Biometric recognition systems based on 3D information of palmprint have been experimented with in the last years. Optical technology is the most widely used, but it provides information on the external surface only. Ultrasound, instead, allows obtaining information that accounts for principal lines depth. In this work, a 3D palmprint recognition system, based on images acquired through an Ultrasound system by using water or gel as a coupling medium between the probe and hand, is proposed and tested. In both cases, a 3D template that contains information on the depth of principal lines is generated by combining 2D templates obtained from images extracted at various under-skin depths. The performances of the system have been evaluated through verification and identification experiments on home-made databases of 633 water samples and 423 gel samples, respectively. For both cases, the 3D method reports better results than the 2D one. Furthermore, the recognition capability of the proposed system is comparable with that of the best optical system reported in the literature.

3D Palmprint Recognition Through Ultrasound Imaging

Antonio Iula
;
Monica Micucci
2023-01-01

Abstract

Biometric recognition systems based on 3D information of palmprint have been experimented with in the last years. Optical technology is the most widely used, but it provides information on the external surface only. Ultrasound, instead, allows obtaining information that accounts for principal lines depth. In this work, a 3D palmprint recognition system, based on images acquired through an Ultrasound system by using water or gel as a coupling medium between the probe and hand, is proposed and tested. In both cases, a 3D template that contains information on the depth of principal lines is generated by combining 2D templates obtained from images extracted at various under-skin depths. The performances of the system have been evaluated through verification and identification experiments on home-made databases of 633 water samples and 423 gel samples, respectively. For both cases, the 3D method reports better results than the 2D one. Furthermore, the recognition capability of the proposed system is comparable with that of the best optical system reported in the literature.
2023
978-3-031-08135-4
978-3-031-08136-1
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11563/162608
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact