Scribd
Upload
6 views13 pages

Iris Recognition Techniques by Daugman

This document summarizes iris recognition technology. It describes how iris recognition works by capturing an image of the iris, locating and normalizing the iris region, representing the iris texture with a 2048-bit code, and comparing this code to stored iris templates to identify a match. It notes that iris recognition has high accuracy, with twins having different iris textures, and is used in many airports worldwide.

Uploaded by

Suneel Kushwaha
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
6 views13 pages

Iris Recognition Techniques by Daugman

This document summarizes iris recognition technology. It describes how iris recognition works by capturing an image of the iris, locating and normalizing the iris region, representing the iris texture with a 2048-bit code, and comparing this code to stored iris templates to identify a match. It notes that iris recognition has high accuracy, with twins having different iris textures, and is used in many airports worldwide.

Uploaded by

Suneel Kushwaha
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd

Iris Recognition

Following the work of John Daugman University of Cambridge

Biometrics
fingerprint Convenience in capturing Low intra-class variance fair good face good fair iris good excellent DNA poor excellent

High interclass variance


Difficult to fool Cost effective

good
good fair

good
good good

excellent
excellent fair

excellent
excellent poor

Properties of the iris


Has highly distinguishing texture Right eye differs from left eye Twins have different iris texture Not trivial to capture quality image + Works well with cooperative subjects + Used in many airports in the world

Represent iris texture as a binary vector of 2048 bits

Representation of iris and also of a person

Textured region is unique for a person

Find (nearly circular) iris and create 8 bands or zones


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.

Cross correlate 1024 local areas with a Gabor wavelet


Get 2 bits at each location/orientation. Threshold the dot product of 2 filters with the iris area. Polar coordinates locate the texture patch. Filter (mask) has 2 width parameters

Use 2nd directional derivative and 1st directional derivative

LOG wave in alpha direction

1st derivative in beta direction

The directional filters defined mathematically

sinusoid

taper down Taper down Image intensity in radial in tangential in polar coords direction direction

Summary of feature extraction


Obtain quality image of certain (left) eye Find boundary of pupil and outside of iris Normalize radii to range, say, 0.5 to 1.0 Define the 8 bands by radii ranges Perform 2 dot products at each of 1024 locations defined around the bands by radius rho and angle phi

How is the matching done to templates of enrolled persons?

Person scanned under controlled environment and iris pattern is stored with ID (say address, SS#, etc.) Might be several million such templates for frequent flyers (6B for all world) At airport or ATM, scan unknown persons left eye; then compute Hamming distance to ALL templates.

Distributions of true matches versus non matches

Hamming distances of false matches

Hamming distances of true matches

Active Iris Systems

Recognition by comparing unknown scan to MILLIONS of stored templates

Less than 32% unmatched bits means MATCH Only need to count unmatched bits use exclusive OR with machine words Mask off bad patches due to eyelid or eyelash interference (have to detect that)

You might also like