apresentação - iris recognition
TRANSCRIPT
![Page 1: Apresentação - Iris Recognition](https://reader030.vdocuments.mx/reader030/viewer/2022021219/577c7ed81a28abe054a28536/html5/thumbnails/1.jpg)
8/17/2019 Apresentação - Iris Recognition
http://slidepdf.com/reader/full/apresentacao-iris-recognition 1/37
IRIS RECOGNITION
Igor Leonardo O. Bastos – [email protected]
Handbook of Biometrics – Chapter 4
![Page 2: Apresentação - Iris Recognition](https://reader030.vdocuments.mx/reader030/viewer/2022021219/577c7ed81a28abe054a28536/html5/thumbnails/2.jpg)
8/17/2019 Apresentação - Iris Recognition
http://slidepdf.com/reader/full/apresentacao-iris-recognition 2/37
Summary
Understanding an eye
A short history about iris recognition
Current state
The Method
Off-Axis Gaze Correction
Detecting and Excluding Eyelashes
Evaluation
References
![Page 3: Apresentação - Iris Recognition](https://reader030.vdocuments.mx/reader030/viewer/2022021219/577c7ed81a28abe054a28536/html5/thumbnails/3.jpg)
8/17/2019 Apresentação - Iris Recognition
http://slidepdf.com/reader/full/apresentacao-iris-recognition 3/37
UNDERSTANDING
AN EYE
![Page 4: Apresentação - Iris Recognition](https://reader030.vdocuments.mx/reader030/viewer/2022021219/577c7ed81a28abe054a28536/html5/thumbnails/4.jpg)
8/17/2019 Apresentação - Iris Recognition
http://slidepdf.com/reader/full/apresentacao-iris-recognition 4/37
Understanding an eye
How is called any part of an eye?
Fig 1 – Eye parts and its names
![Page 5: Apresentação - Iris Recognition](https://reader030.vdocuments.mx/reader030/viewer/2022021219/577c7ed81a28abe054a28536/html5/thumbnails/5.jpg)
8/17/2019 Apresentação - Iris Recognition
http://slidepdf.com/reader/full/apresentacao-iris-recognition 5/37
A SHORT HISTORY OF
IRIS RECOGNITION
![Page 6: Apresentação - Iris Recognition](https://reader030.vdocuments.mx/reader030/viewer/2022021219/577c7ed81a28abe054a28536/html5/thumbnails/6.jpg)
8/17/2019 Apresentação - Iris Recognition
http://slidepdf.com/reader/full/apresentacao-iris-recognition 6/37
A Short History of Iris Recognition
Iris was the target of studies since the ancient Egypt,
Chaldea and ancient Greece
Stone inscriptions, painted ceramic artifacts, writings
Commonly associated to the art of ‘Divination’
Fig 2 – Symbol of protection and royal power
![Page 7: Apresentação - Iris Recognition](https://reader030.vdocuments.mx/reader030/viewer/2022021219/577c7ed81a28abe054a28536/html5/thumbnails/7.jpg)
8/17/2019 Apresentação - Iris Recognition
http://slidepdf.com/reader/full/apresentacao-iris-recognition 7/37
A Short History of Iris Recognition
Studies about iris remits to Hippocrates writings and
Imothep’s
Fig 3 – Hippocrates and Imhotep
![Page 8: Apresentação - Iris Recognition](https://reader030.vdocuments.mx/reader030/viewer/2022021219/577c7ed81a28abe054a28536/html5/thumbnails/8.jpg)
8/17/2019 Apresentação - Iris Recognition
http://slidepdf.com/reader/full/apresentacao-iris-recognition 8/37
A Short History of Iris Recognition
Alphonse Bertillon iris as a distinguishing human
identifier
James Doggartcomplexity of iris patterns and
adequacy to serve in the same way of fingerprints(oneness)
Flom and Safir patent of Doggart’s concept but no
method to make it possible
Fig 4 – Alphonse Bertillon, Leonard Flom and Aran Safir
![Page 9: Apresentação - Iris Recognition](https://reader030.vdocuments.mx/reader030/viewer/2022021219/577c7ed81a28abe054a28536/html5/thumbnails/9.jpg)
8/17/2019 Apresentação - Iris Recognition
http://slidepdf.com/reader/full/apresentacao-iris-recognition 9/37
CURRENT STATE
![Page 10: Apresentação - Iris Recognition](https://reader030.vdocuments.mx/reader030/viewer/2022021219/577c7ed81a28abe054a28536/html5/thumbnails/10.jpg)
8/17/2019 Apresentação - Iris Recognition
http://slidepdf.com/reader/full/apresentacao-iris-recognition 10/37
Current State
Developed rapidly over the past 15 years Large number of active researchers in academy and
industry
Lots of people enrolled in iris recognition systems
Systems are usually designed for use in
identification-modeOne-to-many exhaustive search
Astonishing number of comparisons
