电表图像中多条码的定位与识别  

Location and Recognition of Multiple Barcodes in the Images of Electric Meters

作　　者：雷海军[1] 林毅锋[1] 罗小江[1] 沈伟鹏[1] 

机构地区：[1]深圳大学计算机与软件学院广东省普及型高性能计算机重点实验室深圳市服务计算与应用重点实验室,深圳518060

出　　处：《湖南工程学院学报（自然科学版）》2014年第3期1-4,共4页Journal of Hunan Institute of Engineering(Natural Science Edition)

基　　金：国家自然科学基金-广东联合基金重点项目(U1301252);国家863项目(2012AA01A309);省部产学研项目(2012B091100495);深圳市战略性新兴产业项目(JCYJ20120613113419607)

摘　　要：根据条形码的平行、密集等特性,设计了一套在电表图像中对多条条形码进行定位并且逐一识别的算法,可用于抄录条码的人工智能设备.该算法主要分三部分,分别是条码定位、条码抽取和条码识别.其中条码定位和条码抽取的算法,是根据条形码的平行和紧密的形态特性而设计;而条码识别在条码抽取的基础上利用组合计算条和空的宽度比例.实验表明,本文算法能够对图像中多个条形码进行准确且快速的定位,并且能逐个识别和校验.Based on the bareode＇s parallelTmtenslve features, an algorithm which can locate and recogmze multiple barcodes individually in the images of electric meters has been designed in this paper. It can be used in the Artificial intelligence equipment which records the barcode. The algorithm is divided into bar code location, harcode extraction and barcode recognition in three parts. Barcode location and barcode extraction are based on the characteristics of the barcodes such as parallel and close. Barcode recognition uses combination of bars and spaces to calculate the scale of their width. The experiment proves that this algorithm can locate and recognize multiple barcodes accurately and quickly in the complex background.

关 键 词：边缘检测 霍夫变换 多条码定位 条码抽取 条码识别 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]