Iris recognition

Emine Krichen; Bernadette Dorizzi; Zhenan Sun; Sonia Garcia-Salicetti

doi:10.1007/978-1-84800-292-0_3

Iris recognition

Emine Krichen
, Bernadette Dorizzi
, Zhenan Sun
, Sonia Garcia-Salicetti

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

Abstract

Recognizing persons from their irises is not straightforward as different types of noise can be present in the image. Indeed, the iris is located behind the cornea, which is a highly reflective mirror; the resulting images could therefore be perturbed by illumination reflections. The iris is also covered by eyelids in both its upper and lower parts and partially by eyelashes. This noise is very hard to detect as it has a random form and location. Blur can also be present in the images in case of non controlled acquisition conditions. In this chapter, the state of the art in iris recognition research is presented. In order to allow future benchmarking, a new modular reference system called OSIRIS (Open Source for IRIS) based on Daugman's works is described. Our experiments show that the recognition module of OSIRISv1.0 outperforms Masek, another open-source software. We have defined a benchmarking protocol on a multicultural-European and Chinese-iris database and compared OSIRISv1.0, Masek and two other research systems using this benchmarking framework.

Original language	English
Title of host publication	Guide to Biometric Reference Systems and Performance Evaluation
Publisher	Springer London
Pages	25-49
Number of pages	25
ISBN (Print)	9781848002913
DOIs	https://doi.org/10.1007/978-1-84800-292-0_3
Publication status	Published - 1 Dec 2009

Access to Document

10.1007/978-1-84800-292-0_3

Cite this

@inbook{f75bfc54f6ed4c58b626563260abd870,

title = "Iris recognition",

abstract = "Recognizing persons from their irises is not straightforward as different types of noise can be present in the image. Indeed, the iris is located behind the cornea, which is a highly reflective mirror; the resulting images could therefore be perturbed by illumination reflections. The iris is also covered by eyelids in both its upper and lower parts and partially by eyelashes. This noise is very hard to detect as it has a random form and location. Blur can also be present in the images in case of non controlled acquisition conditions. In this chapter, the state of the art in iris recognition research is presented. In order to allow future benchmarking, a new modular reference system called OSIRIS (Open Source for IRIS) based on Daugman's works is described. Our experiments show that the recognition module of OSIRISv1.0 outperforms Masek, another open-source software. We have defined a benchmarking protocol on a multicultural-European and Chinese-iris database and compared OSIRISv1.0, Masek and two other research systems using this benchmarking framework.",

author = "Emine Krichen and Bernadette Dorizzi and Zhenan Sun and Sonia Garcia-Salicetti",

year = "2009",

month = dec,

day = "1",

doi = "10.1007/978-1-84800-292-0\_3",

language = "English",

isbn = "9781848002913",

pages = "25--49",

booktitle = "Guide to Biometric Reference Systems and Performance Evaluation",

publisher = "Springer London",

}

TY - CHAP

T1 - Iris recognition

AU - Krichen, Emine

AU - Dorizzi, Bernadette

AU - Sun, Zhenan

AU - Garcia-Salicetti, Sonia

PY - 2009/12/1

Y1 - 2009/12/1

N2 - Recognizing persons from their irises is not straightforward as different types of noise can be present in the image. Indeed, the iris is located behind the cornea, which is a highly reflective mirror; the resulting images could therefore be perturbed by illumination reflections. The iris is also covered by eyelids in both its upper and lower parts and partially by eyelashes. This noise is very hard to detect as it has a random form and location. Blur can also be present in the images in case of non controlled acquisition conditions. In this chapter, the state of the art in iris recognition research is presented. In order to allow future benchmarking, a new modular reference system called OSIRIS (Open Source for IRIS) based on Daugman's works is described. Our experiments show that the recognition module of OSIRISv1.0 outperforms Masek, another open-source software. We have defined a benchmarking protocol on a multicultural-European and Chinese-iris database and compared OSIRISv1.0, Masek and two other research systems using this benchmarking framework.

AB - Recognizing persons from their irises is not straightforward as different types of noise can be present in the image. Indeed, the iris is located behind the cornea, which is a highly reflective mirror; the resulting images could therefore be perturbed by illumination reflections. The iris is also covered by eyelids in both its upper and lower parts and partially by eyelashes. This noise is very hard to detect as it has a random form and location. Blur can also be present in the images in case of non controlled acquisition conditions. In this chapter, the state of the art in iris recognition research is presented. In order to allow future benchmarking, a new modular reference system called OSIRIS (Open Source for IRIS) based on Daugman's works is described. Our experiments show that the recognition module of OSIRISv1.0 outperforms Masek, another open-source software. We have defined a benchmarking protocol on a multicultural-European and Chinese-iris database and compared OSIRISv1.0, Masek and two other research systems using this benchmarking framework.

UR - https://www.scopus.com/pages/publications/70450209665

U2 - 10.1007/978-1-84800-292-0_3

DO - 10.1007/978-1-84800-292-0_3

M3 - Chapter

AN - SCOPUS:70450209665

SN - 9781848002913

SP - 25

EP - 49

BT - Guide to Biometric Reference Systems and Performance Evaluation

PB - Springer London

ER -

Iris recognition

Abstract

Access to Document

Other files and links

Fingerprint

Cite this