![Page 11: Apresentação - Iris Recognition](https://reader030.vdocuments.mx/reader030/viewer/2022021219/577c7ed81a28abe054a28536/html5/thumbnails/11.jpg)
8/17/2019 Apresentação - Iris Recognition
http://slidepdf.com/reader/full/apresentacao-iris-recognition 11/37
Current State
Basic research into alternative methods continues
Scientific and engineering literature about iris
recognition grows monthly
Contributions from several university and industrial labs
around the world
Iris recognition systems employed by government
agencies
Project IRIS from UK to identify immigrants
![Page 12: Apresentação - Iris Recognition](https://reader030.vdocuments.mx/reader030/viewer/2022021219/577c7ed81a28abe054a28536/html5/thumbnails/12.jpg)
8/17/2019 Apresentação - Iris Recognition
http://slidepdf.com/reader/full/apresentacao-iris-recognition 12/37
Current State
Many iris recognition datasets are available
CASIA Iris Image Database (v4)
UPOL Iris Database
UBIRIS Database
ICE 2005 Database
BATH University Iris Database
![Page 13: Apresentação - Iris Recognition](https://reader030.vdocuments.mx/reader030/viewer/2022021219/577c7ed81a28abe054a28536/html5/thumbnails/13.jpg)
8/17/2019 Apresentação - Iris Recognition
http://slidepdf.com/reader/full/apresentacao-iris-recognition 13/37
THE METHOD
![Page 14: Apresentação - Iris Recognition](https://reader030.vdocuments.mx/reader030/viewer/2022021219/577c7ed81a28abe054a28536/html5/thumbnails/14.jpg)
8/17/2019 Apresentação - Iris Recognition
http://slidepdf.com/reader/full/apresentacao-iris-recognition 14/37
The Method
Finding the Iris is the first thing to be done
Inner and outer boundaries at pupil and sclera
Upper and lower eyelids
Superimposed eyelashes or reflections from the cornea oreyeglasses
Precision in assigning the true inner and outer
boundaries is a critical operation Innacuracy can cause different mappings of the iris pattern
in its extracted description
![Page 15: Apresentação - Iris Recognition](https://reader030.vdocuments.mx/reader030/viewer/2022021219/577c7ed81a28abe054a28536/html5/thumbnails/15.jpg)
8/17/2019 Apresentação - Iris Recognition
http://slidepdf.com/reader/full/apresentacao-iris-recognition 15/37
The Method
Important point iris is not an annulus
Inner and outer boundaries are usually not concentric
Pupil boundaries and outer iris boundaries are non-circular
Performance improved by relaxing bothassumptions
Methods for modelling boundaries whatever their shapes
![Page 16: Apresentação - Iris Recognition](https://reader030.vdocuments.mx/reader030/viewer/2022021219/577c7ed81a28abe054a28536/html5/thumbnails/16.jpg)
8/17/2019 Apresentação - Iris Recognition
http://slidepdf.com/reader/full/apresentacao-iris-recognition 16/37
The Method
Finding the correct countours can be difficult
Eyelids can occlude iris outer boundary
Reflections from illumination can occlude iris inner boundary
Both can be occluded by reflections from eyeglasses
It is necessary to fit flexible contours that can
tolerate interruptions
A constraint both boundaries are closed curves
![Page 17: Apresentação - Iris Recognition](https://reader030.vdocuments.mx/reader030/viewer/2022021219/577c7ed81a28abe054a28536/html5/thumbnails/17.jpg)
8/17/2019 Apresentação - Iris Recognition
http://slidepdf.com/reader/full/apresentacao-iris-recognition 17/37
The Method
Employment of Active Contours based on discrete
Fourier series expansions of the contour data
Selecting the number of frequency componentsallows control over the degree of smoothness that is
imposed
Truncating means applying a low-pass filtering over theboundary curvature data
![Page 18: Apresentação - Iris Recognition](https://reader030.vdocuments.mx/reader030/viewer/2022021219/577c7ed81a28abe054a28536/html5/thumbnails/18.jpg)
8/17/2019 Apresentação - Iris Recognition
http://slidepdf.com/reader/full/apresentacao-iris-recognition 18/37
The Method
Fig 5 – Snakes and corresponding maps
Snakes representing pupil and iris boundaries
Ideal snakes would be flat and straight
![Page 19: Apresentação - Iris Recognition](https://reader030.vdocuments.mx/reader030/viewer/2022021219/577c7ed81a28abe054a28536/html5/thumbnails/19.jpg)
8/17/2019 Apresentação - Iris Recognition
http://slidepdf.com/reader/full/apresentacao-iris-recognition 19/37
The Method
There is a tradeoff between simplicity of the model
and its precision
Number of terms used on the Fourier Series (M)
Empirically, the author found good approximations
for values M=17 (pupil) and M=5 (iris)
![Page 20: Apresentação - Iris Recognition](https://reader030.vdocuments.mx/reader030/viewer/2022021219/577c7ed81a28abe054a28536/html5/thumbnails/20.jpg)
8/17/2019 Apresentação - Iris Recognition
http://slidepdf.com/reader/full/apresentacao-iris-recognition 20/37
OFF-AXIS GAZE
CORRECTION
![Page 21: Apresentação - Iris Recognition](https://reader030.vdocuments.mx/reader030/viewer/2022021219/577c7ed81a28abe054a28536/html5/thumbnails/21.jpg)
8/17/2019 Apresentação - Iris Recognition
http://slidepdf.com/reader/full/apresentacao-iris-recognition 21/37
Off-Axis Gaze Correction
Model requires an on-axis image of the eye
Stop-and-stare interface
Correcting the projective deformation on the iriswhen its image is off-axis
The essence of the problem is estimating the anglesof gaze relative to the camera
Eye morphology is so variable that is unlikely that this factor
could support a robust estimation
![Page 22: Apresentação - Iris Recognition](https://reader030.vdocuments.mx/reader030/viewer/2022021219/577c7ed81a28abe054a28536/html5/thumbnails/22.jpg)
8/17/2019 Apresentação - Iris Recognition
http://slidepdf.com/reader/full/apresentacao-iris-recognition 22/37
Off-Axis Gaze Correction
Obvious alternative approach shape of pupil
Estimating the ellipticity of the pupil and orientation
of that ellipse would yield the gaze deviation
The author proposes something different Fourier-
based trigonometry
![Page 23: Apresentação - Iris Recognition](https://reader030.vdocuments.mx/reader030/viewer/2022021219/577c7ed81a28abe054a28536/html5/thumbnails/23.jpg)
8/17/2019 Apresentação - Iris Recognition
http://slidepdf.com/reader/full/apresentacao-iris-recognition 23/37
Off-Axis Gaze Correction
Fourier series expansions of the X- and Y-
coordinates of the pupil contains shape distortion
information related to the deviated gaze
If the pupil boundary is a circle, this method is
reduced to the previous one
Estimating these parameters gaze deviation to
be reversed by an affine transformation of the off-
axis image
![Page 24: Apresentação - Iris Recognition](https://reader030.vdocuments.mx/reader030/viewer/2022021219/577c7ed81a28abe054a28536/html5/thumbnails/24.jpg)
8/17/2019 Apresentação - Iris Recognition
http://slidepdf.com/reader/full/apresentacao-iris-recognition 24/37
Off-Axis Gaze Correction
Fig 6 – Off-Axis Gaze Correction
![Page 25: Apresentação - Iris Recognition](https://reader030.vdocuments.mx/reader030/viewer/2022021219/577c7ed81a28abe054a28536/html5/thumbnails/25.jpg)
8/17/2019 Apresentação - Iris Recognition
http://slidepdf.com/reader/full/apresentacao-iris-recognition 25/37
DETECTING AND
EXCLUDING EYELASHES
![Page 26: Apresentação - Iris Recognition](https://reader030.vdocuments.mx/reader030/viewer/2022021219/577c7ed81a28abe054a28536/html5/thumbnails/26.jpg)
8/17/2019 Apresentação - Iris Recognition
http://slidepdf.com/reader/full/apresentacao-iris-recognition 26/37
Detecting and excluding eyelashes
Eyelashes can occlude parts of the eye
Usually have random and complex shapes
Can be the strongest signals in iris images, in terms
of contrast and energy
They could dominate the image with spurious information
Fi 7 – E elashes occludin arts of the e e
![Page 27: Apresentação - Iris Recognition](https://reader030.vdocuments.mx/reader030/viewer/2022021219/577c7ed81a28abe054a28536/html5/thumbnails/27.jpg)
8/17/2019 Apresentação - Iris Recognition
http://slidepdf.com/reader/full/apresentacao-iris-recognition 27/37
Detecting and excluding eyelashes
Employment of statistical estimation methods that
depend essentially on determining whether the
distribution of iris pixels is multi-modal
If the lower tail of the iris pixel histogram supports
na hypothesis of multi-modal mixing, then an
appropriate threshold can be computed
Fi 8 – Histo ram and threshold com utation
![Page 28: Apresentação - Iris Recognition](https://reader030.vdocuments.mx/reader030/viewer/2022021219/577c7ed81a28abe054a28536/html5/thumbnails/28.jpg)
8/17/2019 Apresentação - Iris Recognition
http://slidepdf.com/reader/full/apresentacao-iris-recognition 28/37
EVALUATION
![Page 29: Apresentação - Iris Recognition](https://reader030.vdocuments.mx/reader030/viewer/2022021219/577c7ed81a28abe054a28536/html5/thumbnails/29.jpg)
8/17/2019 Apresentação - Iris Recognition
http://slidepdf.com/reader/full/apresentacao-iris-recognition 29/37
Evaluation
Comparison between IrisCodes (bit pair Bernoulli
trials)
Areas obscured by eyelids, eyelashes or byreflections from eyeglasses are processed and
prevented to influence the iris comparisons
IrisCodes keep the information about the phases
and are compared through bit-wise mask functions
![Page 30: Apresentação - Iris Recognition](https://reader030.vdocuments.mx/reader030/viewer/2022021219/577c7ed81a28abe054a28536/html5/thumbnails/30.jpg)
8/17/2019 Apresentação - Iris Recognition
http://slidepdf.com/reader/full/apresentacao-iris-recognition 30/37
Evaluation
Code related to each iris is ExclusiveOR’ed and
AND’ed to mask functions
Raw Hamming distance used to compared to irises:
The number of bits pairings available for
comparison is usually nearly a thousand
![Page 31: Apresentação - Iris Recognition](https://reader030.vdocuments.mx/reader030/viewer/2022021219/577c7ed81a28abe054a28536/html5/thumbnails/31.jpg)
8/17/2019 Apresentação - Iris Recognition
http://slidepdf.com/reader/full/apresentacao-iris-recognition 31/37
Evaluation
Restrictions related to the ‘behaviour’ of masks
Must take into account the amount of comparison
data that was available
A normalization is performed in order to improve
the confidence level score normalization
![Page 32: Apresentação - Iris Recognition](https://reader030.vdocuments.mx/reader030/viewer/2022021219/577c7ed81a28abe054a28536/html5/thumbnails/32.jpg)
8/17/2019 Apresentação - Iris Recognition
http://slidepdf.com/reader/full/apresentacao-iris-recognition 32/37
LARGE-SCALE
APPLICATIONS
![Page 33: Apresentação - Iris Recognition](https://reader030.vdocuments.mx/reader030/viewer/2022021219/577c7ed81a28abe054a28536/html5/thumbnails/33.jpg)
8/17/2019 Apresentação - Iris Recognition
http://slidepdf.com/reader/full/apresentacao-iris-recognition 33/37
Large-Scale applications
Score distribution for 200 Billion Different Iris Comparisons
Fig 9 – Hamming Distance of different irises
![Page 34: Apresentação - Iris Recognition](https://reader030.vdocuments.mx/reader030/viewer/2022021219/577c7ed81a28abe054a28536/html5/thumbnails/34.jpg)
8/17/2019 Apresentação - Iris Recognition
http://slidepdf.com/reader/full/apresentacao-iris-recognition 34/37
Large-Scale applications
Use of thresholds to compute the similarity of one iris to
another
![Page 35: Apresentação - Iris Recognition](https://reader030.vdocuments.mx/reader030/viewer/2022021219/577c7ed81a28abe054a28536/html5/thumbnails/35.jpg)
8/17/2019 Apresentação - Iris Recognition
http://slidepdf.com/reader/full/apresentacao-iris-recognition 35/37
OBRIGADO !
![Page 36: Apresentação - Iris Recognition](https://reader030.vdocuments.mx/reader030/viewer/2022021219/577c7ed81a28abe054a28536/html5/thumbnails/36.jpg)
8/17/2019 Apresentação - Iris Recognition
http://slidepdf.com/reader/full/apresentacao-iris-recognition 36/37
REFERENCES
![Page 37: Apresentação - Iris Recognition](https://reader030.vdocuments.mx/reader030/viewer/2022021219/577c7ed81a28abe054a28536/html5/thumbnails/37.jpg)
8/17/2019 Apresentação - Iris Recognition
http://slidepdf.com/reader/full/apresentacao-iris-recognition 37/37
References
1. John Daugman. Iris Recognition. In: Handbook of Biometrics,
Springer, USA (2008)
2. Enrique A. Velasco. Connections in Mathematical Analysis: The
Case of Fourier Series. In: American Mathematical Monthly,v.99, USA (1992).
3. Michael Kass, Andrew Witkin and Demetri Terzopoulos.
Snakes: Active Countor Models. In: International Journal ofComputer Vision, p. 321-331. (1998)