[1]王霞玲,吕 岳,文 颖.复杂背景和非均匀光照环境下的条码自动定位和识别[J].智能系统学报,2010,5(01):35-40.
 WANG Xia-ling,LU Yue,WEN Ying.Automatic location and recognition of barcodes on objects with complex background and nonuniform lighting[J].CAAI Transactions on Intelligent Systems,2010,5(01):35-40.
点击复制

复杂背景和非均匀光照环境下的条码自动定位和识别(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第5卷
期数:
2010年01期
页码:
35-40
栏目:
出版日期:
2010-02-25

文章信息/Info

Title:
Automatic location and recognition of barcodes on objects with complex background and nonuniform lighting
文章编号:
1673-4785(2010)01-0035-06
作者:
王霞玲1吕 岳12文 颖23
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
Author(s):
WANG Xia-ling1 LU Yue12 WEN Ying23
1.Department of Computer Science and Technology, East China Normal University, Shanghai 200241, China;
2. Shanghai Research Institute of China Post Group, Shanghai 200062, China;
3.Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, Shanghai 200240, China
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
Keywords:
barcode localization barcode recognition complex scenes uneven illumination Harris corner detection Bernsern algorithm
分类号:
TP391.41
文献标志码:
A
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.
Abstract:
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.

参考文献/References:

[1]LU Xiangju, FAN Guoliang, WANG Yukuan. A robust barcode reading method based on image analysis of a hierarchical feature classification[C]//International Conference on Intelligent Robots and Systems. Beijing, China, 2006: 33583362. 
 [2]ANDO S, HONTANI H. Automatic visual searching and reading of barcodes in 3D scene[C]//Proceedings of the IEEE International Vehicle Electronics Conference. Tottori, Japan, 2001: 4954.
[3]OKTEM R. Bar code localization in wavelet domain by using binary morphology[C]//Proceedings of the IEEE 12th Signal Processing and Communications Applications Conference. Ankara, Turkey, 2004: 499501.
[4]ZHANG Chunhui, WANG Jian, HAN Shi, et al. Automatic realtime barcode localization in complex scenes[C]//IEEE International Conference on Image Processing. Atlanta, USA, 2006: 497500. 
 [5]JAIN A K, CHEN Y. Barcode localization using texture analysis[C]//Proceedings of the 2nd International Conference on Document Analysis and Recognition. Tsukuba City, Japan, 1993: 4144.
[6]TROPF A, CHAI D. Locating 1D bar codes in DCTdomain[C]//IEEE International Conference on Acoustics, Speech and Signal Processing. Toulouse, France, 2006: 1419.
[7]刘宁钟. 复杂背景中条码检测定位技术的研究[J]. 南京航空航天大学学报,2005(37): 14. 
LIU Ningzhong. Detection and localization of barcode in complicated background[J]. Journal of Nanjing University of Aeronautics & Astronautics, 2005(37): 14. 
[8]HARRIS C, STEPHENS M J. A combined corner and edge detector[C]//Proceedings of the Fourth Alvey Vision Conference. Manchester, UK, 1988: 147151.
[9]SCHIMID C, MOHR R, BAUCKHAGE C. Evaluation of interest point detectors[J]. International Journal of Computer Vision, 2000(37): 151172.
[10]SCHMID C, MOHR R, BAUCKHAGE C. Comparing and evaluating interest points[C]//Proceedings of the 6th International Conference on Computer Vision. Bombay, India, 1998: 230235.
[11]DRIVAS D, AMIN A. Page segmentation and classification utilizing[C]//Proceedings of the 3rd International Conference on Document Analysis and Recognition. Montreal, Canada, 1995: 4246.
[12]PRATT W K. Digital image processing[M]. 3rd ed. New York, USA: John Wiley & Sons, Inc, 2001: 174175.
[13】BERNSEN J. Dynamic thresholding of graylevel images[C]//Proceedings of 8th International Conference on Pattern Recognition. Paris, France, 1986: 12511255.

备注/Memo

备注/Memo:
收稿日期:2008-11-24.
基金项目: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).
通信作者:王霞玲.E-mail:lilinling@gmail.com.
作者简介:
王霞玲,女,1985年生,硕士研究生, 主要研究方向为图像处理和模式识别.
吕 岳,男,1968年生,教授、博士生导师、博士,华东师范大学计算机科学技术系主任,上海市自动化学会常务理事、模式识别专业委员会副主任,上海市计算机学会理事、普适计算专业委员会副主任、计算机教育专业委员会副主任.主要研究方向为图像处理、模式识别、智能系统.教育部新世纪优秀人才支持计划入选者,上海市曙光学者.发表学术论文70余篇,授权发明专利2项.
文 颖,女,1975年生,博士研究生,主要研究方向为图像处理、统计学习理论、流形学习、机器学习、人脸识别、字符识别等
更新日期/Last Update: 2010-04-06