You are on page 1of 22

IRIS SCANNING

CONTENTS

What is iris scanning? A typical iris. How does it work? Creation of the iris code. Iris scanning configuration. Technology used. Iris localization. Iris normalization. Image enhancement. Division of the iris. Advantages and disadvantages. Future aspects. Reference.

WHAT IS IRIS SCANNING?


Iris is the area of the eye where the pigmented or colored circle usually brown or blue, rings the dark pupil of the eye.
Iris scanning is a process of recognizing a person by analyzing the random pattern of the iris.

A TYPICAL IRIS

Eye = Camera Cornea bends, refracts, and focuses light.

Retina = Film for image projection (converts image into electrical signals).
Optical nerve transmits signals to the brain.

HOW DOES IT WORK?


SCAN BEGINS WITH A PHOTOGRAPH BY A SPECIALIZED CAMERA.

USES A CAMERA,TYPICALLY VERY

CLOSE,NOT MORE THAN THREE FEET.

HOW DOES IT WORK(Contd.)

AN INFRARED IMAGER ILLUMINATES

THE EYE AND TAKES A VERY HIGH RESOLUTION PHOTOGRAPH.

THE PROCESS TAKES ONE TO TWO SECONDS.

CREATION OF THE IRIS CODE


THE PICTURE OF THE EYE IS FIRST PROCESSED BY A SOFTWARE THAT LOCALIZES THE INNER AND OUTER BOUNDARIES OF THE IRIS.
ENCODING IS DONE BY IMAGE PROCESSING TECHNOLOGIES.

IRIS SCANNING CONFIGURATION


Uniform distribution

Stored templates

Pre processing
Iris scan 2d image capture Iris localization enrolment Authentication

Reject Featureextraction Transform representation Identification Verification Accept comparison

TECHNIQUES USED
IRIS LOCALIZATION.
IRIS NORMALIZATION. IMAGE ENHANCEMENT.

IRIS LOCALIZATION
Both the inner boundary and the outer

boundary of a typical iris can be taken as circles. But the two circles are usually not co-centric.

We detect the inner boundary between

the pupil and the iris.

We detect the outer boundary by

maximizing changes of the perimeternormalized along the circle. The technique is found to be efficient and effective.

IRIS NORMALIZATION
The size of the pupil may change due to

the variation of the illumination and the associated elastic deformations in the iris texture may interface with the results of pattern matching.
For the purpose of accurate texture

analysis, it is necessary to compensate this deformation.

Since both the inner and outer boundaries

of the iris have been detected, it is easy to map the iris ring to a rectangular block of texture of a fixed size.

IMAGE ENHANCEMENT
The original image has low contrast and may have non-uniform illumination caused by the position of the light source.
These may impair the result of the texture

analysis.
We enhance the iris image reduce the effect of

non-uniform illumination.

DIVIDE IRIS AND CREATE BANDS

Need to locate the overall region of the iris. Then need to measure texture in 1024 small neighborhoods; perhaps 128 around each of 8 bands.

ADVANTAGES OF IRIS SCANNING


Highly protected, internal organ of the eye.
Externally visible; patterns imaged from a

distance .
Iris patterns possess a high degree of

randomness.
variability: 244 degrees-of-freedom . uniqueness: set by combinatorial complexity .

Changing pupil size confirms natural physiology . Patterns apparently stable throughout life.

DISADVANTAGES OF IRIS SCANNING


Small target (1 cm) to acquire from a distance (1 m) . Obscured by eyelashes, lenses, reflections.
Illumination should not be visible or bright. Deforms non-elastically as pupil changes

size.

FUTURE ASPECTS
Regardless of the challenges, the popularity of iris scanningand its cousin, facial recognition technologyis growing. This is

particularly true in physical security applications, like those used at some airports and government installations.
No-contact scanning is the future of biometrics. Iris scanning is positioned to take a central role.

To process large numbers of individuals, a biometrics solution must be fast and nonintrusive. Products like Sarnoffs Iris On the

Move (IOM) (video) allows the scanning of up to 30 people per minute from a distance of several feet. The scanned individuals do not even have to stop. Compare this with an expected throughput of 10 to 15 people per minute with high-end hand or fingerprint scanners.

REFERENCE
Daugman J (1999) "Biometric decision landscapes." Technical Report No TR482,

University of Cambridge Computer Laboratory. http://www.cl.cam.ac.uk/~jgd1000/


http://en.wikipedia.org/wiki/Iris_recognition http://www.google.com

THANK YOU