The increasing popularity of smartphones amongst the population laid the basis for a wide range of applications aimed at security and privacy protection. Very modern mobile devices have recently demonstrated the feasibility of using a camera sensor to access the system without typing any alphanumerical password. In this work, we present a method that implements iris recognition in the visible spectrum through unsupervised learning by means of Self Organizing Maps (SOM). The proposed method uses a SOM network to cluster iris features at pixel level. The discriminative feature map is obtained by using RGB data of the iris combined with the statistical descriptors of kurtosis and skewness. An experimental analysis on MICHE-I and UBIRISv1 datasets demonstrates the strengths and weaknesses of the algorithm, which has been specifically designed to require low processing power in compliance with the limited capability of common mobile devices.

Kurtosis and Skewness at pixel level as input for SOM networks to iris recognition on mobile devices

Silvio Barra;Luigi Gallo;Fabio Narducci
2017

Abstract

The increasing popularity of smartphones amongst the population laid the basis for a wide range of applications aimed at security and privacy protection. Very modern mobile devices have recently demonstrated the feasibility of using a camera sensor to access the system without typing any alphanumerical password. In this work, we present a method that implements iris recognition in the visible spectrum through unsupervised learning by means of Self Organizing Maps (SOM). The proposed method uses a SOM network to cluster iris features at pixel level. The discriminative feature map is obtained by using RGB data of the iris combined with the statistical descriptors of kurtosis and skewness. An experimental analysis on MICHE-I and UBIRISv1 datasets demonstrates the strengths and weaknesses of the algorithm, which has been specifically designed to require low processing power in compliance with the limited capability of common mobile devices.
2017
Istituto di Calcolo e Reti ad Alte Prestazioni - ICAR
Iris Recognition; Mobile Biometric Recognition; Unsupervised Learning; Statistical descriptors
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/20.500.14243/329470
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 17
  • ???jsp.display-item.citation.isi??? ND
social impact