PERSONAL IDENTIFICATION

1
PERSONAL IDENTIFICATION BASED ON IRIS PATTERN
By Roll No 10224002 M.Tech (Computer Tech.) NIT
Under the guidance of Assistant professor Dept.
of Electrical Engineering NIT
2
Personal Identification Based On Iris Pattern

• CONTENTS
• 1.INTRODUCTION OF IRIS RECOGNITION
• What is Iris Recognition
• Human Iris
• Operating Principle
• Advantages
• Disadvantages
• History
• 2. STATE OF THE ART

3
Contents (Cntd.)

• 3. TECHNICAL ISSUES
• Image Acquisition
• Segmentation
• Normalization
• Feature Encoding And Matching
• Iris Image Database
• 4 PERFORMANCE METRICS FOR IRIS RECOGNITION
• 5. APPLICATIONS OF IRIS RECOGNITION
• 6. REFERENCES

4
1. INTRODUCTION OF IRIS RECOGNITION

• 1.1 What Is Iris Recognition
• Iris recognition is a method of biometric authenti
  cation that uses pattern-recognition techniques
  based on high-resolution images of the iris of an
  individual's eyes.
• A Iris recognition system provides Personal
  identification of an individual based on a unique
  feature or characteristic possessed by the human
  Iris.
• The physiological complexity of the organ results
  in the random patterns in iris, which are
  statistically unique and suitable for biometric
  measurements.

5
INTRODUCTION OF IRIS RECOGNITION(Cntd.)

• 1.2 Human Iris
• The iris is a thin circular diaphragm, which lies
  between the cornea and the lens of the human eye.
  front-on view of the iris is shown in Figure 1.1.
  
• 
  
• Figure 1.1 A front-on view of the human eye.

6
1.2 Human Iris(cntd.)

• The iris is perforated close to its centre by a
  circular aperture known as the pupil.
• The function of the iris is to control the amount
  of light entering through the pupil, and this is
  done by the sphincter and the dilator muscles,
  which adjust the size of the pupil. The average
  diameter of the iris is 12 mm, and the pupil size
  can vary from 10 to 80 of the iris diameter .
• The iris consists of a number of layers, the
  lowest is the epithelium layer, which contains
  dense pigmentation cells. The stromal layer lies
  above the epithelium layer, and contains blood
  vessels, pigment cells and the two iris muscles.
  The density of stromal pigmentation determines
  the colour of the iris.

7
1.2 Human Iris(cntd.)

• Formation of the iris begins during the third
  month of embryonic life 3. The unique pattern
  on the surface of the iris is formed
  during the first year of life, and
  pigmentation of the stroma takes place for the
  first few years. Formation of the unique patterns
  of the iris is random and not related to any
  genetic factors 4.
• The only characteristic that is dependent on
  genetics is the pigmentation of the iris, which
  determines its colour. Due to the epigenetic
  nature of iris patterns, the two eyes of an
  individual contain completely independent iris
  patterns, and identical twins possess
  uncorrelated iris patterns3.

8
INTRODUCTION OF IRIS RECOGNITION(Cntd.)

• 1.3 Operating Principle
• An iris-recognition algorithm first has to
  identify the approximately concentric circular
  outer boundaries of the iris and the pupil in a
  photo of an eye.
• The set of pixels covering only the iris is then
  transformed into a bit pattern that preserves the
  information that is essential for a statistically
  meaningful comparison between two iris images.
• To authenticate via identification or
  verification, a template created by imaging the
  iris is compared to a stored value template in a
  database.
• If the Hamming Distance is below the decision
  threshold, a positive identification has
  effectively been made(HDlt0.32).

9
1.3 Operating Principle(Cntd.)

