Feature characterization in iris recognition with stochastic autoregressive models

Authors:
Luis E. Garza Castañón;Saúl Montes de Oca;Rubén Morales-Menéndez
Affiliations:
Department of Mechatronics and Automation, ITESM Monterrey Campus;Automation Graduate Program Student, ITESM Monterrey Campus, Monterrey, N.L., México;Department of Mechatronics and Automation, ITESM Monterrey Campus
Venue:
IBERAMIA-SBIA'06 Proceedings of the 2nd international joint conference, and Proceedings of the 10th Ibero-American Conference on AI 18th Brazilian conference on Advances in Artificial Intelligence
Year:
2006

Citing 7
Cited 0

Digital Control of Dynamic Systems

Digital Control of Dynamic Systems
An Iris Biometric System for Public and Personal Use

Computer
Personal Identification Based on Iris Texture Analysis

IEEE Transactions on Pattern Analysis and Machine Intelligence
A New Iris Segmentation Method for Recognition

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 3 - Volume 03
UBIRIS: a noisy iris image database

ICIAP'05 Proceedings of the 13th international conference on Image Analysis and Processing
An introduction to biometric recognition

IEEE Transactions on Circuits and Systems for Video Technology
How iris recognition works

IEEE Transactions on Circuits and Systems for Video Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

Iris recognition is a reliable technique for identification of people. A typical iris recognition system is composed of four phases: image acquisition and preprocessing, iris localization and extraction, iris features characterization, and comparison and matching. We are introducing stoch- astic autoregressive with exogenous inputs models for the features characterization step. Every model is learned from data. In the comparison and matching step, data taken from iris sample are substituted into every model and residuals are generated. A decision is taken based on a threshold calculated experimentally. A successful rate of identifications for UBIRIS and MILES databases shows potential applications.