对抗图像旋转的手指静脉身份识别新算法的设计

doi:10.3724/SP.J.1087.2012.03193

计算机应用 ›› 2012, Vol. 32 ›› Issue (11): 3193-3197.DOI: 10.3724/SP.J.1087.2012.03193

对抗图像旋转的手指静脉身份识别新算法的设计

汤露,彭双平

中国船舶重工集团公司第七一〇研究所，湖北宜昌 443003

收稿日期:2012-05-13 修回日期:2012-07-12 发布日期:2012-11-12 出版日期:2012-11-01
通讯作者: 汤露
作者简介:汤露(1986-),男,湖北潜江人,硕士研究生,主要研究方向：手指静脉身份识别、FPGA技术；彭双平(1985-),男,湖北荆州人,电子工程师,硕士,主要研究方向：嵌入式系统

New design of finger-vein identification algorithm against image rotation

TANG Lu,PENG Shuang-ping

No.710 Research and Development Institute, China Shipbuilding Industry Corporation, Yichang Hubei 443003, China

Received:2012-05-13 Revised:2012-07-12 Online:2012-11-12 Published:2012-11-01
Contact: TANG Lu

摘要/Abstract

摘要： 为了克服图像旋转对手指静脉身份识别系统正确率的影响，在图像预处理部分提出一种基于手指指尖点的旋转定位方法，改进了基于方向模板和局部动态阈值分割提取静脉特征的方法并用改进Hausdorff距离（MHD）距离进行匹配验证。实验结果表明，同一根手指的图片在平面偏移角度小于20°时，可以达到0.75%的等误率，正确识别率达97.25%，而且整个处理过程在VC++6.0上面执行耗时仅为161.6949ms，系统具有很好的实时性能，对实际手指静脉身份识别产品的开发具有一定的现实意义。

关键词: 手指静脉, 生物特征身份识别, 旋转校正, 指尖定位, 特征提取

Abstract: In order to overcome the impacts of image rotation on the accuracy of the finger-vein identification system, in the image pre-processing module, a new rotation approach based on the fingertip position to correct the target region was presented in this paper. The other part of the proposed system consists of an improved feature extraction module using direction templates and local dynamic threshold segmentation and a classification module using a Modified Hausdorff Distance (MHD). The experimental results show that it achieves a high recognition rate of 97.25%, and the Equal Error Rate (EER) is 0.75% when the drift angle among the images of the same finger is less than 20 degrees. What is more, the whole process took only 161.6949ms in VC〖KG-*3〗+〖KG-*3〗+6.0, which meant that the system had a superior real-time performance. The proposed system also has certain practical significance for developing finger-vein identification products.

Key words: finger-vein, biometric identification, rotation correction, fingertip location, feature extraction

中图分类号:

TP391.41

汤露彭双平. 对抗图像旋转的手指静脉身份识别新算法的设计[J]. 计算机应用, 2012, 32(11): 3193-3197.

TANG Lu PENG Shuang-ping. New design of finger-vein identification algorithm against image rotation[J]. Journal of Computer Applications, 2012, 32(11): 3193-3197.

