Lecture 5: Iris Recognition

1
Lecture 5 Iris Recognition

• Ioannis Pavlidis

U of H
COSC 6397
2
Genotype and Phenotype

• Genotype refers to a genetic constitution, or a
  group sharing it.
• blood group and DNA
• Phenotype refers to the actual expression of a
  feature through the interaction of genotype,
  development, and environment.
• face, fingerprint, and iris
• Genotypic Error Rate is the minimum False Match
  Rate (e.g., identical twins).
• Phenotypic Error Rate is the minimum False
  Rejection rate (e.g., facial appearance)

3
Properties of the Iris

• The iris is composed of elastic connective
  tissue.
• It consists of pectinate ligaments adhering into
  a tangled mesh revealing striations, ciliary
  processes, crypts, rings, furrows, a corona,
  sometimes freckles, and vasculature.
• Pupillary motion provides a live ness test in
  high security applications.

4
Localization and Analysis of Iris Patterns

• We localize the inner and outer boundaries of the
  iris. This is accomplished through
  integro-differential operations.
• A normalized coordinate system is defined, which
  is invariant to size (e.g., camera zoom and
  distance to the eye).
• The iris pattern is encoded into a 256-byte
  IrisCode by demodulating it with 2D Gabor
  wavelets, which represent the texture by phasors
  in the complex plane.

5
Independence and DOF in IrisCodes

• It is important to establish that there exists
  independent variation in iris patterns, across
  populations and across positions in the iris.
• This is confirmed by tracking the possibility of
  a bit being set.
• The fact that the plot is flat at a value of 0.5
  means that any given bit in an IrisCode is
  equally likely to be set or cleared.