面向条码识读的自适应二值化改进算法  

Improved adaptive thresholding algorithm used in barcode reading

作　　者：罗松[1] 王俊峰[1] 唐鹏[2] 陈懿[3] 

机构地区：[1]四川大学计算机学院,四川成都610064 [2]西南交通大学电气工程学院,四川成都610031 [3]航天信息股份有限公司,北京100195

出　　处：《计算机工程与设计》2013年第4期1324-1330,共7页Computer Engineering and Design

基　　金：国家科技重大专项基金项目(2013ZX03005009-002);国家自然科学基金项目(11102124);教育部新世纪优秀人才支持计划基金项目(NCET-10-0604);教育部博士基金项目(20090181110053);四川省青年基金项目(09ZQ026-028)

摘　　要：为了对条码内容进行识读解码,需要对条码图像进行二值化处理以求取出条码的条空序列。现行的二值化方法大多要么不能够获取到较好的条码二值化图像,要么二值化所需的处理时间太长不能够满足实时性需求。对此,提出一种使用积分图的基于Wellner自适应二值化算法的改进方法。实验结果表明,该方法对不同光照环境的图像都能够获取到较好的条码二值化图像,为条码识读解码提供较好的图像效果,从而提升条码识别成功率;此外,该方法所需处理时间较短,能够满足大多数条码识读应用对实时性的需求。To decode the content of barcode, a good binary image is needed. There are many binarization methods, but most of them either not able to get a good barcode binary image or need a long time to process image. To solve these problems, an im- proved adaptive thresholding algorithm uses integral image based on Wellner＇s method is presented. Experimental results show that this method can get a good binary image for both uniform and uneven illumination, which will give a good support for detec- ting and decoding barcode. The experimental results also show that the processing just need a little time, so it can be used in real-time required applications such as embedded system applications.

关 键 词：自适应二值化 积分图 阈值化 条码识读 二维码 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]