• A practical problem of iris recognition is that
  the iris is usually partially covered by eyelids
  and eyelashes. In order to reduce the
  false-reject risk in such cases, additional
  algorithms are needed to identify the locations
  of eyelids and eyelashes and to exclude the bits
  in the resulting code from the comparison
  operation
• Human iris identification process is basically
  divided into four steps,
• Localization - The inner and the outer boundaries
  of the iris are calculated.
• Normalization - Iris of different people may
  be captured in different size, for the
  same person also size may vary because of
  the variation in illumination and other
  factors.
• Feature extraction - Iris provides abundant
  texture information. A feature vector is
  formed which consists of the ordered
  sequence of features extracted from the
  Various representations of the iris images.
• Matching - The feature vectors are classified
  through different thresholding techniques like
  Hamming Distance, weight vector and winner
  selection, dissimilarity function, etc.

10
1.3 Operating Principle(Cntd.)

• Image for explaining Identification process

11
Iris recognition system
12
INTRODUCTION OF IRIS RECOGNITION(Cntd.)

• 1.4 Advantages
• The iris of the eye has been described as the
  ideal part of the human body for biometric
  identification for several reasons
• It is an internal organ that is well protected
  against damage and wear by a highly transparent
  and sensitive membrane (the cornea). This
  distinguishes it from fingerprints, which can be
  difficult to recognize after years of certain
  types of manual labor.
• The iris is mostly flat, and its geometric
  configuration is only controlled by two
  complementary muscles (the sphincter pupillae and
  dilator pupillae) that control the diameter of
  the pupil. This makes the iris shape far more
  predictable than, for instance, that of the face.

13
1.4 Advantages(Cntd)

• The iris has a fine texture that like
  fingerprints is determined randomly during
  embryonic gestation . Like the fingerprint, it is
  very hard (if not impossible) to prove that the
  iris is unique. However, there are so many
  factors that go into the formation of these
  textures (the iris and fingerprint) that the
  chance of false matches for either is extremely
  low. Even genetically identical individuals have
  completely independent iris textures.
• An iris scan is similar to taking a photograph
  and can be performed from about 10 cm to a few
  meters away. There is no need for the person to
  be identified to touch any equipment that has
  recently been touched by a stranger, thereby
  eliminating an objection that has been raised in
  some cultures against fingerprint scanners, where
  a finger has to touch a surface, or retinal
  scanning, where the eye can be brought very close
  to a lens (like looking into a microscope
  lens).The originally commercially deployed
  iris-recognition algorithm, John Daugman's Iris
  Code, has an unprecedented false match rate

14
1.4 Advantages(Cntd)

• While there are some medical and surgical
  procedures that can affect the color and overall
  shape of the iris, the fine texture remains
  remarkably stable over many decades. Some Iris
  identificationn have succeeded over a period
  about 30 year.

15
INTRODUCTION OF IRIS RECOGNITION(Cntd.)

• 1.5 Disadvantage
• Many commercial Iris scanners can be easily
  fooled by a high quality image of an iris or face
  in place of the real thing.
• The scanners are often tough to adjust and can
  become bothersome for multiple people of
  different heights to use in succession.
• No one is completely sure how an infrared light
  could potentially damage eyesight and many feel
  that it should have been heavily researched
  before it was marketed and sold. The accuracy of
  scanners can be affected by changes in lighting.
• Iris recognition is very difficult to perform at
  a distance larger than a few meters and if the
  person to be identified is not cooperating by
  holding the head still and looking into the
  camera. However, several academic institutions
  and biometric vendors are developing products
  that claim to be able to identify subjects at
  distances of up to 10 meters
• As with other photographic biometric
  technologies, iris recognition is susceptible to
  poor image quality, with associated failure to
  enroll rates.

16
INTRODUCTION OF IRIS RECOGNITION(Cntd.)

• 1.5 History
• The history of iris recognition goes back to mid
  19th-century when the French physician, Alphonse
  Bertillon, studied the use of eye color as an
  identifier 2.
• However, it is believed that the main idea of
  using iris patterns for identification, the way
  we know it today, was first introduced by an eye
  surgeon, Frank Burch, in 1936 6.
• In 1987, two ophthalmologists, Flom and Safir,
  patented this idea and proposed it to Daugman, a
  professor at Harvard University, to study the
  possibility of developing an iris recognition
  algorithm.
• After a few years of scientific experiments,
  Daugman proposed and developed a high condense
  iris recognition system and published the results
  in 1993. The proposed system then evolved and
  achieved better performance in time by testing
  and optimizing it with respect to large iris
  databases.

