Automated Iris Recognition Technology

1
Automated Iris Recognition Technology Iris
Biometric System
CS 790Q Biometrics

• Instructor Dr G. Bebis
• Presented by Chang Jia
• Dec 9th, 2005

2
Overview

• The Iris as a Biometrics The iris is an overt
  body that is available for remote assessment with
  the aid of a machine vision system to do
  automated iris recognition.
• Iris recognition technology combines computer
  vision, pattern recognition, statistical
  inference, and optics.
• The spatial patterns that are apparent in the
  human iris are highly distinctive to an
  individual.
• Clinical observations
• Developmental biology

3
Overview
The structure of the human eye
The structure of the iris seen in a transverse
section
The structure of the iris seen in a frontal
section
4
Overview

• 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
• physical protection by a transparent window (the
  cornea), highly protected by internal organ of
  the eye
• externally visible, so noninvasive patterns
  imaged from a distance

5
Overview

• The disadvantages to use iris as a biometric
  measurement are
• Small target (1 cm) to acquire from a distance
  (about 1 m)
• Moving target
• Located behind a curved, wet, reflecting surface
• Obscured by eyelashes, lenses, reflections
• Partially occluded by eyelids, often drooping
• Deforms non-elastically as pupil changes size
• Illumination should not be visible or bright

6
PART IIris Recognition An Emerging Biometric
Technology
CS 790Q Biometrics

• R. Wildes, "Iris Recognition An Emerging
  Biometric Technology", Proceedings of the IEEE,
  vol 85, no. 9, pp. 1348-1363, 1997.

7
Outline

• Technical Issues
• Image Acquisition
• Iris Localization
• Pattern Matching
• Systems and Performance
• (Throughout the discussion in this paper, the
  iris-recognition systems of Daugman and Wildes et
  al. will be used to provide illustrations.)

8
Technical Issues
Schematic diagram of iris recognition
9
I. Image Acquisition

• Why important?
• One of the major challenges of automated iris
  recognition is to capture a high-quality image of
  the iris while remaining noninvasive to the human
  operator.
• Concerns on the image acquisition rigs
• Obtained images with sufficient resolution and
  sharpness
• Good contrast in the interior iris pattern with
  proper illumination
• Well centered without unduly constraining the
  operator
• Artifacts eliminated as much as possible

10
I. Image Acquisition - Rigs

• The Daugman image-acquisition rig

11
I. Image Acquisition - Rigs

• The Wildes et al. image-acquisition rig

12
I. Image Acquisition - Results
Result Image from Wildes et al. rig -- capture
the iris as part of a larger image that also
contains data derived from the immediately
surrounding eye region
13
Discussion

• In common
• Easy for a human operator to master
• Use video rate capture
• Difference
• Illumination
• The Daugmans system makes use of an LED-based
  point light source in conjunction with a standard
  video camera.
• The Wildes et al. system makes use of a diffuse
  source and polarization in conjunction with a
  low-light level camera.
• Operator self-position
• The Daugmans system provides the operator with
  live video feedback
• The Wildes et al. system provides a reticle to
  aid the operator in positioning

14
II. Iris Localization

• Purpose to localize that portion of the acquired
  image that corresponds to an iris
• In particular, it is necessary to localize that
  portion of the image derived from inside the
  limbus (the border between the sclera and the
  iris) and outside the pupil.
• Desired characteristics of iris localization
• Sensitive to a wide range of edge contrast
• Robust to irregular borders
• Capable of dealing with variable occlusions

15
II. Iris Localization

• The Daugman system fits the circular contours via
  gradient ascent on the parameters so as to
  maximize

Where
is a radial Gaussian, and circular contours
(for the limbic and pupillary boundaries) be
parameterized by center location (xc,yc), and
radius r (active contour fitting method)
16
II. Iris Localization

• The Wildes et al. system performs its contour
  fitting in two steps. (histogram-based approach)
• First, the image intensity information is
  converted into a binary edge-map
• where
• and
• Second, the edge points vote to instantiate
  particular contour parameter values.

17
II. Iris Localization

• The voting procedure of the Wildes et al. system
  is realized via Hough transforms on parametric
  definitions of the iris boundary contours.

18
Illustrative Results of Iris Localization
only that portion of the image below the upper
eyelid and above the lower eyelid should be
included
Obtained by using the Wildes et al. system
19
Discussion

• Both approaches are likely to encounter
  difficulties if required to deal with images that
  contain broader regions of the surrounding face
  than the immediate eye region
• Difference
• the active contour approach avoids the inevitable
  thresholding involved in generating a binary
  edge-map
• the histogram-based approach to model fitting
  should avoid problems with local minima that the
  active contour models gradient descent procedure
  might experience

20
III. Pattern Matching

• Four steps
• 1) bringing the newly acquired iris pattern into
  spatial alignment with a candidate data base
  entry
• 2) choosing a representation of the aligned iris
  patterns that makes their distinctive patterns
  apparent
• 3) evaluating the goodness of match between the
  newly acquired and data base representations
• 4) deciding if the newly acquired data and the
  data base entry were derived from the same iris
  based on the goodness of match.

21
III. Pattern Matching -Alignment

• Purpose to establish a precise correspondence
  between characteristic structures across the two
  images.
• Both of the systems under discussion compensate
  for image shift, scaling, and rotation.
• For both systems, iris localization is charged
  with isolating an iris in a larger acquired image
  and thereby accomplishes alignment for image
  shift.

