A Comparative Study of Cross-Device Finger Vein Recognition Using Classical and Deep Learning Approaches

Finger vein recognition is gaining popularity in the field of biometrics, yet the inter-operability of finger vein patterns has received limited attention. This study aims to fill this gap by introducing a cross-device finger vein dataset and evaluating the performance of finger vein recognition acr...

Full description

Saved in:
Bibliographic Details
Main Authors: Tuğçe Arıcan, Raymond Veldhuis, Luuk Spreeuwers, Loïc Bergeron, Christoph Busch, Ehsaneddin Jalilian, Christof Kauba, Simon Kirchgasser, Sébastien Marcel, Bernhard Prommegger, Kiran Raja, Raghavendra Ramachandra, Andreas Uhl
Format: Article
Language:English
Published: Wiley 2024-01-01
Series:IET Biometrics
Online Access:http://dx.doi.org/10.1049/2024/3236602
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832548308078297088
author Tuğçe Arıcan
Raymond Veldhuis
Luuk Spreeuwers
Loïc Bergeron
Christoph Busch
Ehsaneddin Jalilian
Christof Kauba
Simon Kirchgasser
Sébastien Marcel
Bernhard Prommegger
Kiran Raja
Raghavendra Ramachandra
Andreas Uhl
author_facet Tuğçe Arıcan
Raymond Veldhuis
Luuk Spreeuwers
Loïc Bergeron
Christoph Busch
Ehsaneddin Jalilian
Christof Kauba
Simon Kirchgasser
Sébastien Marcel
Bernhard Prommegger
Kiran Raja
Raghavendra Ramachandra
Andreas Uhl
author_sort Tuğçe Arıcan
collection DOAJ
description Finger vein recognition is gaining popularity in the field of biometrics, yet the inter-operability of finger vein patterns has received limited attention. This study aims to fill this gap by introducing a cross-device finger vein dataset and evaluating the performance of finger vein recognition across devices using a classical method, a convolutional neural network, and our proposed patch-based convolutional auto-encoder (CAE). The findings emphasise the importance of standardisation of finger vein recognition, similar to that of fingerprints or irises, crucial for achieving inter-operability. Despite the inherent challenges of cross-device recognition, the proposed CAE architecture in this study demonstrates promising results in finger vein recognition, particularly in the context of cross-device comparisons.
format Article
id doaj-art-068612a31caa4ac587a134935dda2508
institution Kabale University
issn 2047-4946
language English
publishDate 2024-01-01
publisher Wiley
record_format Article
series IET Biometrics
spelling doaj-art-068612a31caa4ac587a134935dda25082025-02-03T06:14:53ZengWileyIET Biometrics2047-49462024-01-01202410.1049/2024/3236602A Comparative Study of Cross-Device Finger Vein Recognition Using Classical and Deep Learning ApproachesTuğçe Arıcan0Raymond Veldhuis1Luuk Spreeuwers2Loïc Bergeron3Christoph Busch4Ehsaneddin Jalilian5Christof Kauba6Simon Kirchgasser7Sébastien Marcel8Bernhard Prommegger9Kiran Raja10Raghavendra Ramachandra11Andreas Uhl12Faculty of Electrical EngineeringFaculty of Electrical EngineeringFaculty of Electrical EngineeringDepartment of Computer ScienceDepartment of Computer ScienceDepartment of Computer SciencesDepartment of Computer SciencesDepartment of Computer SciencesIDIAP Research InstituteDepartment of Computer SciencesDepartment of Computer ScienceDepartment of Computer ScienceDepartment of Computer SciencesFinger vein recognition is gaining popularity in the field of biometrics, yet the inter-operability of finger vein patterns has received limited attention. This study aims to fill this gap by introducing a cross-device finger vein dataset and evaluating the performance of finger vein recognition across devices using a classical method, a convolutional neural network, and our proposed patch-based convolutional auto-encoder (CAE). The findings emphasise the importance of standardisation of finger vein recognition, similar to that of fingerprints or irises, crucial for achieving inter-operability. Despite the inherent challenges of cross-device recognition, the proposed CAE architecture in this study demonstrates promising results in finger vein recognition, particularly in the context of cross-device comparisons.http://dx.doi.org/10.1049/2024/3236602