17
1.5 History(Cntd..)

• A few years after the publication of the First
  algorithm by Daugman, other researchers developed
  new iris recognition algorithms.
• Systems presented by Wildes et al. 11, Boles
  and Boashash , Tisse et al., Zhu et al., Lim et
  al., Noh et al. and Ma et al. are some of the
  well-known algorithms so far.
• Among these algorithms, the works done by Lim et
  al. and Noh et al. are also commercialized.
• The algorithms developed by Wildes and Boles are
  suitable for verification applications because
  the normalization of irises is performed in the
  matching process and would be very time consuming
  in identification applications.
• Although these algorithms have been successful,
  they still require to be improved in the accuracy
  and speed aspects compared to the proposed
  algorithm by Daugman.

18
2. State of the art

• For instance, the developed algorithm by Daugman,
  which is known as the state-of-the-art in the
  field of iris recognition, has initiated huge
  investments on the technology for more than a
  decade. IriScan Inc. patents the core technology
  of the Daugman's system and several companies
  such as IBM, Iridian Technologies, IrisGuard
  Inc., Securimetrics Inc. and Panasonic are active
  in providing iris recognition products and
  services.
• Even though the Daugman system is the most
  successful and most well known, many other
  systems have been developed. The most notable
  include the systems of Wildes et al., Boles and
  Boashash, Lim et al., and Noh et al.
• The algorithms by Lim et al. are used in the iris
  recognition system developed by the Evermedia and
  Senex companies. Also, the Noh et al. algorithm
  is used in the IRIS2000 system, sold by
  IriTech. These are, apart from the Daugman
  system, the only other known commercial
  implementations.
•  

19
2. State of the art (Cntd)

• The Daugman system has been tested under numerous
  studies, all reporting a zero failure rate. The
  Daugman system is claimed to be able to perfectly
  identify an individual, given millions of
  possibilities. The prototype system by Wildes et
  al. also reports flawless performance with 520
  iris images , and the Lim et al. system attains a
  recognition rate of 98.4 with a database of
  around 6,000 eye images.
• Compared with other biometric technologies, such
  as face, speech and finger recognition, iris
  recognition can easily be considered as the most
  reliable form of biometric technology .
• However, there have been no independent trials of
  the technology, and source code for systems is
  not available. Also, there is a lack of publicly
  available datasets for testing and research, and
  the test results published have usually been
  produced using carefully imaged irises under
  favourable conditions.

20
3. TECHNICAL ISSUES

• 3.1 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

21
3.1 IMAGE ACQUISITION(Cntd..)

• Image Acquisition Rigs
• a.The Daugman image-acquisition rig

22

• b. The Wildes et al. image-acquisition rig

23
Image Acquisition(Cntd)

• 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

24
3.1 Image Acquisition(Cntd)

• Discussion
• In common
• Easy for a human operator to master
• Use video rate capture
• Difference.
• 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

25
3. TECHNICAL ISSUES(Cntd.)

• 3.2 SEGMENTATION
• In segmentation, it is desired to distinguish
  the iris texture from the rest of the image. An
  iris is normally segmented by detecting its inner
  (pupil) and outer (limbus) boundaries.
• Well-known methods such as the
  Integro-differential, Hough transform and active
  contour models have been successful techniques in
  detecting the boundaries. In the following, these
  methods are described and some of their
  weaknesses are pointed out.
• Iris Segmentation algorithm performed following
  steps
• Reflection Removal and Iris Detection
• Pupillary and Limbic Boundary Localization(Iris
  Localization)
• Eyelid Localization
• Eyelashes and shadow detection

26
3.2 SEGMENTATION(Cntd)

• Segmentation Alogorithm

27
3.2 SEGMENTATION(Cntd)

• 3.2.1 Daugman's Integro-differential Operator
• In order to localize an iris, Daugman
  proposed the Integro-differential operator. The
  operator assumes that pupil and limbus are
  circular contour and performs as a circular Edge
  detector . Detecting the upper and lower eyelids
  are also performed using the Integro-differential
  operator by adjusting the contour search from
  circular to a designed arcuate. The
  Integro-differential is defned as
• The operator pixel-wise searches throughout
  the raw input image, I(x,y), and obtains the
  blurred partial derivative of the integral over
  normalized circular contours in different radii.

