基于特征层和二代曲波变换的多模生物特征融合识别方法

许学斌 1; 张德运 1; 张新曼 1; 张铁登 2; 邓万宇 1

您当前的位置：

首页 >

文章列表页 >

基于特征层和二代曲波变换的多模生物特征融合识别方法

更新时间：2025-07-09

- 基于特征层和二代曲波变换的多模生物特征融合识别方法
- An Algorithm for Multimodal Biometric Recognition Based on Feature Level and the Second-Generation Curvelet Transform
- 西安交通大学学报 2009年43卷第10期页码：32-36
- 作者机构：
  
  西安交通大学电子与信息工程学院,西安,710049
- 作者简介：
- 基金信息：
  
  : 2009-02-17. 作者简介: 许学斌(1974-),男,博士生;张德运(联系人),男,教授,博士生导师. 基金项目: 国家高技术研究发展计划资助项目(2005AA121130);国家自然科学基金资助项目(60602025)
- DOI：
  中图分类号： TP391.41
- 网络首发：2009-10-10，
  
  纸质出版：2009
- 稿件说明：
移动端阅览
许学斌 1, 张德运 1, 张新曼 1, 等. 基于特征层和二代曲波变换的多模生物特征融合识别方法[J]. 西安交通大学学报, 2009,43(10):32-36.

An Algorithm for Multimodal Biometric Recognition Based on Feature Level and the Second-Generation Curvelet Transform[J]. 2009, 43(10): 32-36.
许学斌 1, 张德运 1, 张新曼 1, 等. 基于特征层和二代曲波变换的多模生物特征融合识别方法[J]. 西安交通大学学报, 2009,43(10):32-36. DOI：

An Algorithm for Multimodal Biometric Recognition Based on Feature Level and the Second-Generation Curvelet Transform[J]. 2009, 43(10): 32-36. DOI：

摘要

针对单模生物特征识别方法在实际应用中存在识别正确率较低的问题

提出了一种基于特征层和二代曲波变换的单样本多模生物特征融合识别方法

其采用了2种生物特征:掌纹特征和人脸特征.将所有归一化后的学习样本图像和测试图像通过组合的快速离散曲波变换和小波变换进行分解

系数经组合和规范化处理后

在特征层实现融合

融合后的特征参数送入K-最近邻分类器进行分类

从而获得最终识别结果.在香港理工大学掌纹数据库和Ljubljana大学人脸数据库上的实验结果表明

所提方法在每个类别仅使用1个学习样本的情况下

其生物特征图像的最佳平均识别正确率达到92.40%

比单模人脸、单模掌纹识别方法的识别率分别提高了35.38%和8.92%.

Abstract

A single sample biometric recognition approach is proposed based on the feature level and curvelet transform of the second-generation to improve the recognition rate of the single modal biometric system in application. Two kinds of biometric features are used. These are the palm-print feature and the face feature. All image samples are normalized and decomposed using the combination of curvelet & wavelet transform. Then the normalized curvelet & wavelet-transformed face and palm-print features are combined at the feature fusion level. The K-NN classifier is used to determine the final biometric classification

and then the recognition results are reported. The experimental results show that the proposed approach has better performance than the single modal solution: the best average recognition rate is improved to 92.40%

and the recognition rate is improved by 35.38% and 8.92% compared with single face feature and single palm-print feature respectively.

关键词

Keywords

references

JAIN A K. Biometric recognition [J]. Nature,2007,449(9): 38-40.

LU J, PLATANIOTIS K N, VENETSANOPOULOS A N. Face recognition using kernel direct discriminant analysis algorithms[J]. IEEE Trans on Neural Net, 2003, 14(1): 117-126.

JING Xiaoyuan, YAO Yongfang, ZHANG David. Face and palmprint pixel level fusion and kernel DCV-RBF classifier for small sample biometric recognition[J]. Pattern Recognition, 2007, 40(11): 3209-3224.

JAIN A K, NANDAKUMAR K, ROSS A. Score normalization in multimodal biometric systems[J]. Pattern Recognition, 2005, 38(12): 2270-2285.

YAO Yongfang, JING Xiaoyuan, WONG H S. Face and palmprint feature level fusion for single sample biometrics recognition[J]. Neurocomputing, 2007,70(5): 1582-1586.

CANDES E J, DEMANET L, DONOHO D L, et al. Fast discrete curvelet transforms, DMS01-40698 [R].Pasadena, CA, USA: California Institute of Technology, 2005:1-43.

LI Shutao, YANG Bin. Multifocus image fusion by combining curvelet and wavelet transform [J]. Pattern Recognition Letters, 2008, 29(2): 1295-1301.

许学斌, 张德运, 张新曼,等. 采用二代曲波变换和反向传播神经网络的人脸识别方法 [J].西安交通大学学报, 2008, 42(10): 1213-1216.

XU Xuebin, ZHANG Deyun, ZHANG Xinman, et,al. Method for face recognition using second generation curvelet transform and back propagation neural network [J]. Journal of Xi'an Jiaotong University, 2008, 42(10): 1213-1216.

MANDAL T, JONATHAN Q M, WU Yuanyuan. Curvelet based face recognition via dimension reduction[J].Signal Processing, 2009, 89(12): 2345-2353.

李晖晖, 郭雷, 刘航.基于二代Curvelet变换的图像融合研究 [J].光学学报, 2006, 26(5): 657-662.

LI Huihui, GUO Lei, LIU Hang. Research on image fusion based on the second generation curvelet transform [J]. Acta Optica Sinica, 2006, 26(5): 657-662.

杨镠, 郭宝龙, 倪伟. 基于区域特性的Contourlet域多聚焦图像融合算法 [J].西安交通大学学报, 2007, 41(4): 448-452.

YANG Liu, GUO Baolong, NI Wei. Multifocus image fusion algorithm based on region statistics in contourlet domain [J]. Journal of Xi'an Jiaotong University, 2007, 41(4): 448-452.

PERLIBAKAS V. Distance measures for PCA-based face recognition[J]. Pattern Recognition Letters, 2004, 25(6): 711-724.

SOLINA F, PEER P, BATAGELJ B, et al. Color-based face detection in the 15 seconds of fame art installation [C]∥Conference on Computer Vision/Computer Graphics Collaboration for Model-based Imaging, Rendering, Image Analysis and Graphical Special Effects. Rocquencourt, France:INRIA, 2003: 38-47.

JIA Wei, HUANG Deshuang, ZHANG David. Palmprint verification based on robust line orientation code[J]. Pattern Recognition, 2008, 41(5): 1504-1513.

KONG A, ZHANG D, KAMEL M. Three measures for secure palmprint identification [J]. Pattern Recognition, 2008, 41(4): 1329-1337.

基于区域特性的Contourlet域多聚焦图像融合算法.西安交通大学学报,2007,41(4):448-452.

一种Log Cabor滤波结合特征融合的虹膜识别方法.西安交通大学学报,2007,41(8):889-893.

结合对比度塔和克隆选择加权Wedgelets的图像融合.西安交通大学学报,2007,41(10):1170-1174.

基于异步航迹融合的乱序数据处理算法.西安交通大学学报,2008,42(4):458-461.

法向约束的多幅点云数据融合算法.西安交通大学学报,2009,43(5):71-75.

移动最小二乘增量式多视点云数据融合算法.西安交通大学学报,2009,43(9):46-50.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

采用二代曲波变换和反向传播神经网络的人脸识别方法

细粒度深度特征掩码估计的遮挡人脸识别算法

利用粒子群优化的人脸特征提取识别算法

一种快速的零空间算法

基于区域特性的Contourlet域多聚焦图像融合算法