spellingShingle Tuğçe Arıcan
Raymond Veldhuis
Luuk Spreeuwers
Loïc Bergeron
Christoph Busch
Ehsaneddin Jalilian
Christof Kauba
Simon Kirchgasser
Sébastien Marcel
Bernhard Prommegger
Kiran Raja
Raghavendra Ramachandra
Andreas Uhl
A Comparative Study of Cross-Device Finger Vein Recognition Using Classical and Deep Learning Approaches
IET Biometrics
title A Comparative Study of Cross-Device Finger Vein Recognition Using Classical and Deep Learning Approaches
title_full A Comparative Study of Cross-Device Finger Vein Recognition Using Classical and Deep Learning Approaches
title_fullStr A Comparative Study of Cross-Device Finger Vein Recognition Using Classical and Deep Learning Approaches
title_full_unstemmed A Comparative Study of Cross-Device Finger Vein Recognition Using Classical and Deep Learning Approaches
title_short A Comparative Study of Cross-Device Finger Vein Recognition Using Classical and Deep Learning Approaches
title_sort comparative study of cross device finger vein recognition using classical and deep learning approaches
url http://dx.doi.org/10.1049/2024/3236602
work_keys_str_mv AT tugcearıcan acomparativestudyofcrossdevicefingerveinrecognitionusingclassicalanddeeplearningapproaches
AT raymondveldhuis acomparativestudyofcrossdevicefingerveinrecognitionusingclassicalanddeeplearningapproaches
AT luukspreeuwers acomparativestudyofcrossdevicefingerveinrecognitionusingclassicalanddeeplearningapproaches
AT loicbergeron acomparativestudyofcrossdevicefingerveinrecognitionusingclassicalanddeeplearningapproaches
AT christophbusch acomparativestudyofcrossdevicefingerveinrecognitionusingclassicalanddeeplearningapproaches
AT ehsaneddinjalilian acomparativestudyofcrossdevicefingerveinrecognitionusingclassicalanddeeplearningapproaches
AT christofkauba acomparativestudyofcrossdevicefingerveinrecognitionusingclassicalanddeeplearningapproaches
AT simonkirchgasser acomparativestudyofcrossdevicefingerveinrecognitionusingclassicalanddeeplearningapproaches
AT sebastienmarcel acomparativestudyofcrossdevicefingerveinrecognitionusingclassicalanddeeplearningapproaches
AT bernhardprommegger acomparativestudyofcrossdevicefingerveinrecognitionusingclassicalanddeeplearningapproaches
AT kiranraja acomparativestudyofcrossdevicefingerveinrecognitionusingclassicalanddeeplearningapproaches
AT raghavendraramachandra acomparativestudyofcrossdevicefingerveinrecognitionusingclassicalanddeeplearningapproaches
AT andreasuhl acomparativestudyofcrossdevicefingerveinrecognitionusingclassicalanddeeplearningapproaches
AT tugcearıcan comparativestudyofcrossdevicefingerveinrecognitionusingclassicalanddeeplearningapproaches
AT raymondveldhuis comparativestudyofcrossdevicefingerveinrecognitionusingclassicalanddeeplearningapproaches
AT luukspreeuwers comparativestudyofcrossdevicefingerveinrecognitionusingclassicalanddeeplearningapproaches
AT loicbergeron comparativestudyofcrossdevicefingerveinrecognitionusingclassicalanddeeplearningapproaches
AT christophbusch comparativestudyofcrossdevicefingerveinrecognitionusingclassicalanddeeplearningapproaches
AT ehsaneddinjalilian comparativestudyofcrossdevicefingerveinrecognitionusingclassicalanddeeplearningapproaches
AT christofkauba comparativestudyofcrossdevicefingerveinrecognitionusingclassicalanddeeplearningapproaches
AT simonkirchgasser comparativestudyofcrossdevicefingerveinrecognitionusingclassicalanddeeplearningapproaches
AT sebastienmarcel comparativestudyofcrossdevicefingerveinrecognitionusingclassicalanddeeplearningapproaches
AT bernhardprommegger comparativestudyofcrossdevicefingerveinrecognitionusingclassicalanddeeplearningapproaches
AT kiranraja comparativestudyofcrossdevicefingerveinrecognitionusingclassicalanddeeplearningapproaches
AT raghavendraramachandra comparativestudyofcrossdevicefingerveinrecognitionusingclassicalanddeeplearningapproaches
AT andreasuhl comparativestudyofcrossdevicefingerveinrecognitionusingclassicalanddeeplearningapproaches