28
3.2.1 Daugman's Integro-differential
Operator(Cntd)

• The pupil and limbus boundaries are expected to
  maximize the contour integral derivative, where
  the intensity values over the circular b orders
  would make a sudden change. Gs (r) is a smoothing
  function controlled by s that smoothes the image
  intensity for a more precise search.

29
3.2 SEGMENTATION(Cntd)

• 3.2.2 Hough Transform
• 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

30
3.2.2 Hough Transform (Cntd.)

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

31
3. TECHNICAL ISSUES(Cntd.)

• 3.3 NORMALIZATION
• Normalization refers to preparing a segmented
  iris image for the feature extraction pro cess.
  In Cartesian co ordinates, iris images are highly
  aected by their distance and angular position
  with resp ect to the camera. Moreover,
  illumination has a direct impact on pupil size
  and causes non-linear variations of the iris
  patterns. A prop er normalization technique is
  exp ected to transform the iris image to comp
  ensate these variations.
• Methematical Tools For Normalization
• 3.3.1 Daugman's Cartesian to Polar Transform
• 3.3.2 Wildes' Image Registration
• 3.3.3 Virtual Circles

32
3. TECHNICAL ISSUES(Cntd.)

• 3.4 FEATURE ENCODING AND MATCHING
• In order to provide accurate recognition of
  individuals, the most discriminating information
  present in an iris pattern must be extracted.
  Only the significant features of the iris must be
  encoded so that comparisons between templates can
  be made.
• Mathematical Tools For Feature Encoding
• 3.4.1 Wavelet Encoding
• 3.4.2 Gabor Filters
• 3.4.3 Log-Gabor Filters
• 3.4.4 Zero-crossings of the 1D wavelet
• 3.4.5 Haar Wavelet

33
3.4 FEATURE ENCODING AND MATCHING(Cntd)

• The template that is generated in the feature
  encoding process will also need a corresponding
  matching metric, which gives a measure of
  similarity between two iris templates. This
  metric should give one range of values when
  comparing templates generated from the same eye,
  known as intra-class comparisons, and another
  range of values when comparing templates created
  from different irises, known as inter-class
  comparisons. These two cases should give distinct
  and separate values, so that a decision can be
  made with high confidence as to whether two
  templates are from the same iris, or from two
  different irises.
• Mathematical Tools For Matching
• 3.4.6 Hamming distance
• 3.4.7 Weighted Euclidean Distance

34
3. TECHNICAL ISSUES(Cntd.)

• 3.5 IRIS IMAGE DATABASE
• The accuracy of the iris recognition system
  depends on the image quality of the iris images.
  Noisy and low quality images degrade
• the performance of the system.
• Some Iris image database available are
• UBIRIS
• CASIA
• LEA
• MMU
• ICE database

35
4. PERFORMANCE METRICS FOR IRIS RECOGNITION

• The following are used as performance metrics for
  Iris Recognition systems
• False accept rate or false match rate (FAR or
  FMR) The probability that the system incorrectly
  matches the input pattern to a non-matching
  template in the database. It measures the percent
  of invalid inputs which are incorrectly accepted.
• False reject rate or false non-match rate (FRR or
  FNMR) the probability that the system fails to
  detect a match between the input pattern and a
  matching template in the database. It measures
  the percent of valid inputs which are incorrectly
  rejected.
• Fqual error rate or crossover error rate (EER or
  CER) the rate at which both accept and reject
  errors are equal. The value of the EER can be
  easily obtained from the ROC curve. The EER is a
  quick way to compare the accuracy of devices with
  different ROC curves. In general, the device with
  the lowest EER is most accurate.
• Failure to enroll rate (FTE or FER)the rate at
  which attempts to create a template from an input
  is unsuccessful. This is most commonly caused by
  low quality inputs

36
4. PERFORMANCE METRICS FOR IRIS RECOGNITION
(Cntd..)

