth method based on feature vector and texture comparability theory is adopted to produce the candidate sub-area set of two-dimensional barcode in high frequency sub-images, and then the candidate sub-area set are verified by examining the start/stop pattern and edge characteristics of PDF417 in low frequency sub-image to gain the location of PDF417 in original image. Experiments show that the approach can detect and locate exactly the two dimensional barcode for PDF417 with different backgrounds, and is superior to the traditional algorithms in practicability.
关 键 词: 小波分析 多分辨率分析 图像定位 特征提取 二维条码
领 域: [自动化与计算机技术] [自动化与计算机技术]