华东师范大学学报（自然科学版） >

2015 , Vol. 2015 >Issue 3: 98 - 104

DOI: https://doi.org/10.3969/j.issn.1000-5641.2015.03.012

计算机科学

基于Curvelet稳定特征曲面的掌纹识别新方法

  • 申莎莎
展开
  • 运城学院 物理与电子工程系 山西 运城044000
申莎莎，女，博士，讲师，研究方向为图像信号处理. E-mail: ss728@163.com.

收稿日期: 2014-07-19

  网络出版日期: 2015-05-28

基金资助

深圳市重点实验室提升项目（CXB201105060068A）

收起

A novel palmprint recognition algorithm based on Curvelet invariant features of the surface

  • SHEN Sha-Sha
Expand

Received date: 2014-07-19

  Online published: 2015-05-28

Fold

摘要

针对掌纹特征提取困难、稳定性较差以及特征维数较大的问题，提出一种基于Curvelet稳定特征曲面的掌纹识别方法.将掌纹图像经Curvelet变换得到稳定特征曲面，把该曲面作为特征进行匹配，不仅避免了特征提取或图像编码等传统繁琐操作，而且特征维数较低，在保证识别精度的同时，图像稳定性增强，识别速度较快.最后，采用归一化相关分类器对掌纹所属类别进行判定，通过PolyU掌纹库的验证，本文算法的等误率为1.769 0%，匹配时间为16.6 ms，表明了本文算法的有效性.

关键词： 掌纹识别; Curvelet; 稳定特征曲面; 归一化相关分类器; FAR和FRR曲线分布图

本文引用格式

申莎莎 . 基于Curvelet稳定特征曲面的掌纹识别新方法[J]. 华东师范大学学报（自然科学版）, 2015 , 2015(3) : 98 -104 . DOI: 10.3969/j.issn.1000-5641.2015.03.012

Abstract

Corresponding to the problem of difficult feature extraction , poor stability and large characteristic dimension of palmprint, a novel palmprint recognition algorithm based on Curveletinvariant features of the surface is proposed.We can obtain the stable feature surface though Curvelet transform,which is used to match.This way not only simplifies the operation, such asfeature extraction, image coding and other traditional operation,but also has lower dimension, which leads tohigh stability and fast recognition speed with a high recognition accuracy at the same time. Finally, we use the normalized correlation classifier to measure the similarity. By PolyU palmprint database verification, the equal error rate of our algorithmis only 1.7690% and matching time is 16.6 ms, which demonstrates the effectiveness of the proposed algorithm.

Key words： palmprint recognition; Curvelet; invariant features of the surface; normalized correlation classifier; FAR and FRR curves

参考文献

1］KONG A, ZHANG D, KAMEL M. A survey of palmprint recognition ［J］. Pattern Recognition, 2009, 42(7):14081418.

［2］HONG D F, PAN Z K, WU X. Improved differential box counting with multiscale and multidirection: A new 〖JP2〗palmprint recognition method ［J］. OptikInternational Journal of Light Electron Optics, 2014, 125(15)：41544160.〖JP〗

［3］HONG D F, SU J, HONG Q G, et al. Blurred palmprint recognition based on stablefeature extraction using a VeseOsher decomposition model ［J］. PLOS ONE, 2014, 9(7): e101866.

［4］洪丹枫,潘振宽,苏健,等.VO图像分解模型的模糊掌纹识别方法［J］. 计算机辅助设计与图形学学报，2014, 26(10): 17371746.

［5］HONG D F, LIU W Q, SU J, et al. A novel hierarchical approach for multispectral palmprint recognition ［J］.Neurocomputing, 2015(151): 511521.

［6］MALATHI LATHA Y L,PRASAD M V N K. GLCM Based Texture Features for Palmprint Identification System［J］.Computational Intelligence in Data Mining, Volume 1; Smart Innovation, Systems and Technologies, 2015(31):155163.

［7］苑玮琦,范永刚,柯丽.基于灰度曲面匹配的掌纹识别方法［J］.光电子·激光,2009,20(6):807811.

［8］WANG X C, YUE K H, LIU Y M. Palmprint recognition based on curvelet transform decision fusion［J］. Procedia Engineering, 2011(23):303309.

［9］CANDES E J, DONOHO D L. CurveletsA surprisingly effective nonadaptive representation for objects with edges［M］//RABUT C, COHEN A, SCHUMAKER L L.Curves and Surface Fitting SaintMab.Nashville,TN:Vanderbilt University Press,1999.

［10］马猷.基于2DPCA的掌纹识别方法研究［D］. 广州:华南理工大学,2010.

［11］郭金玉, 苑玮琦.基于二维Fisher线性判别的掌纹识别方法［J］.计算机工程,2008,34(6):212213.

［12］赵志刚，吴鑫，洪丹枫，等.基于信息熵的GLBP掌纹识别算法研究［J］. 计算机科学，2013, 41(8): 293296.
Options
文章导航

/

〈 〉