[1]董夙慧,孙中廷,徐永刚.采用GPU并行计算与图像匹配的工件条码识别算法[J].华侨大学学报(自然科学版),2017,38(1):80-85.[doi:10.11830/ISSN.1000-5013.201701015]
　DONG Suhui,SUN Zhongting,XU Yonggang.Workpiece Barcode Identification Algorithm Using GPU Parallel Computing and Image Matching[J].Journal of Huaqiao University(Natural Science),2017,38(1):80-85.[doi:10.11830/ISSN.1000-5013.201701015]
点击复制

采用GPU并行计算与图像匹配的工件条码识别算法()
分享到：

《华侨大学学报（自然科学版）》[ISSN:1000-5013/CN:35-1079/N]

卷:
第38卷
期数:
2017年第1期
页码:
80-85
栏目:
出版日期:
2017-01-09

文章信息/Info

Title:
Workpiece Barcode Identification Algorithm Using GPU Parallel Computing and Image Matching
文章编号:
1000-5013(2017)01-0080-06
作者:
董夙慧1; 2;  孙中廷1; 2;  徐永刚1
1. 中国矿业大学 信息与电气工程学院, 江苏 徐州 221008;2. 江苏联合职业技术学院 徐州财经分院, 江苏 徐州 221011
Author(s):
DONG Suhui1; 2;  SUN Zhongting1; 2;  XU Yonggang1
1. College of Information and Electrical Engineering, China University of Mining and Technology, Xuzhou 221008, China; 2. Xuzhou Branch of Finance, Jiangsu Lianhe Technical Institute, Xuzhou 221001, China
关键词:
条码识别;  图形处理器;  图像匹配;  并行计算;  归一化协方差
Keywords:
barcode identification;  graphics processing unit;  image matching;  parallel computing;  normalized covariance
分类号:
TP391
DOI:
10.11830/ISSN.1000-5013.201701015
文献标志码:
A
摘要:
设计基于图形处理器(GPU)并行计算与图像匹配的条码识别算法.首先,设计基于归一化协方差的图像匹配算子,定位每个条码的位置.然后,根据条码面积、周长、形状因子,确定条码种类.最后,采用GPU并行计算方式完成条码解析.实验数据显示:与当前条码识别技术相比,所提算法能够同步识别多种条码,且在面对光照强度较暗或过高时,该算法具有更高的稳定性与抗干扰性,其仍具有更高的识别精度与效率.
Abstract:
The workpiece barcode synchronization identification algorithm based on graphics processing unit(GPU)parallel computing and image matching was proposed in this paper. Firstly, the position of each barcode was located by designing image matching operator based on normalized covariance. Then the type of barcode was determined according to the barcode area, perimeter, and shape factor. Finally, the analysis of the barcode was finished by GPU parallel computing method. Experimental data shows that: compared with the current barcode recognition technique, this algorithm can identify a variety of barcode, this algorithm had a higher stability under the light intensity is dark or too high, and it had a higher recognition accuracy and efficiency.

参考文献/References:

[1] 殷锐,陈金亮.面向DNC车间的刀具全寿命周期管理技术研究[J].组合机床与自动化加工技术,2013,2(3):134-136.
[2] 王宇,黄富贵,李兴旺.平面度误差统计特征实验[J].华侨大学学报(自然科学版),2014,35(5):487-491.
[3] 胡辉.检测算法在条码识别中的应用研究[J].计算机工程,2015,32(14):18-25.
[4] NARAYAN G R,JAMES M V.Barcode recognition from video by combining image processing and xilinx[J].Procedia Engineering,2012,38(12):2140-2146.
[5] 胡大辉.边缘检测算法在污损条码识别中的应用研究[J].包装工程,2015,43(2):71-76.
[6] 王鹏.航空信息系统中基于CPU & GPU结构的条码识别技术的研究[J].计算机科学,2015,33(10):86-100.
[7] 胡智宏.平移匹配在倾斜条码快速识别中的应用研究[J].包装工程,2015,21(21):283-287.
[8] ZHOU Shengbo,SHEN Aiqin,LI Gengfei.Concrete image segmentation based on multiscale mathematic morphology operators and otsu method[J].Advances in Materials Science and Engineering,2015,11(7):124-135.
[9] LUO Nan,SUN Quansen,CHEN Qiang.A novel tracking algorithm via feature points matching[J].PloS One,2015,10(1):e0116315-e0116324.
[10] PENG Shiyou,DONG Qinghua.GPU-based parallel prewitt algorithm implementation and its application on GPR[J].Computer Science and Application,2013,3(3):153-158.
[11] HUANG Yao,XIAO Bingjia,LUO Zhengping,et al.Implementation of GPU parallel equilibrium reconstruction for plasma control in EAST[J].Fusion Engineering and Design,2016,34(10):134-145.
[12] SATOSHI O.Coevolutionary design of a watermark embedding scheme and an extraction algorithm for detecting replicated two-dimensional barcodes[J].Applied Soft Computing,2015,710(24):34-35.

备注/Memo

备注/Memo:
收稿日期: 2016-03-04
通信作者: 董夙慧(1977-),男,副教授,主要从事图像识别与应用、网络安全、大数据的研究.E-mail:dongsuhui1977@aliyun.com.
基金项目: 江苏省自然科学基金资助项目(BD2011129)
更新日期/Last Update: 2017-01-20