Paper Info
Title
A fast adaboosting based method for iris and pupil contour detection
Abstract
The iris localization plays a fundamental role in the recognition process because the speed and performance of the iris recognition system largely depends on the quality of the pupil and iris detection. This process includes the detection of inner (pupil) and outer (iris) boundaries. In this paper we present a new method for iris and pupil boundaries detection based on Adaboosting technique for localization of circular objects and an algorithm based on the elements of analytic geometry, in particular, the determination of the bounded circumference of a tangential square that encloses the pupil and iris. The proposed approach overcomes the limitations that had previous methods regarding the use of images obtained under not controlled conditions like specular light reflected in the pupil or in the iris. We experimented our approach comparing the results in detection with the results obtained by Daugman algorithm using images from two contrasting databases, CASIA and UBIRIS.
Year
DOI
Venue
2006
10.1007/11892755_13
CIARP
Keywords
Field
DocType
pupil boundary,fast adaboosting,daugman algorithm,recognition process,iris detection,iris recognition system,pupil contour detection,analytic geometry,bounded circumference,adaboosting technique,iris localization,iris recognition
Specular highlight,Iris recognition,Computer vision,AdaBoost,Pattern recognition,Computer science,Edge detection,Image processing,Pupil,Analytic geometry,Artificial intelligence,Biometrics
Conference
Volume
ISSN
ISBN
4225
0302-9743
3-540-46556-1
Citations 
PageRank 
References 
2
0.39
7
Authors
4
Name
Order
Citations
PageRank
Francisco Silva-Mata131.47
Eduardo Garea Llano2236.42
Estela María Álvarez Morales320.72
José Luís Gil Rodríguez430.79