Mode control of electrically injected semiconductor laser with parity-tim...
Eight-channel hybrid-integrated laser array with 100 GHz channel spacing
Numerical simulation analysis of effect of energy band alignment and func...
Observation of nonreciprocal magnetophonon effect in nonencapsulated few-...
Electric Field Tuning of Interlayer Coupling in Noncentrosymmetric 3R-MoS...
Even-odd-dependent optical transitions of zigzag monolayer black phosphor...
Role of interfacial 2D graphene in high performance 3D graphene/germanium...
All-MBE grown InAs/GaAs quantum dot lasers with thin Ge buffer layer on S...
Effect of Processing Technique Factors on Structure and Photophysical Pro...
"Fast" Plasmons Propagating in Graphene Plasmonic Waveguides with Negativ...

### Adaptive Learning Gabor Filter for Finger-Vein Recognition

2020-11-19

Author(s): Zhang, YK (Zhang, Yakun); Li, WJ (Li, Weijun); Zhang, LP (Zhang, Liping); Ning, X (Ning, Xin); Sun, LJ (Sun, Linjun); Lu, YX (Lu, Yaxuan)

Source: IEEE ACCESS Volume: 7 Pages: 159821-159830 DOI: 10.1109/ACCESS.2019.2950698 Published: 2019

Abstract: Presently, finger-vein recognition is a new research direction in the field of biometric recognition. The Gabor filter has been extensively used for finger-vein recognition; however, its parameters are difficult to adjust. To solve this problem, an adaptive-learning Gabor filter is presented herein. We combine convolutional neural networks with a Gabor filter to calculate the gradient of the Gabor-filter parameters, based on the objective function, and to then optimize its parameters via back-propagation. The parameter $\theta$ of Gabor filter can be trained to the same angle as the vein texture of finger vein image. The parameter $\sigma$ of Gabor filter has a certain relation with $\lambda$ , and the parameter $\lambda$ of Gabor filter can converge to the optimal value well. Using this method, we not only select appropriate and effective Gabor filter parameters to design the filter banks, we also consider the relationship between those parameters. Finally, we perform experiments on four public finger-vein datasets. Experimental results demonstrate that our method outperforms state-of-the-art methods in finger-vein classification.

Accession Number: WOS:000497167600080

Author Identifiers:

Author        Web of Science ResearcherID        ORCID Number

Zhang, Yakun                  0000-0001-5829-1371

Ning, Xin                  0000-0001-7897-1673

ISSN: 2169-3536

##### 電話

010-82304210/010-82305052(傳真)

semi@semi.ac.cn