Title

IRIS BIOMETRIC RESEARCH AT PACIFIC

Introduction

Iris texture is a reliable biometric that is unique, remarkably stable through the life of an individual, and easy to capture. Images of individual’s iris are processed and enrolled into a database to later be used for recognition purposes. Issues that can arise when using iris texture as an identifier include: 1) the time to search the large database of iris codes; 2) the differences introduced by dilation of the appearance of the iris for a single individual; and 3) the possibility of spoofing the system by individuals that use cosmetic contacts. Research at Pacific is currently addressing each of these areas. Many applications include verifying the identity of a subject or identifying an unknown individual from a list of possibilities that involve searching a large database. Prediction of ethnicity separates the data into subcategories that will make this search much faster. Research by Mou and Zarei presents an image categorization solution using Artificial Neural Networks that allows the system to automatically categorize human iris images by using supervised and unsupervised learning algorithms. This research is currently ongoing. Iris biometrics has emerged as one of the most reliable and accurate systems when dealing with cooperating subjects. The ideal system would capture iris images across a wide range of pupil dilation; however, challenges arise when attempting to minimize the amount of intrusion when capturing images. Research by Hasegawa and Stark examines the feasibility of using 3D software to synthetically dilate the pupils of existing iris images to more comprehensively cover the possible dynamic range of pupil dilation. Results show there is a marked improvement in recognition accuracy by enrolling a set of synthetic eye images to cover a range of dilation values. Cosmetic contact lenses have the potential to fool an iris biometric system, anything from evading a match to a watch list to masquerading as another person. Existing approaches to detecting cosmetic contact lenses are either limited to detecting lenses created by a particular manufacturing technology or requiring a sequence of images. Research by Hughes focuses on a general method of detecting cosmetic contact lenses by taking a “snapshot” of stereo pair of images, from which the shape of the surface of the iris texture region is estimated. In the presence of cosmetic contacts, this region presents a distinct hemispherical surface. This is the first approach to analyze iris biometric images in the context of 3D shape, and has thus far prove to reliably detect when a person is wearing cosmetic contact lenses. The significance of the three iris biometrics research areas is that biometrics are becoming more important as a way to uniquely identify an individual, and will likely in the future increasingly become ubiquitous in our daily lives. The ability to quickly access iris data and assure its accuracy are fundamental to this. From verifying a person's identity at a banking ATM to passing through security at the airport, iris biometrics has the potential to greatly increase personal security and public safety.

Location

DeRosa University Center, Stockton campus, University of the Pacific

Format

Poster Presentation

This document is currently not available here.

Share

COinS
 
Mar 25th, 10:00 AM Mar 25th, 3:00 PM

IRIS BIOMETRIC RESEARCH AT PACIFIC

DeRosa University Center, Stockton campus, University of the Pacific

Iris texture is a reliable biometric that is unique, remarkably stable through the life of an individual, and easy to capture. Images of individual’s iris are processed and enrolled into a database to later be used for recognition purposes. Issues that can arise when using iris texture as an identifier include: 1) the time to search the large database of iris codes; 2) the differences introduced by dilation of the appearance of the iris for a single individual; and 3) the possibility of spoofing the system by individuals that use cosmetic contacts. Research at Pacific is currently addressing each of these areas. Many applications include verifying the identity of a subject or identifying an unknown individual from a list of possibilities that involve searching a large database. Prediction of ethnicity separates the data into subcategories that will make this search much faster. Research by Mou and Zarei presents an image categorization solution using Artificial Neural Networks that allows the system to automatically categorize human iris images by using supervised and unsupervised learning algorithms. This research is currently ongoing. Iris biometrics has emerged as one of the most reliable and accurate systems when dealing with cooperating subjects. The ideal system would capture iris images across a wide range of pupil dilation; however, challenges arise when attempting to minimize the amount of intrusion when capturing images. Research by Hasegawa and Stark examines the feasibility of using 3D software to synthetically dilate the pupils of existing iris images to more comprehensively cover the possible dynamic range of pupil dilation. Results show there is a marked improvement in recognition accuracy by enrolling a set of synthetic eye images to cover a range of dilation values. Cosmetic contact lenses have the potential to fool an iris biometric system, anything from evading a match to a watch list to masquerading as another person. Existing approaches to detecting cosmetic contact lenses are either limited to detecting lenses created by a particular manufacturing technology or requiring a sequence of images. Research by Hughes focuses on a general method of detecting cosmetic contact lenses by taking a “snapshot” of stereo pair of images, from which the shape of the surface of the iris texture region is estimated. In the presence of cosmetic contacts, this region presents a distinct hemispherical surface. This is the first approach to analyze iris biometric images in the context of 3D shape, and has thus far prove to reliably detect when a person is wearing cosmetic contact lenses. The significance of the three iris biometrics research areas is that biometrics are becoming more important as a way to uniquely identify an individual, and will likely in the future increasingly become ubiquitous in our daily lives. The ability to quickly access iris data and assure its accuracy are fundamental to this. From verifying a person's identity at a banking ATM to passing through security at the airport, iris biometrics has the potential to greatly increase personal security and public safety.