Author(s): Zhang, LP (Zhang, Liping); Sun, LJ (Sun, Linjun); Li, WJ (Li, Weijun); Zhang, JM (Zhang, Jianming); Cai, WW (Cai, Weiwei); Cheng, CT (Cheng, Chuantong); Ning, X (Ning, Xin)

Source: IEEE SENSORS JOURNAL Volume: 22 Issue: 1 Pages: 785-794 DOI: 10.1109/JSEN.2021.3130951 Published: JAN 1 2022

Abstract: Finger vein recognition has attracted considerable attention from the biometric identification technology community owing to its convenience and security. Unlike most previous works only pay attention to one part of finger vein recognition, we propose a joint Bayesian framework in this paper, which is based on partial least squares discriminant analysis (PLS-DA). It involves three major stages: 1) robust feature description, 2) discriminative feature mapping, and 3) separative verification. In stage 1), we extract line responses and orientation of finger veins using a bank of Gabor filter, and histograms are constructed in local patches as primitive features. Subsequently, in stage 2), a discriminant feature mapping based the PLS-DA (PLS-DA-FM) method is proposed to project these primitive features into low-dimensional forms in a supervised manner. Thus, highly compact and discriminative features are obtained in this stage. Finally, in stage 3), we directly build a Bayesian model based on the joint distribution of finger vein feature pairs to measure the similarity between the features. Extensive experiments on five finger vein datasets demonstrate the superior performance of the proposed method to most state-of-the-art finger vein recognition methods.

Accession Number: WOS:000735528200087

Author Identifiers:

Author Web of Science ResearcherID ORCID Number

Cai, Weiwei AAH-5456-2020 0000-0001-6795-6152

Ning, Xin M-9479-2018 0000-0001-7897-1673

ISSN: 1530-437X

eISSN: 1558-1748

Full Text: https://ieeexplore.ieee.org/document/9627706