改进二值化算法在QR码识别中的应用  

The Improvement Binarization Algorithm for QR Code Recognition

作　　者：杨凌霄[1] 冯庆修 YANG Ling-xiao;FENG Qing-xiu(School of Electrical Engineering and Automation,Henan Polytechnic University,Jiaozuo 454000,China)

机构地区：[1]河南理工大学电气工程与自动化学院,河南焦作454000

出　　处：《软件导刊》2020年第3期163-167,共5页Software Guide

摘　　要：针对模糊、光照不均情况下获得的低质量QR码难以识别的问题,设计一种低质量QR码识别算法,包括加权平均值法灰度化、中值滤波算法降噪、二值化、基于位置探测图形定位、基于透视变换法的旋转矫正,以及基于Zbar开源库的译码算法等。重点研究针对模糊、光照不均QR码图像的二值化算法,提出一种基于Bernsen算法思想的改进算法,将全局阈值引入该算法中,实现对图像的二值化处理。在VS2010环境下基于Opencv2.4.9图像处理库对识别算法进行验证,结果表明,通过该算法得到的QR码图像完整且噪声少,有效克服了低质量QR码的影响,提高了图像识别率,具有一定的实用性。The paper devises an improved computing method for low quality QR code,including graying,the de-nosing median filtering algorithm,binarization,positioning,correction and a decoding computing method based on Zbar open source library,so as to address the problem of the inability to recognize the QR code caused by blur images and uneven lighting.The paper attaches great importance to the binarization of blurring and uneven light QR images,thus proposing an improved computing method based on Bernsen method with the introduction of global thresholding to achieve the binarization of QR code.The author tests this computing method based on OpenCV2.4.9 computer vision open source library in VS2010 setting.The study indicates that this approach will efficiently overcome the negative impact low quality QR code have on the recognition,consequently and proficiently create a full image with less noises and improve the recognition rate of QR code.

关 键 词：低质量QR码 二值化 Bernsen Zbar 图像识别 

分 类 号：TP319[自动化与计算机技术—计算机软件与理论]