复杂背景和非均匀光照环境下的条码自动定位和识别  

Automatic location and recognition of barcodes on objects with complex background and non-uniform lighting

作　　者：王霞玲[1] 吕岳[1,2] 文颖[2,3] 

机构地区：[1]华东师范大学计算机科学与技术系,上海200241 [2]中国邮政集团公司上海研究院,上海200062 [3]上海交通大学图像处理与模式识别研究所,上海200240

出　　处：《智能系统学报》2010年第1期35-40,共6页CAAI Transactions on Intelligent Systems

基　　金：国家自然科学基金资助项目(60475006);教育部新世纪优秀人才支持计划资助项目(NCET-05-0430)

摘　　要：提出了一种在复杂背景和非均匀光照环境下的条码自动定位识别算法,用于定位和识别实际应用中的条码图像.该算法首先将灰度图像分成若干个子区域,根据每个子区域的梯度特征和角点特征筛选出可能含有条码的子区域,对这些子区域采用连通区域算法进行合并和分析,定位出条码区域.由于传统的二值化方法对于非均匀光照环境下的条码图像处理效果不佳,提出一种改进的Bernsen二值化算法对条码区域进行二值化处理,有效地减小了光照不均对条码识别的影响.实验结果表明,该算法可以有效去除大量复杂背景,准确定位和识别任意角度的条码区域.特别在非均匀光照环境和含有大量文字等复杂背景的情况下,该方法具有明显优势.An algorithm was proposed that more effectively locates and recognizes barcodes.The first step was to divide the image into several sub-regions.Then sub-regions containing barcodes were determined according to gradients and the presence of corner features.If sub-regions with probable barcodes were found in more than one region,the sub-regions were merged and then analyzed to locate the barcode.Since traditional binarization algorithms produce poor results in non-uniformly illuminated images,the improvements to Bernsen＇s algorithm were formalized.They greatly reduced the effects of non-uniform illumination on barcode recognition.Experimental results showed that the proposed method could remove complex backgrounds,accurately locating and recognizing barcode regions at any arbitrary angle.In particular,the method achieved good performance even with uneven illumination and complex background.

关 键 词：条码定位 条码识别 复杂背景 非均匀光照 HARRIS角点检测 Bernsen算法 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]