22
III. Pattern Matching -Alignment

• The Daugmans system uses radial scaling to
  compensate for overall size as well as a simple
  model of pupil variation based on linear
  stretching.

Map Cartesian image coordinates (x, y) to
dimensionless polar (r, ?) image coordinates
according to

• The Wildes et al. system uses an
  image-registration technique to compensate for
  both scaling and rotation. The mapping function
  (u,v) is to minimize

while being constrained to capture a similarity
transformation of image coordinates (x, y) to
(x, y)
23
III. Pattern Matching -Alignment

• The two methods for establishing correspondences
  between acquired and data base iris images seem
  to be adequate for controlled assessment
  scenarios
• Improvements
• more sophisticated methods may prove to be
  necessary in more relaxed scenarios
• more complicated global geometric compensations
  will be necessary if full perspective distortions
  (e.g., foreshortening) become significant

24
III. Pattern Matching - Representation

• The Daugmans system uses demodulation with
  complex-valued 2D Gabor wavelets to encode the
  phase sequence of the iris pattern to an
  IrisCode.

25
III. Pattern Matching - Representation

• In implementation, the Gabor filtering is
  performed via a relaxation algorithm, with
  quantization of the recovered phase information
  yielding the final representation.

Pictorial Examples of one IrisCode
26
III. Pattern Matching - Representation

• The Wildes et al. system makes us of an isotropic
  bandpass decomposition derived from application
  of Laplacian of Gaussian filters to the image
  data.
• In practice, the filtered image is realized as a
  Laplacian pyramid. This representation is defined
  procedurally in terms of a cascade of small
  Gaussian-like filters.

with s the standard deviation of the Gaussian and
? the radial distance of a point from the
filters center
27
III. Pattern Matching - Representation

• Result Multiscale representation for iris
  pattern matching. Distinctive features of the
  iris are manifest across a range of spatial
  scales.

Obtained by using the Wildes et al. system
28
IV. Pattern Matching Goodness of Match

• The Daugman system computes the normalized
  Hamming distance as
• The result of this computation is then used as
  the goodness of match, with smaller values
  indicating better matches.

29
IV. Pattern Matching - Decision

• The Wildes et al. system employs normalized
  correlation between the acquired and data base
  representations.

30
IV. Pattern Matching - Decision

• For the Daugman system, this amounts to choosing
  a separation point in the space of (normalized)
  Hamming distances between iris representations.
• In order to calculate the cross-over point,
  sample populations of imposters and authentics
  were each fit with parametrically defined
  distributions.

31
IV. Pattern Matching - Decision

• For the Wildes et al. system, the decision-making
  process must combine the four goodness-of-match
  measurements that are calculated by the previous
  stage of processing (i.e., one for each pass band
  in the Laplacian pyramid representation) into a
  single accept/reject judgment.

32
Systems and Performance - The Daugman
iris-recognition system

• Both the enrollment and verification modes take
  under 1s to complete.
• Empirical test 1 592 irises from 323 persons ?
  the system exhibited no false accepts and no
  false rejects
• Empirical test 2
• Phase1 199 irises from 122 persons, 878 attempts
  in identification mode over 8 days ? no false
  accepts and 89 false rejects (47 retry with still
  16 rejected)
• Phase2 96 irises (among 199) with 403 entries
  for identification ? no false accepts and no
  false rejects

33
Systems and Performance - The Wildes et al.
iris-recognition system

• Both the enrollment and verification modes
  require approximately 10s to complete.
• Only one empirical test 60 different irises with
  10 images each (5 at the beginning and 5 about
  one month later) from 40 persons ? no false
  accepts and no false rejects.

34
Questions?
35
PART IIAn Iris Biometric System for Public and
Personal Use
CS 790Q Biometrics

• M. Negin et al., "An Iris Biometric System for
  Public and Personal Use", IEEE Computer, pp.
  70-75, February 2000.

36
Iris identification process

• The system captures a digital image of one eye,
  encodes its iris pattern, then matches that file
  against the file stored in the database for that
  individual.

37
The public-use system

• The public-use multiple-camera system for
  correctly positioning and imaging a subjects
  iris.

Note wide-field-of-view (WFOV)
narrow-field-of-view (NFOV) camera
38
The public-use optical platform

• left and right illuminator pods, gaze director,
  and optical filter

(b) a solid model of the platforms internal
components.
39
The personal-use system

• The user manually positions the camera three to
  four inches in front of the eye.
• Make sure that the devices LED centers within
  the aperture that superimposes the users line of
  sight and the cameras optical axis.

40
Identification Performance

• Verification distributions of authentic results
  (in brown) and imposter results (in green).

41
Field Trial Experience

• The first pilot programwith the Nationwide
  Building Society in Swindon, Englandran for six
  months and included more than 1,000 participants,
  before going into regular service during the
  fourth quarter of 1998.
• The field trial experience has been very
  positive
• 91 percent prefer iris identification to a PIN
  (personal identification number) or signature,
• 94 percent would recommend iris identification to
  friends and family,
• 94 percent were comfortable or very comfortable
  using the system.
• The survey also found nearly 100 percent approval
  on three areas of crucial importance to
  consumers reliability, security, and
  acceptability.

42
Questions?
Thank You.