Feature level fusion of fingerprint and finger vein biometrics

Authors:
Kunming Lin;Fengling Han;Yongming Yang;Zulong Zhang
Affiliations:
State Key Laboratory of Power Transmission Equipment & System Security and New Technology, Chongqing University, Chongqing, China;School of Computer Science and IT, RMIT University, Melbourne, Australia;State Key Laboratory of Power Transmission Equipment & System Security and New Technology, Chongqing University, Chongqing, China;State Key Laboratory of Power Transmission Equipment & System Security and New Technology, Chongqing University, Chongqing, China
Venue:
ICSI'11 Proceedings of the Second international conference on Advances in swarm intelligence - Volume Part II
Year:
2011

Citing 7
Cited 1

Integrating Faces and Fingerprints for Personal Identification

IEEE Transactions on Pattern Analysis and Machine Intelligence
Information fusion in biometrics

Pattern Recognition Letters - Special issue: Audio- and video-based biometric person authentication (AVBPA 2001)
Multibiometric systems

Communications of the ACM - Multimodal interfaces that flex, adapt, and persist
Handbook of Fingerprint Recognition

Handbook of Fingerprint Recognition
Human Authentication Using Face and Fingerprint Biometrics

CICSYN '10 Proceedings of the 2010 2nd International Conference on Computational Intelligence, Communication Systems and Networks
A Comparative Study of Fingerprint Image-Quality Estimation Methods

IEEE Transactions on Information Forensics and Security
Filterbank-based fingerprint matching

IEEE Transactions on Image Processing

A robust face and ear based multimodal biometric system using sparse representation

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

The aim is to study the fusion at feature extraction level for fingerprint and finger vein biometrics. A novel dynamic weighting matching algorithm based on quality evaluation of interest features is proposed. First, fingerprint and finger vein images are preprocessed by filtering, enhancement, gray-scale normalization and etc. The effective feature point-sets are extracted from two model sources. To handle the problem of curse of dimension, neighborhood elimination and reservation of points belonging to specific regions are implemented, prior and after the feature point-sets fusion. Then, according to the results of features evaluation, dynamic weighting strategy is introduction for the fusion biometrics. Finally, the fused feature point-sets for the database and the query images are matched using point pattern matching and the proposed weight matching algorithm. Experimental results based on FVC2000 and self-constructed finger vein databases show that our scheme can improve verification performance and security significantly.