Loading [MathJax]/extensions/MathZoom.js
New Methods in Iris Recognition | IEEE Journals & Magazine | IEEE Xplore

New Methods in Iris Recognition


Abstract:

This paper presents the following four advances in iris recognition: 1) more disciplined methods for detecting and faithfully modeling the iris inner and outer boundaries...Show More

Abstract:

This paper presents the following four advances in iris recognition: 1) more disciplined methods for detecting and faithfully modeling the iris inner and outer boundaries with active contours, leading to more flexible embedded coordinate systems; 2) Fourier-based methods for solving problems in iris trigonometry and projective geometry, allowing off-axis gaze to be handled by detecting it and ldquorotatingrdquo the eye into orthographic perspective; 3) statistical inference methods for detecting and excluding eyelashes; and 4) exploration of score normalizations, depending on the amount of iris data that is available in images and the required scale of database search. Statistical results are presented based on 200 billion iris cross-comparisons that were generated from 632 500 irises in the United Arab Emirates database to analyze the normalization issues raised in different regions of receiver operating characteristic curves.
Page(s): 1167 - 1175
Date of Publication: 24 September 2007

ISSN Information:

PubMed ID: 17926700

I. Introduction

The anticipated large-scale applications of biometric technologies such as iris recognition are driving innovations at all levels, ranging from sensors to user interfaces, to algorithms and decision theory. At the same time as these good innovations, possibly even outpacing them, the demands on the technology are getting greater. Today, many countries are considering or have even announced procurement of biometrically enabled national identity (ID) card schemes, one of whose purposes will be to detect and prevent multiple IDs. Achieving that purpose will require, at least at the time when cards are issued and IDs are registered, an offline “each-against-all” cross-comparison. In effect then the number of biometric comparisons that must be performed scales as the square of the population. The decision confidence levels that will be required to keep the false match rate (FMR) negligible, despite such vast numbers of opportunities to make false matches, can only be described as astronomical.

References

References is not available for this document.