全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...
电子学报  2008 

基于多尺度序列谱核半定规划优化的签名认证方法

, PP. 44-49

Keywords: 半定规划,序列谱核,签名认证

Full-Text   Cite this paper   Add to My Lib

Abstract:

变化尺度进行签名序列的相似性描述有利于获得更准确的相似性描述结果.本文定义了签名序列的变化尺度的谱核矩阵,在多个尺度的核变换空间上进行序列的相似性描述,并利用半定规划对多尺度谱核矩阵进行优化,结合支持向量机建立起一种能够自动优化签名序列多尺度相似性描述的认证方法.该方法能够适应不同个人的签名特点,克服统一尺度下相似性描述的缺陷,提高签名序列相似性描述的准确性,在相同签名数据集上的实验结果显示该方法可以获得更高的认证准确率.

References

[1]  Impedovo D,Pirlo G.Automatic signature verification:the state of art[J].IE Trans on SMC-Part C:Application and Reviews,2008,38(5):609-635.
[2]  邱德红,陈传波,等.局域动态特征弯曲校正和作用均衡签名认证方法[J].小型微型计算机系统,2006,27(10):1957-1960.Qiu De-hong,Chert Chuan-bo,et al.Signature verification based on characteristic parts of signing signal through warp rectifying and effect balancing[J],Mini-Micro Systems,2006,27 (10):1957-1960.(in Chinese)
[3]  Hu L,Wang Y H.On-line signature verification based on fusion of global and local information[A].in Proc ICWAPR''07[C].Beijing,China,2007.3:1192-1196.
[4]  Qiu D H,Chen C B,et al.Machine learning approaches for robust and high performance sign_atom verification[J].Journal of Computational Information Systems,2006,2(3):933-938.
[5]  Fierrez J,Ortega-Garcia J,et al.HMM-based on-line signature verification:feature extraction and signature modeling[J].Pattern.Recognition Letters,2(X)7,28(12):2325-2334.
[6]  Zhang D Q,Chen S C,et al.Learning the kernel parameters in kernel minimum distance classifier[J].Pattern Recognition.2006,39(1):133-135.
[7]  Stephen B,Lieven V.Convex Optimization[M],Cambridge University Press,2004.
[8]  Scholkopf B,Smola A J.Learning with Kernels-Support Vector Machines:Regularization,Optimization and Beyond[M].Cambridge,Massachusetts:MIT Press,2002.
[9]  Labit Y,Peaucelle D,et al.SeDuMi Interface 1.02:a tool for solving LMI problems with SeDuMi[A].in Proc IEEE CACSD[C].Glasgow,UK,2002.272-277.
[10]  Prabhakar S,Kittler J,et al.Special issue on biometrics:progress and directions[J].IEEE Trans on PAMI,2007,29 (4):513-516.
[11]  邱德红,陈传波,等.非线性局部寻优时间弯曲校正及签名特征空间稳定性研究[J].计算机研究与发展,2002,39(10):1227-1232.Qiu De-hong,Chen Chuan-bo,et al.A study of the stability of signature features by nonlinear local optimal time warping[J].Journal of Computer Research and Development,2002,39 (10):1227-1232.(in Chinese)
[12]  Mario E M,Pietro P,Visual identification by signature tracking[J].IEEE Trans on PAMI,2003,25(2):200-217.
[13]  Quan Z H,Huang D S,et al.A hybrid HMM/ANN based approach for online signature verification[A].in Proc IJCNN[C].Orlando,FL,2(X)7,402-405.
[14]  Wan L,Wan B,et al.On-line signature verification with twostage statistical models[A],in Proc 8th ICDAR[C].Seoul,South Korea,2005.1:282-286.
[15]  Lanckriet G R G,Cristianini N,et al.Learning the kernel matrix with semidefinite programming[J].Journal of Machine Learning Research,2004,5:27-72.
[16]  Ye J P,Ji S W,et al.Learning the kernel matrix in discriminant analysis via quadratically constrained quadratic programming[A].in Proc 13th ACM SIGKDD KDD[C].San Jose,California,USA,2007.854-863.
[17]  Christina S,Leslie C,et al.Fast string kernels using inexact matching for protein sequences[J].Journal of Machine Learn
[18]  Pólik 1,Terlaky T,et al.SeDuMi:a package for conic optimization[EB/OL].http://imre,polik,googlepages,com/SeDuMi_IMA_poster,pdf
[19]  Antoniou A,Lu W S.Practical optimization:algorithms and engineering applications[M].Springer,2007.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133