首页 > 论文 > 光学学报 > 33卷 > 10期(pp:1015004--1)

基于灰度曲面匹配的快速手掌静脉识别

Fast Palm Vein Identification Algorithm Based on Grayscale Surface Matching

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

为使掌脉识别系统在识别性能和识别时间上有一个较好的平衡,提出了一种基于灰度曲面匹配的快速手掌静脉识别算法。对手掌静脉图像提取感兴趣区域,将感兴趣区域等分为若干个子区域,计算每个子区域像素灰度平均值作为该子区域灰度值,以各子区域灰度值构建待匹配图像。匹配时对两个待匹配灰度曲面中的像素灰度做差,得到灰度差曲面,求出该灰度差曲面的方差,将此方差作为衡量两个掌脉特征曲面之间距离的依据,并据此判定两幅掌脉图像是否来自同一只手。应用自建掌脉图库进行实验分析,该算法选择子区域大小为8 pixel×8 pixel时的正确识别率达到97.94%,识别时间仅用0.163 ms。实验结果表明,与传统掌脉识别算法相比,该算法在识别性能和识别时间上有一个较好的平衡。

Abstract

In order to improve the recognition speed with effective recognition performance of palm vein identification system, a fast palm vein identification algorithm based on grayscale surface matching is proposed. The algorithm extracts region of interest (ROI) of palm vein image firstly. Then, the ROI is equally divided into several sub-regions. The algorithm computes average value of the grayscale of every sub-region. These average values construct an image for matching. At the stage of matching, the algorithm computes the difference between two pixels from two matching images and gets the grayscale difference surface. It calculates the variance of the grayscale difference surface and considers this variance as the distance between two feature surfaces. At last, it decides whether these two images come from the same hand or not according to the variance. A self-built palm vein database is used in the experiment. The experimental result shows that the scheme with sub-region parameter of 8 pixel×8 pixel reaches correct recognition rate (CRR) of 97.94%, with recognition time of only 0.163 ms. Compared with the traditional palm vein recognition method, the proposed method increases recognition speed with effective recognition performance.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391.41

DOI:10.3788/aos201333.1015004

所属栏目:机器视觉

责任编辑:李文喆  信息反馈

基金项目:国家自然科学基金(60972123)、高等学校博士学科点专项科研基金(20092102110002)、沈阳市科技计划(F10-213-1-00)、辽宁省教育厅科研项目(L2012034)

收稿日期:2013-03-08

修改稿日期:2013-06-07

网络出版日期:--

作者单位    点击查看

吴微:沈阳工业大学视觉检测技术研究所, 辽宁 沈阳 110870沈阳大学信息工程学院, 辽宁 沈阳 110041
苑玮琦:沈阳工业大学视觉检测技术研究所, 辽宁 沈阳 110870
林森:沈阳工业大学视觉检测技术研究所, 辽宁 沈阳 110870
宋辉:沈阳工业大学视觉检测技术研究所, 辽宁 沈阳 110870
桑海峰:沈阳工业大学视觉检测技术研究所, 辽宁 沈阳 110870

联系人作者:吴微(wuwei429@163.com)

备注:吴微(1979—),女,博士研究生,讲师,主要从事机器视觉检测、生物特征识别等方面的研究。

【1】Wang Lingyu, Graham Leedham. Near- and far-infrared imaging for vein pattern biometrics [C]. Proceedings of the IEEE International Conference on Video and Signal Based Surveillance, 2006. 52-57.

【2】Masaki Watanabe. Palm Vein Authentication in Advances in Biometrics [M]. Heidelberg: Springer-Verlag, 2008. 75-88.

【3】Yuan Weiqi, Feng Suyue. Simulation system of improved non-contact on-line palmprint recognition [J]. Acta Optica Sinica, 2011, 31(7): 0712003.
苑玮琦, 冯素月. 改进的非接触式在线掌纹识别模拟系统[J]. 光学学报, 2011, 31(7): 0712003.

【4】David Zhang, Zhenhua Guo, Guangming Lu, et al.. Online joint palmprint and palmvein verification [J]. Expert System with Applications, 2011, 38(3): 2621-2631.

【5】Liu Tiegen, Wang Yunxin, Li Xiuyan, et al.. Biometric recognition system based on hand vein pattern [J]. Acta Optica Sinica, 2009, 29(12): 3339-3343.
刘铁根, 王云新, 李秀艳, 等. 基于手背静脉的生物特征识别系统[J]. 光学学报, 2009, 29(12): 3339-3343.

【6】Ye Changming, Jiang Jianguo, Zhan Shu, et al.. Face recognition with 3D depth map in varied poses [J]. J Electronic Measurement and Instrument, 2011, 25(10): 870-878.
叶长明, 蒋建国, 詹曙, 等. 不同姿态人脸深度图识别的研究[J]. 电子测量与仪器学报, 2011, 25(10): 870-878.

