IRIS RECOGNISATION

11
Guided by: - Dr. Aditya Abhyankar By: - Deepak Attarde Mayank Gupta Vishwanath Srinivasan

description

 

Transcript of IRIS RECOGNISATION

Page 1: IRIS RECOGNISATION

Guided by: - Dr. Aditya Abhyankar

By: -Deepak AttardeMayank GuptaVishwanath Srinivasan

Page 2: IRIS RECOGNISATION

BIOMETRIC SECURITY

Modern and reliable method Hard to breach Wide range

Why Iris RecognitionHighly protected and stable, template size is small and image encoding and matching is relatively fast.

Page 3: IRIS RECOGNISATION

INTRODUCTION TO IRIS RECOGNITION

John Daugman, University of Cambridge – Pioneer in Iris Recognition.

Sharbat Gula – aged 12 at Afghani refugee camp.

18 years later at a remote location in Afghanistan.

Page 4: IRIS RECOGNISATION

OVERVIEW OF OUR SYSTEM

Page 5: IRIS RECOGNISATION

SEGMENTATION

Detecting the pupil edges Detecting the iris edges Extracting the iris region

Canny Edge Detection Algorithm

Page 6: IRIS RECOGNISATION

NORMALISATION

Daugman’s Rubber Sheet Model:

(R, theta) to unwrap iris and easily generate a template code.

Fixed Dimension, Cartesian co-ordinates to Polar co-ordinates.

Variations in eye: Optical size (iris), position (pupil), Orientation (iris).

Page 7: IRIS RECOGNISATION

FEATURE EXTRACTION AND MATCHING Generate a template code along with a

mask code. Compare 2 iris templates using

Hamming distances. Shifting of Hamming distances: To

counter rotational inconsistencies. <0.32: Iris Match >0.32: Not a Match

Page 8: IRIS RECOGNISATION

RESULTS AND CASE STUDIES

FAR, FRR EER: 18.3 % which gives an accuracy close to 82%

ROC: Receiver Operator Characteristics

Page 9: IRIS RECOGNISATION

Advantages Uniqueness of iris patterns hence improved

accuracy. Highly protected, internal organ of the eye Stability : Persistence of iris patterns. Non-invasive : Relatively easy to be

acquired. Speed : Smaller template size so large

databases can be easily stored and checked.

Cannot be easily forged or modified.

Page 10: IRIS RECOGNISATION

Concerns / Possible improvements

High cost of implementation Person has to be “physically” present. Capture images independent of surroundings

and environment / Techniques for dark eyes. Non-ideal iris images

Inconsistent Iris size Pupil Dilation Eye Rotation

Page 11: IRIS RECOGNISATION

THANK YOU!!!