TY - JOUR
T1 - A Comparative Study of Cross-Device Finger Vein Recognition Using Classical and Deep Learning Approaches
AU - Arıcan, Tuğçe
AU - Veldhuis, Raymond
AU - Spreeuwers, Luuk
AU - Bergeron, Loïc
AU - Busch, Christoph
AU - Jalilian, Ehsaneddin
AU - Kauba, Christof
AU - Kirchgasser, Simon
AU - Marcel, Sébastien
AU - Prommegger, Bernhard
AU - Raja, Kiran
AU - Ramachandra, Raghavendra
AU - Uhl, Andreas
N1 - Publisher Copyright:
© 2024 Tuğçe Arıcan et al.
PY - 2024/3/25
Y1 - 2024/3/25
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85197866691&partnerID=8YFLogxK
U2 - 10.1049/2024/3236602
DO - 10.1049/2024/3236602
M3 - Article
AN - SCOPUS:85197866691
SN - 2047-4938
VL - 2024
JO - IET biometrics
JF - IET biometrics
M1 - 3236602
ER -