EyeCerts

Schonberg, Daniel

doi:10.1109/TIFS.2006.873604

Return

EyeCerts

2006-06-01

PRE

Schonberg, Daniel *

Kirovski, Darko

DOI：10.1109/TIFS.2006.873604

Original

Original request for help

Save

Abstract

En 中文

In this paper, we propose EyeCerts, a biometric system for the identification of people which achieves offline verification of certified, cryptographically secure documents. An EyeCert is a printed document which certifies the association of content on the document with a biometric feature-a compressed version of a human iris in this work. The system is highly cost-effective since it does not require high complexity, hard-to-replicate printing technologies. Further, the device used to verify an EyeCert is inexpensive, estimated to have approximately the same cost as an off-the-shelf iris-scanning camera. As a central component of the EyeCert system, we present an Iris analysis technique that aims to extract and compress the unique features of a given iris with a discrimination criterion using limited storage. The compressed features should be at maximal distance with respect to a reference iris image database. The iris analysis algorithm performs several steps in three main phases: 1) the algorithm detects the human iris by using a new model which is able to compensate for the noise introduced by the surrounding eyelashes and eyelids, 2) it converts the isolated iris using a modified Fourier-Mellin transform into a standard domain where the common radial patterns of the human iris are concisely represented, and 3) it optimally selects, aligns, and near-optimally compresses the most distinctive transform coefficients for each individual user. Using a low-quality imaging system (sub-U.S.$100), a chi(2) error distribution model, and assuming a fixed false negatives rate of 5%, EyeCert caused false positives at rates better than 10(-5) and as low as 10(-3)0 for certain users.

Keywords:

biometrics

compression of annular and radial patterns

feature extraction

Fourier-Mellin transform (FMT)

iris recognition

multimedia hashing

person identification

template matching

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.