Nowadays, many smartphones are provided with built-in sensors for the acquisition and the recognition of specific biometric traits of the user. This policy has been adopted since the massive use of such devices brought the user to store sensible data in them as well as effectuate sensitive transactions on-the-move. As a consequence, many biometric systems have been migrated from stand alone to mobile environments. The methodology proposed in the following presents an approach to the iris recognition in visible spectrum. Iris images are first enhanced by a fuzzy color/contrast preserving technique and then passed to a two-tier clustering: the first is based on the linear decomposition of the iris into superpixels; the second one exploits an unsupervised learning network model to built a feature vector of the iris. According to the performance obtained in terms of time and recognition rate, the method is compliant with the needs of real-time and in-movement environments.

Two-Tier Image Features Clustering for Iris Recognition on Mobile

Abate, Andrea F.;Narducci, Fabio
2016-01-01

Abstract

Nowadays, many smartphones are provided with built-in sensors for the acquisition and the recognition of specific biometric traits of the user. This policy has been adopted since the massive use of such devices brought the user to store sensible data in them as well as effectuate sensitive transactions on-the-move. As a consequence, many biometric systems have been migrated from stand alone to mobile environments. The methodology proposed in the following presents an approach to the iris recognition in visible spectrum. Iris images are first enhanced by a fuzzy color/contrast preserving technique and then passed to a two-tier clustering: the first is based on the linear decomposition of the iris into superpixels; the second one exploits an unsupervised learning network model to built a feature vector of the iris. According to the performance obtained in terms of time and recognition rate, the method is compliant with the needs of real-time and in-movement environments.
2016
978-3-319-52961-5
978-3-319-52962-2
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/11386/4719545
 Attenzione

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

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 6
  • ???jsp.display-item.citation.isi??? 3
social impact