Contactless Multispectral Palm-Vein Recognition With Lightweight Convolutional Neural Network
The development of information technology has made it possible to replace traditional keys and passwords with biometric recognition. Among the various human recognition technologies, contactless palm-vein authentication is becoming increasingly popular because it is hygienic and safe. In the field o...
Guardado en:
Autores principales: | , , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
IEEE
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/12db00b71822455498b214fba8d9d4e6 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:12db00b71822455498b214fba8d9d4e6 |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:12db00b71822455498b214fba8d9d4e62021-11-18T00:02:38ZContactless Multispectral Palm-Vein Recognition With Lightweight Convolutional Neural Network2169-353610.1109/ACCESS.2021.3124631https://doaj.org/article/12db00b71822455498b214fba8d9d4e62021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9597538/https://doaj.org/toc/2169-3536The development of information technology has made it possible to replace traditional keys and passwords with biometric recognition. Among the various human recognition technologies, contactless palm-vein authentication is becoming increasingly popular because it is hygienic and safe. In the field of deep learning (DL), system security and multispectral compatibility are crucial issues that require outright solutions. One of the most widely investigated DL algorithms is the convolutional neural network (CNN), which has been proven to have strong feature extraction capability. However, the training of CNN requires large samples and thus entails a heavy computational load, resulting in high hardware and software costs. Therefore, this paper proposes an adaptive Gabor filter with enhanced imaging features and triplet loss function that captures sufficient palm-vein data. A multispectral palm database from the CASIA public database was employed in this study to analyze the proposed system. The experimental results show that the proposed method has a low recognition error rate of 0.0556% and uses only a few network parameters in a multispectral environment.Yung-Yao ChenChih-Hsien HsiaPing-Han ChenIEEEarticleBiometricpalm-vein recognitionconvolutional neural networkstriplet loss functionhandcrafted featuresElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 149796-149806 (2021) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
Biometric palm-vein recognition convolutional neural networks triplet loss function handcrafted features Electrical engineering. Electronics. Nuclear engineering TK1-9971 |
spellingShingle |
Biometric palm-vein recognition convolutional neural networks triplet loss function handcrafted features Electrical engineering. Electronics. Nuclear engineering TK1-9971 Yung-Yao Chen Chih-Hsien Hsia Ping-Han Chen Contactless Multispectral Palm-Vein Recognition With Lightweight Convolutional Neural Network |
description |
The development of information technology has made it possible to replace traditional keys and passwords with biometric recognition. Among the various human recognition technologies, contactless palm-vein authentication is becoming increasingly popular because it is hygienic and safe. In the field of deep learning (DL), system security and multispectral compatibility are crucial issues that require outright solutions. One of the most widely investigated DL algorithms is the convolutional neural network (CNN), which has been proven to have strong feature extraction capability. However, the training of CNN requires large samples and thus entails a heavy computational load, resulting in high hardware and software costs. Therefore, this paper proposes an adaptive Gabor filter with enhanced imaging features and triplet loss function that captures sufficient palm-vein data. A multispectral palm database from the CASIA public database was employed in this study to analyze the proposed system. The experimental results show that the proposed method has a low recognition error rate of 0.0556% and uses only a few network parameters in a multispectral environment. |
format |
article |
author |
Yung-Yao Chen Chih-Hsien Hsia Ping-Han Chen |
author_facet |
Yung-Yao Chen Chih-Hsien Hsia Ping-Han Chen |
author_sort |
Yung-Yao Chen |
title |
Contactless Multispectral Palm-Vein Recognition With Lightweight Convolutional Neural Network |
title_short |
Contactless Multispectral Palm-Vein Recognition With Lightweight Convolutional Neural Network |
title_full |
Contactless Multispectral Palm-Vein Recognition With Lightweight Convolutional Neural Network |
title_fullStr |
Contactless Multispectral Palm-Vein Recognition With Lightweight Convolutional Neural Network |
title_full_unstemmed |
Contactless Multispectral Palm-Vein Recognition With Lightweight Convolutional Neural Network |
title_sort |
contactless multispectral palm-vein recognition with lightweight convolutional neural network |
publisher |
IEEE |
publishDate |
2021 |
url |
https://doaj.org/article/12db00b71822455498b214fba8d9d4e6 |
work_keys_str_mv |
AT yungyaochen contactlessmultispectralpalmveinrecognitionwithlightweightconvolutionalneuralnetwork AT chihhsienhsia contactlessmultispectralpalmveinrecognitionwithlightweightconvolutionalneuralnetwork AT pinghanchen contactlessmultispectralpalmveinrecognitionwithlightweightconvolutionalneuralnetwork |
_version_ |
1718425207400562688 |