一种QR码识别的低复杂度图像预处理方法  

A Low-complexity Image Pre-processing for Quick Response Barcode Recognition

作　　者：陈威兵[1,2] 杨高波[1] 冯璐[2] 

机构地区：[1]湖南大学信息科学与工程学院,湖南长沙410082 [2]长沙学院电子与通信工程系,湖南长沙410003

出　　处：《湖南大学学报（自然科学版）》2012年第10期93-97,共5页Journal of Hunan University:Natural Sciences

基　　金：国家自然科学基金资助项目(61072122);湖南省科技计划资助项目(2011FJ3116)

摘　　要：QR(Quick Response)码是一种常见的二维条形码,图像预处理是实现复杂条件下QR码图像自动识别的重要步骤.为了降低QR码使用门槛,提出了一种实用的低复杂度QR码识别图像预处理算法,它可以提高解码器识别速率,便于算法嵌入移动终端.由于没有使用传统的边缘检测和直线检测手段,而是依据QR码自身编码特点进行探测定位,所以几何失真、背景噪声对其影响较小;此外,为提高了QR码的识别率,采用结合校正图形并按区域自适应取样的方法来生成码流.实验结果表明,该算法可以克服QR码识别过程中易受噪声干扰、光照不均和几何失真等影响,并能满足实时解码的要求.Quick Response （QR） barcode is a quite common two dimensional barcode. Image prepro- cessing is a key step for the automatic recognition of QR barcode decoder. In order to lower the used threshold, a practical image preprocessing method was proposed for QR barcode recognition. It could in- crease the speed of recognition by this decoder so as to embed this algorithm into mobile terminals. It didn ＂t utilize the traditional methods such as edge detection and line detection, but only the encoding character- istic of QR to locate, thus the influence of geometric distortion and background noise was reduced. Moreo- ver, in order to improve the recognition rate, it used the rectification images to adaptively sample the QR code in terms of regions. Experiment results demonstrate that the proposed approach can overcome the in- fluence of noise, inhomogeneous light and geometric distortion, and meet the requirements of real-time de- coding.

关 键 词：二维条形码 快速反应码 图像预处理 定位 二值化 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]