Biometric recognition is often affected by low quality images. This is especially true in iris recognition fields, due to the fact that the area of the iris is quite small and wrong detection are very common when standard iris detection methods are used, like the Hough transform. In this paper, the iris quality assessment of over 1200 images is achieved, from three different datasets. The evaluation of the iris is done by using shallow learning techniques. Two different experiments have been carried out and the results obtained show good accuracy performance on the test sets.

Iris Quality Assessment: A Statistical Approach for Biometric Security Applications

Abate, Andrea F.;Barra, Silvio
;
Casanova, Andrea;Fenu, Gianni;Marras, Mirko
2018-01-01

Abstract

Biometric recognition is often affected by low quality images. This is especially true in iris recognition fields, due to the fact that the area of the iris is quite small and wrong detection are very common when standard iris detection methods are used, like the Hough transform. In this paper, the iris quality assessment of over 1200 images is achieved, from three different datasets. The evaluation of the iris is done by using shallow learning techniques. Two different experiments have been carried out and the results obtained show good accuracy performance on the test sets.
2018
978-3-030-01688-3
978-3-030-01689-0
File in questo prodotto:
File Dimensione Formato  
Iris Quality Assessment_A Statistical Approach for Biometric Security Applications.pdf

Solo gestori archivio

Tipologia: versione post-print
Dimensione 2.83 MB
Formato Adobe PDF
2.83 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

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/11584/265402
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 5
  • ???jsp.display-item.citation.isi??? ND
social impact