• 6. Failure to capture rate (FTC) Within
  automatic systems, the probability that the
  system fails to detect a biometric input when
  presented correctly.
• 7. template capacity The maximum number of sets
  of data which can be stored in the system.

37
5. APPLICATION OF IRIS RECOGNITION

• Some Current and Future Applications of Iris
  Recognition
• national border controls the iris as a living
  passport.
• computer login the iris as a living password.
• cell phone and other wireless-device-based
  authentication.
• secure access to bank accounts at cash machines.
• premises access control (home, office,
  laboratory, etc)
• driving licenses other personal certificates
• forensics birth certificates tracing missing or
  wanted persons
• credit-card authentication
• credit-card authentication
• anti-terrorism (e.g. security screening at
  airports)
• secure financial transactions (electronic
  commerce, banking)
• Biometric-Key Cryptography" (stable keys from
  unstable templates)

38
6. REFERENCES

• 1 S Sanderson, J. Erbetta. Authentication for
  secure environments based on iris scanning
  technology. IEE Colloquium on Visual Biometrics,
  2000.
• 2 J.Daugman. How iris recognition works.
  Proceedings of 2002 International Conference on
  Image Processing, Vol. 1, 2002.
• 3 E. Wolff. Anatomy of the Eye and Orbit. 7th
  edition. H. K. Lewis Co. LTD,1976.
• 4 R. Wildes. Iris recognition an emerging
  biometric technology. Proceedings of the IEEE,
  Vol. 85, No. 9, 1997.
• 5 J. Daugman. Biometric personal identification
  system based on iris analysis. United States
  Patent, Patent Number 5,291,560, 1994.
• 6 J. Daugman, High Confidence Visual
  Recognition by a test of Statistical
  Independence, IEEE Trans. Pattern Analysis and
  Machine Intelligence, Vol. 15, No.11,
  pp.1148-1161,1993.
• 7 R.P.Wildes, J.C.Asmuth, G.L. Green, S.C.Hsu,
  R.J,Kolczynski, J.R.Matey, S.E.McBride, David
  Sarno_ Res. Center, Princeton, NJ, A System for
  Automated Iris Recognition, Proceedings of the
  Second IEEE Workshop on Applications of
  ComputerVision,1994.
• 8 W. W. Boles and B. Boashash , A Human
  Identification Technique Using Images of the
  Iris and Wavelet Transform, IEEE Transactions On
  Signal Processing, Vol. 46, No. 4, April 1998.

39
6. REFERENCES (Cntd..)

• 9 S. Lim, K. Lee, O. Byeon, T. Kim. Efficient
  iris recognition through improvement of feature
  vector and classifier. ETRI Journal, Vol. 23, No.
  2, Korea, 2001.
• 10 S. Noh, K. Pae, C. Lee, J. Kim.
  Multiresolution independent component analysis
  for iris identification. The 2002 International
  Technical Conference on Circuits/Systems,Computers
  and Communications, Phuket, Thailand, 2002.
• 11 Y. Zhu, T. Tan, Y. Wang. Biometric personal
  identification based on irispatterns. Proceedings
  of the 15th International Conference on Pattern
  Recognition, Spain, Vol. 2, 2000.
• 12 C. Tisse, L. Martin, L. Torres, M. Robert.
  Person identification technique using human iris
• recognition. International Conference on Vision
  Interface, Canada, 2002.
• 13Chinese Academy of Sciences Institute of
  Automation. Database of 756 Greyscale Eye Images.
  http//www.sinobiometrics.com Version 1.0, 2003.
• 14 C. Barry, N. Ritter. Database of 120
  Greyscale Eye Images. Lions Eye Institute, Perth
  Western Australia.
• 15 W. Kong, D. Zhang. Accurate iris
  segmentation based on novel reflection and
  eyelashdetection model. Proceedings of 2001
  International Symposium on Intelligent
  Multimedia, Video and Speech Processing, Hong
  Kong, 2001.

40
End of slide

• Questions?
• THANK YOU