【7】Yuan Weiqi, Xu Lu, Lin Zhonghua. Iris identification method based on gray surface matching [J]. Acta Optica Sinica, 2006, 26(10): 1537-1542.
苑玮琦, 徐露, 林忠华. 基于灰度曲面匹配的虹膜识别方法[J]. 光学学报, 2006, 26(10): 1537-1542.

【8】Han Min, Peng Yuhua, Zhang Shunli, et al.. Iris recognition based on empirical mode decomposition [J]. Acta Optica Sinica, 2010, 30(2): 364-368.
韩民, 彭玉华, 张顺利, 等. 基于经验模态分解的虹膜识别 [J]. 光学学报, 2010, 30(2): 364-368.

【9】K O M Goh, T B J Andrew. Design and implementation of a contactless palm vein recognition system [C]. Proceedings of the 2010 Symposium on Information and Communication Technology, 2010. 92-99.

【10】Zhang Huan, Hu Dewen. A palm vein recognition system [C]. International Conference on Intelligent Computation Technology and Automation, 2010, 1: 285-288.

【11】Pan Mi, Kang Wenxiong. Palm vein recognition based on three local invariant feature extraction algorithms [J]. Lecture Notes in Computer Science, 2011, 7098: 116-124.

【12】Zhou Yibo, Kumar A. Human identification using palm-vein images [J]. IEEE Trans Information Forensics and Security, 2011, 9(4): 1259-1274.

【13】Qiang Li, Yan′an Zeng, Xiaojun Peng, et al.. Curvelet-based palm vein biometric recognition [J]. Chin Opt Lett, 2010, 8(6): 577-579.

【14】J C Lee. A novel biometric system based on palm vein image [J]. Pattern Recognition Lett, 2012, 33(12): 1520-1528.

【15】Wang Jiangang, Yau Weiyun, Suwandy Andy, et al.. Fusion of palmprint and palm vein images for person recognition based on “Laplacianpalm” feature [J]. Pattern Recognition, 2008, 41(5): 1514-1527.

【16】Wu Wei, Yuan Weiqi, Lin Sen, et al.. Selection of typical wavelength for palm vein recognition [J]. Acta Optica Sinica, 2012, 32(12): 1211002.
吴微, 苑玮琦, 林森, 等. 手掌静脉识别典型波长选择[J]. 光学学报, 2012, 32(12): 1211002.

【17】Wu Wei, Yuan Weiqi, Lin Sen, et al.. Study of ROI selection and location for palm vein recognition [J]. J Optoelectronics·Laser, 2013, 24(1): 152-160.
吴微, 苑玮琦, 林森, 等. 手掌静脉识别中感兴趣区域的选择与定位研究 [J]. 光电子·激光, 2013, 24(1): 152-160.

【18】Zhang David, Guo Zhenhua, Lu Guangming, et al.. An online system of multispectral palmprint verification [J]. IEEE Trans Instrumentation and Measurement, 2010, 59(2): 480-490.

【19】Hao Ying, Sun Zhenan, Tan Tieniu, et al.. Multispectral palm image fusion for accurate contact-free palmprint recognition [C]. Proceedings of the Image Processing, 2008. 281-284.

【20】Lu Guangming, Zhang David, Wang Kuan Quan. Palmprint recognition using eigenpalms features [J]. Pattern Recognition Lett, 2003, 24(9-10): 1463-1467.

【21】Wu Xiangqian, Zhang Dapeng, Wang Kuanquan. Palmprint Recognition [M]. Beijing: Science Press, 2006. 9-10.
邬向前, 张大鹏, 王宽全. 掌纹识别技术[M]. 北京: 科学出版社, 2006. 9-10.

【22】Wang Huiwen, Wu Zaibin, Meng Jie, et al.. Linear and Non-Linear Method of Partial Least Squares [M]. Beijing: National Defense Industry Press, 2006. 150-155.
王惠文, 吴载斌, 孟洁, 等. 偏最小二乘回归的线性与非线性方法[M]. 北京: 国防工业出版社, 2006. 150-155.

引用该论文

Wu Wei,Yuan Weiqi,Lin Sen,Song Hui,Sang Haifeng. Fast Palm Vein Identification Algorithm Based on Grayscale Surface Matching[J]. Acta Optica Sinica, 2013, 33(10): 1015004

吴微,苑玮琦,林森,宋辉,桑海峰. 基于灰度曲面匹配的快速手掌静脉识别[J]. 光学学报, 2013, 33(10): 1015004

被引情况

【1】惠晓威,张俊宇,林森,常正英. 改进局部方向模式在掌脉识别中的应用. 激光与光电子学进展, 2015, 52(7): 71001--1

【2】徐天扬,惠晓威,林森. 基于小波灰度曲面的近红外手指静脉识别方法. 激光与光电子学进展, 2016, 53(4): 41005--1

【3】林森,徐天扬,王颖. 基于Gabor小波和NBP算法的手掌静脉识别. 激光与光电子学进展, 2017, 54(5): 51002--1

【4】吴微,林森,苑玮琦. 一种存储伪图像的手掌静脉识别研究. 光学学报, 2018, 38(4): 411007--1

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF