基于细节特征点的掌纹比对算法及GPU加速

doi:10.7523/j.issn.2095-6134.2015.04.021

中国科学院大学学报 ›› 2015, Vol. 32 ›› Issue (4): 571-576.DOI: 10.7523/j.issn.2095-6134.2015.04.021

• 计算机科学 • 上一篇

基于细节特征点的掌纹比对算法及GPU加速

吴春生^1,2,3, 冯才刚¹, 迟学斌²

1. 北京市刑事科学技术研究所, 北京 100054;
2. 中国科学院计算机网络信息中心, 北京 100190;
3. 中国科学院大学, 北京 100190

收稿日期:2014-12-22 修回日期:2015-03-11 发布日期:2015-07-15
通讯作者: 吴春生
基金资助:
北京市科技计划(Z121100000312099)资助

Palmprint matching algorithm based on minutia feature points and GPU application

WU Chunsheng^1,2,3, FENG Caigang¹, CHI Xuebin²

1. Beijing Criminal Science Institution, Beijing 100054, China;
2. Computer Network Information Center, Chinese Academy of Sciences, Beijing 100190, China;
3. University of Chinese Academy of Sciences, Beijing 100190, China

Received:2014-12-22 Revised:2015-03-11 Published:2015-07-15

摘要/Abstract

摘要： 针对当前公安机关在掌纹识别应用中存在的掌纹库容量大和现场掌纹质量差等问题,首先对掌纹特征点匹配算法的计算复杂度进行分析,根据分析结果提出特征点的三级比对算法;然后详细介绍三级比对算法的工作流程;对算法进行GPU并行化改造;最后给出测试结果.首次将GPU计算技术应用于掌纹识别之中.文中掌纹特征比对方法相比现有同类掌纹识别速度提高3倍左右,经过GPU加速后可进一步提升比对速度15倍以上.

关键词: 掌纹识别, 细节特征点, GPU

Abstract: The problems of palmprint application in public security department, such as large database and poor quality of scene palmprint, are described in this paper. Firstly, the computational complexity of palmprint feature point matching algorithm is analyzed. The three-level feature point matching algorithm is presented based on the results of the analysis. Secondly, the working process of three-level feature point matching algorithm is described in detail. Finally the algorithm is transformed to the GPU parallel and the test results are given. The GPU technology is first applied to palmprint recognition in our study. The results show that the speed of palmprint feature matching increases about three times compared with others, and the speed may increase more than 15 times after using GPU technology.

Key words: palmprint recognition, minutia feature point, GPU

中图分类号:

TP391.41

吴春生, 冯才刚, 迟学斌. 基于细节特征点的掌纹比对算法及GPU加速[J]. 中国科学院大学学报, 2015, 32(4): 571-576.

WU Chunsheng, FENG Caigang, CHI Xuebin. Palmprint matching algorithm based on minutia feature points and GPU application[J]. , 2015, 32(4): 571-576.

参考文献

[1] 郑艳. 脱机掌纹图像处理方法研究 [D]. 天津: 南开大学, 2008.
[2] 袁国武,魏骁勇,徐丹. 基于掌纹的身份鉴别[J]. 计算机辅助设计与图形学学报, 2005, 17(12): 2 590-2 595.
[3] 岳峰, 左旺孟, 张大鹏. 掌纹识别算法综述[J]. 自动化学报, 2010, 36(3): 353-365.
[4] 于为民, 赵继印,李敏, 等. 全手形特征的生物识别技术综述[J].大连民族学院学报, 2012, 14(1): 19-23.
[5] Zheng Y S, Guang S W, Qing R, et al. Location of special areas on palmprint [C]//Image and Signal Processing 2008. 2008: 786-791
[6] Zheng Y S, Guang S, Zhang L, et al. Research on offline palmprint enhancement [C]//Image Processing, ICIP 2007. IEEE International Conference on, 2007: 541-544.
[7] 高欣,刘重晋,封举富. 一种自适应的T型结构掌纹分区算法[J]. 计算机辅助设计与图形学学报, 2011, 23(9): 1 463-1 467.
[8] Connie T, Jin A T B, Ong Michael G K, et al. An automated palmprint recognition system[J]. Image and Vision computing, 2005, 23(5): 501-515.
[9] Zhang D, Guo Z H, Lu G M, et al. Online joint palmprint and palmvein verification[J]. Expert Systems with Applications, 2011, 38(3): 2 621-2 631.
[10] Zhang D, Lu G M, Kong A, et al. Online palmprint identification system for civil applications[J]. Journal of Computer Science and Technology, 2005, 20(1): 70-76.
[11] Zhang D, Kong W K, You J, et al. Online palmprint identification [C]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2003, 25(9): 1 041-1 050.
[12] Wang X, Lei L, Wang M Z. Palmprint verification based on 2D-Gabor wavelet and pulse-coupled neural network[J]. Knowledge-Based Systems, 2012, 27: 451- 455.
[13] Nibouche O, Jiang J, Trundle P. Analysis of performance of palmprint matching with enforced sparsity[J]. Digital Signal Processing, 2012, 22: 348-355.
[14] 谭泽超. 脱机掌纹提取与比对算法研究 [D]. 天津: 南开大学, 2010.
[15] Galton. NSTC Subcommittee on Biometrics [N/OL].(2009) [2014-12-01]. http://www.bi omemcscatalog.org.
[16] Jain A K, Feng J J. Latent palmprint matching [C]//IEEE trans. PAMI, 2009, 31(6):1 032-1 047.
[17] GA 774.5—2008.指纹特征规范(第5部分:指纹细节特征点标注方法)[S].北京:中国标准出版社,2008.
[18] Zhang D P, Shu W. Two novel charactefistics in palmpritit verification:datum point invariance and line feature matching[J]. Pattem Recognition, 1999, 32:691-702
[19] 史广顺,梁倩,谭泽超. 高分辨率脱机掌纹比对算法研究 [C]//全国模式识别学术会议论文集, 2010:809-813.

基于细节特征点的掌纹比对算法及GPU加速

Palmprint matching algorithm based on minutia feature points and GPU application

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 4

编辑推荐

Metrics

本文评价

访问统计

联系我们

[1]	郭长顺, 范湘涛, 谭剑, 詹勤, 亢叙杰. 基于虚拟地球的电离层电子密度时空多维可视化方法[J]. 中国科学院大学学报, 2019, 36(6): 817-824.
[2]	顾久祥, 杨仁忠, 石璐, 韦宏卫. 基于GPU的HJ-1C实时成像处理技术[J]. 中国科学院大学学报, 2014, 31(5): 708-713.
[3]	吴春生, 冯才刚, 迟学斌. 刑侦领域高分辨率掌纹识别技术及快速匹配方法[J]. 中国科学院大学学报, 2014, 31(4): 555-563.
[4]	钱权, 朱伟, 车弘毅, 张瑞. 改进的多模式串匹配算法及GPU并行化研究[J]. 中国科学院大学学报, 2013, 30(5): 706-712.