Dechu Final Ppt

IRIS RECOGNITION SYSTEM March 23, 2011 1

VIVEKANANDA COLLEGE OF ENGINEERING & TECHNOLOGY

Technical Seminar On

“IRIS BASED RECOGNITION SYSTEM USING WAVELET TRANSFORM”

byDECHAMMA I A(4VP07EC011)

VIII sem,EC


IS FINGER PRINTING STRONG ENOUGH??


IS VOICE RECOGNITION RELIABLE??


IS DNA THE ULTIMATE??


IS FACE RECOGNITION REALLY ROBUST??


REAL AUTHENTICITY LIES IN

YOUR EYES…..


Technical Seminar On

“IRIS BASED RECOGNITION SYSTEM USING WAVELET TRANSFORM”

byDECHAMMA I A(4VP07EC011)

VIII sem,EC

VIVEKANANDA COLLEGE OF ENGINEERING & TECHNOLOGY


OVERVIEW OF PRESENTATION

Biometric System

Why IRIS?

Block Diagram

Advantages

Disadvantages

Conclusion

Reference


Biometric System

A biometric system provides an automatic recognition of an individual based on some sort

of unique feature or characteristic possessed by the individual.

Something you know - password, PINSomething you have - smart card, token(secure ID card)Something you are - biometric

Security field uses three different types of authentication


CATEGORIES OF BIOMETRICS

PHYSICAL BIOMETRICS1) Iris Recognition2) Retina Recognition3) Fingerprint Recognition4) Face Recognition5) Hand Scan6) Finger Scan

BEHAVIORAL BIOMETRICS1) Signature Recognition2) Voice Recognition3) Typing Recognition


WHAT IS AN IRIS?

Coloured part of the eye

Contains delicate patterns

Texture is unique to a person


Its suitability as an exceptionally accurate biometric

derives from its

extremely data-rich physical structure

genetic independence — no two eyes are the

same

patterns apparently stable throughout life

Highly protected by internal organ of the eye

Why IRIS?


Anatomy of the Human Eye

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.


Individuality of Iris

Left and right eye irises have distinctive pattern.

IRIS RECOGNITION?


Most accurate biometric method

Uses pattern recognition techniques

Completely Non-Invasive


Iris Recognition System

Feature Extraction by Haar Wavelet

Iris code

Normalization

WORKING


Image Acqisition

Iris Localization

Iris Normalization

Feature Extraction

Matching


I. Image Acquisition

Why important?

One of the major challenges of automated iris

recognition is to capture a high-quality image of the iris.

Concerns on the image acquisition rigs Obtain images with sufficient resolution and sharpness

Good contrast in the iris pattern with proper illumination

Well centered without unduly constraining the operator

Artifacts eliminated as much as possible


Image Acquisition Device


Purpose: To isolate the actual iris region in a digital

eye.

II. Iris Localization

Iris can be approximated by two circles, One for

iris/sclera boundary and another for iris/pupil boundary.


How localization is done?

Pupil & Iris detection: Circular Hough Transform

xc^2 + yc^2 – r^2 = 0

xc & yc are centre coordinates of pupilr is radius of pupil


III. Normalization

θ

θ

rr

0 1

θ

θ

Circular band is divided into 8 subbands of equal thickness for a given angle .

Subbands are sampled uniformly in and in r.

θ

θ

θ

θ

Rubber Sheet Model Each pixel (x,y) is mapped into pair of polar coordinates (r, ).

Where R is on interval (0,1) is angle (0,2pi)


III. Feature Extraction

WAVELET ENCODING:-

Wavelet can be used to decompose the data in the iris region into components that appear at different resolution.

A number of wavelet filters is applied to 2D iris region, one for each resolution with each wavelet a scaled version of some basic function.

Output of applying wavelets (Haar Wavelet) is then encoded to provide iris pattern.


HAAR WAVELET

Wavelet Transform breaks an image down into four sub-images.

Haar Wavelet Haar Transform

APPROACH:

Mapped image of size 100 x 402 pixels is decomposed to a max

of 5 levels

Levels are cd1 to cd5 in vertical, horizontal and diagonal

directions

Finally we get combinations of six matrices

Cd4(h) & Cd5(h)

Cd4(v) & Cd5(v)

Cd4(d) & Cd5(d)


APPROACH:


These matrices are combined to build one single vector called

Feature Vector.

Binary Coding Scheme:

To obtain vector in binary code.

Let “Coef” be Feature Vector of an image than the following

Quantization scheme coverts it to its code-word:

o If Coef(i) >= 0 then Coef(i)=1

o If Coef(i) < 0 then Coef(i)=0



For matching, the Hamming distance was chosen as a metric for recognition.

The Daugman system computes the Hamming distance. The hamming distance between iris code X and Y is given by:

The decision whether two images belong to same person depends on the following result:

IV. Pattern Matching

If HD <= 0.32 decide that it is same person If HD > 0.32 decide that it is different person

An illustration of the shifting process. One shift is defined as one shift left, and one shift right of a reference template. In this example one filter is used to encode the templates, so only two bits are moved during a shift. The lowest Hamming distance, in this case zero, is then used since this corresponds to the best match between the two templates.

IRIS RECOGNITION SYSTEM 29March 23, 2011

Graphical User Interface



Advantages:

Result is 99.9% accurate.

externally visible, so noninvasive — patterns imaged from a

distance.

Iris patterns possess a high degree of randomness .

Patterns apparently stable throughout life.

extremely data-rich physical structure.

It is a living password.


Small target (1 cm) to acquire from a distance (1 m)

Cannot be applied to blind with impaired iris

Colored glasses must be avoided

Obscured by eyelashes, lenses, reflections

Deforms non-elastically as pupil changes size

Illumination should not be visible or bright

DISADVANTAGES:

APPLICATIONS:

Automatic Teller Machines(ATMs).

Tracking Prisoner Movement. Computer login. Premises access control. Personal certificates Forensics. Internet security.



Conclusion:

Proven to be the most accurate and versatile security measure.

No room for human error


J. Daugman, High confidence recognition of persons by test of statistical independence, IEEE Trans. Pattern Anal. Mach. Intell. 15

(11) (1993) 1148 – 1161. Jafar M.H.Ali and Aboul Ella Hassanien,”An Iris recognition system to

enhance E-security environment based on wavelet Theory”,AMO Journal,Volume 2

Daugman.J,”How iris recognition works,” IEEE trans Trans. On circuits and systems for video technolgy,vol.11.

www.wikipedia.org/iris regognition.html

Reference:



Dechu Final Ppt

Documents