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. - 11161:(2018), pp. 270-278. (Intervento presentato al convegno 10th International Symposium on Cyberspace Safety and Security, CSS 2018 tenutosi a Amalfi, Italy nel October 29–31, 2018) [10.1007/978-3-030-01689-0_21].
Iris Quality Assessment: A Statistical Approach for Biometric Security Applications
Barra, Silvio;
2018
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.| File | Dimensione | Formato | |
|---|---|---|---|
|
Iris Quality Assessment_A Statistical Approach for Biometric Security Applications.pdf
non disponibili
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.