参考文献

［1］余成波，秦华锋.生物特征识别技术——手指静脉识别技术[M].北京：清华大学出版社，2009. ［2］郭庆昌，陈金花，张静，等.手指静脉图像采集识别装置的手指安放器：中国，201020602567.3 [P],2011-05-25. ［3］管凤旭，王科俊，刘靖宇，等.归一双向加权（2D）2PCA的手指静脉识别方法[J].模式识别与人工智能,2011,24（3）：417-424. ［4］丁宇航.手背静脉识别技术研究[D].哈尔滨：哈尔滨工程大学,2006. ［5］王科俊，袁智.基于小波矩融合PCA变换的手指静脉识别[J].模式识别与人工智能，2007，20（5）：692-697. ［6］ CANNY J. A computational approach to edge detection [J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, 8(6)：679-698. ［7］和青芳.计算机图形学原理及算法教程：Visual C〖KG-*3〗〖KG-*3〗版[M].北京：清华大学出版社，2006。［8］王昊京，王建立，王鸣浩，等.采用双线性插值收缩的图像修复方法[J].光学精密工程,2010,18（5）：1234-1241. 〖HJ〗［9］ MIURA N, NAGASAKA A, MIYATAKE T. Feature extraction of finger-vein patterns based on repeated line tracking and its application to personal identification[J].Machine Vision and Applications, 2004, 15（4）：194-203. ［10］ YU C B, QING H F, ZHANG L. A research on extracting low quality human finger vein pattern characteristics[C]// The 2nd International Conference on Bioinformatics and Biomedical Engineering.Washington, DC: IEEE Computer Society, 2008：1876-1879. ［11］ DING Y H, ZHUANG D Y, WANG K J. A study of hand vein recognition method[C]// 2005 IEEE International Conference on Mechatronics and Automation.Washington, DC: IEEE Computer Society,2005：2106-2110. ［12］孙家广，胡事民.计算机图形学基础教程[M].北京：清华大学出版社，2005. ［13］ ZHANG T Y, SUEN C Y. A fast parallel algorithm for thinning digital patterns[J].Association for Computing Machinery,1984,27(3)：236-239. ［14］ WANG L Y, LEEDHAM G, CHO D S Y. Minutiae feature analysis for infrared hand vein pattern biometrics[J].Pattern Recognition, 2008, 41(3)：920-929. ［15］ DUBUISSON M P, JAIN A K. A modified Hausdorff distance for object matching[C] // Proceedings of the 12th IAPR International Conference on Pattern Recognition.Washington, DC: IEEE Computer Society,1994：566-568. ［16］王科俊，马慧.使用改进的方向滤波与修正的Hausdorff距离的指静脉识别方法[J].计算机辅助设计与图形学学报，2011,23（3）：385-391. ［17］王科俊，刘靖宇.基于相对距离和角度的手指静脉识别方法[J].华中科技大学学报:自然科学版，2011,39（5）：96-99. 〖ZK)〗〖HT〗〖HJ〗〖HQK〗〖FL)〗 〖KH-1〗〖HS1*2〗〖JZ〗〖CDS54〗 〖HTK〗〖HJ〗〖MZ（7H〗（上接第〖BP（〗周渝民〖BP）〗 3188 页）〖MZ）〗〖HT〗〖FL（K2〗〖HJ1.3mm〗〖HT6SS〗［10］ SPAGNOLO P, ORAZIOT D, LEO M, et al. Moving object segmentation by background subtraction and temporal analysis［J］. Image and Vision Computing, 2006,24(5):411-423. ［11］熊亮, 刘伟铭. 基于背景Codebook模型的前景检测算法［J］. 科学技术与工程,2010,10(9):2118-2121. ［12］ ILYAS A, SCUTURICI M,MIGUET S. Real time foreground-background segmentation using a modified codebook model［C］// Proceedings of IEEE Conference of Advanced Video and Signal Based Surveillance. Washington, DC: IEEE Computer Society, 2009:454-459. ［13］ SIGARI M H, FATHY M. Real-time background modeling/subtraction using two-layer codebook model［C］// Proceedings of the International Multi-Conference of Engineers and Computer Scientists.London, UK :Academic Press. 2008,1:717-720. ［14］〖JP4〗SUN JIAN, ZHANG WEIWEI, TANG XIAO’OU, et al. Background cut［C］// ECCV06 Proceedings of the 9th European Conference on Computer Vision. Berlin:Springer-Verlag，2006,2: 628-641. ［15］高韬,刘正光,张军,等. 基于特征点的多运动目标跟踪［J］.电子与信息学报,2010,32(5):1111-1115. ［16］〖JP4〗TA D-N, CHEN WEI-CHAO,GELFAND N, et al. SURFTrac: efficient tracking and continuous object recognition using local feature descriptors［C］// Proceedings of IEEE Conference of Computer Vision and Pattern Recognition. Washington, DC: IEEE Computer Society, 2009: 2937-2944. ［17］ CHOI J, CHO Y. Performance improvement of moving object recognition and tracking algorithm using parallel processing of SURS and optical flow［J］. World Academy of Science, Engineering and Technology, 2012, 62(6):264-267. ［18］ ERTYEK S. Real-time digital image stabilization using Kalman filter［J］. Real-time Imaging, 2002, 8(4):317-328. ［19］ PRITCH Y, RATOVITCH S, HENDEL A, et al. Clustered synopsis of surveillance video［C］// AVSS’09:Proceedings of IEEE Conference of Advanced Video and Signal Based Surveillance. Washington, DC: IEEE Computer Society, 2009:195-200. ［20］ PRITCH Y, RAV-ACHA A, PELEG S. Nonchronological video synopsis and indexing［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30(11): 1971-1984。［21］ ZHOU YUBIN. Real-time digital image stabilization based on contour motion classification for image stabilization with moving-objects［C］// SPIE’08:Proceedings of of International Society for Optics and Photonics Engineering. Washington, DC: IEEE Computer Society,2008,7156:71561F1-7. ［22］ ZHOU YUBIN. Real-time electronic digital image stabilization system based on multi-core computation［C］// Proceedings of Electronic Measurement and Instruments. Washington, DC: IEEE Computer Society, 2009:4308-414. ［23］ ZHANG PENG, DU JIANGUO, XIE XIAODONG, et al. A multi-standard video codec architecture based on multi-core pipeline［J］. Computer Research and Development, 2008, 45(11):1985-1993. ［24］ RASMUSSEN M S,STUART M B, KARLSSON S. Parallelism and scalability in an image processing application［J］. International Journal of Parallel Programming, 2009,37(3):306-323. ［25］ TERBOVEN C, an MEY D, SCHMIDL D, et al. First experiences with intel cluster OpenMP［C］// Proceedings of the 4th International Conference on OpenMP in a New Era of Parallelism. Berlin:Springer-Verlag, 2008:48-59.

[1]	郑志强, 胡鑫, 翁智, 王雨禾, 程曦. 基于改进DenseNet的牛眼图像特征提取方法[J]. 计算机应用, 2021, 41(9): 2780-2784.
[2]	佘玉龙, 张晓龙, 程若勤, 邓春华. 基于边缘关注模型的语义分割方法[J]. 计算机应用, 2021, 41(2): 343-349.
[3]	赵津, 宋文爱, 邰隽, 杨吉江, 王青, 李晓丹, 雷毅, 邱悦. 儿童阻塞性睡眠呼吸暂停计算机人脸辅助诊断综述[J]. 《计算机应用》唯一官方网站, 2021, 41(11): 3394-3401.
[4]	朱新成, 何坤金, 倪娜, 郝博. 基于改进迭代最近点算法的接骨板贴合性快捷计算方法[J]. 计算机应用, 2021, 41(10): 3033-3039.
[5]	尹春勇, 何苗. 基于改进胶囊网络的文本分类[J]. 计算机应用, 2020, 40(9): 2525-2530.
[6]	周云, 陈淑荣. 基于双流非局部残差网络的行为识别方法[J]. 计算机应用, 2020, 40(8): 2236-2240.
[7]	张家岗, 李达平, 杨晓东, 邹茂扬, 吴锡, 胡金蓉. 基于深度卷积特征光流的形变医学图像配准算法[J]. 计算机应用, 2020, 40(6): 1799-1805.
[8]	徐代, 岳璋, 杨文霞, 任潇. 基于改进的三向流Faster R-CNN的篡改图像识别[J]. 计算机应用, 2020, 40(5): 1315-1321.
[9]	张俊升, 徐晶晶, 余伟. 面部美化图像质量无参考评价方法[J]. 计算机应用, 2020, 40(4): 1184-1190.
[10]	刘尚旺, 刘承伟, 张爱丽. 基于深度可分卷积神经网络的实时人脸表情和性别分类[J]. 计算机应用, 2020, 40(4): 990-995.
[11]	沈亮, 王鑫, 陈曙晖. 面向移动应用识别的结构化特征提取方法[J]. 计算机应用, 2020, 40(4): 1109-1114.
[12]	郭志强, 胡永武, 刘鹏, 杨杰. 基于特征融合的室外天气图像分类[J]. 计算机应用, 2020, 40(4): 1023-1029.
[13]	朱喆, 许少华. 降噪自编码器深度卷积过程神经网络及在时变信号分类中的应用[J]. 计算机应用, 2020, 40(3): 698-703.
[14]	陈梅婕, 谢振平, 陈晓琪, 许鹏. 专利新词发现的双向聚合度特征提取新方法[J]. 计算机应用, 2020, 40(3): 631-637.
[15]	王海鹏, 降爱莲, 李鹏翔. 牛顿-软阈值迭代鲁棒主成分分析算法[J]. 计算机应用, 2020, 40(11): 3133-3138.

对抗图像旋转的手指静脉身份识别新算法的设计

New design of finger-vein identification algorithm against image rotation

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics