3. Introduction
“Biometrics is the science of verifying and
establishing identity of an individual
through physiological features or
behavioral traits.”
Biometric is more about what you are than
what you have or know
Password and tokens are not reliable
4. Introduction…
Biometric has been used since 14th
century in china
Everyone have unique physical or
behavioral characteristics and so unique
Identity
Enhanced convenience and augmented
security measure
5. Biometric Recognition
Biometric modalities
Physical Biometrics:
Face, Fingerprints, Iris-scans, Hand
geometry
Behavioral Biometrics:
Speech, Signature, and Keystroke dynamics
Chemical biometrics:
Odor and the chemical composition of human
perspiration
6. Iris
Iris is the area of the eye
where the pigmented or
coloured circle, usually
brown, blue, rings the dark
pupil of the eye
Image is typically captured
using a noncontact imaging Iris portion
process
Iris should be at the
predetermined distance
from the focal plane of the
camera
7. Face Recognition
Method of acquiring face
images is nonintrusive
Facial disguise is of concern
in unattended recognition
applications
It is challenging to develop
techniques that can tolerate
the effects of aging, facial
expression, variations in the
imaging environment
8. Hand and Finger
Geometry
Features related to the human
hand are relatively invariant and
peculiar to an individual
System requires cooperation of
the subject to capture frontal and
side view images of the palm
flatly placed on a panel with
outstretched fingers
Only used for verification
9. Hand Vein
Recognition
Back of a clenched fist
used to determine hand
vein structure
Systems for vein capture
use inexpensive infra-red
light emitting diodes
10. Voice
Recognition
Voice capture is unobtrusive and
only feasible applications
requiring person recognition
over a telephone
Voice signal available for
recognition is typically degraded
in quality by the microphone,
communication channel
Voice is affected by factors such
as a person‟s health, stress and
emotional state
11. Signature
The way a person signs his
name is known to be a
characteristic of that individual
Signature is a behavioural
biometric that changes over
time
Professional forgers can
reproduce signatures of others
to fool the unskilled eye
12. Biometric Systems
An important issue in designing a practical
biometric system is to determine how an
individual is going to be recognized
Biometric system
Enrolment
Verification system
Identification system
13. Enrolment
Subject
Identifier
Template
Identifier
Feature Template
Extraction Data
Creation Storage
Sample Feature set
Capture
Enrolment Process
14. Verification
Subject
Identifier Claimed Identity
Feature
Extraction Matching Data
Storage
Sample Feature set One Subjects
Capture
template
Match or
Non-Match
Verification Process
15. Identification
Subject
Identifier
Feature Pre-selection
Extraction and Data
Matching Storage
Sample Feature set ‘N’ Subject
Capture
Templates
Subject Identified
Or not Identified
Identification Process
16. Architecture
Biometric sensor Feature
extraction
Database
Enrolment
Biometric sensor Feature extraction
Matching
Authentication Result
General architecture of a biometric system
18. Fingerprint
Skin on human fingertips contains
ridges and valleys which together
forms distinctive patterns
These patterns are fully developed
under pregnancy and are permanent
throughout whole lifetime
No two persons have the same
fingerprints
Automatization of the fingerprint
recognition process turned out to be
success in forensic applications
21. Fingerprint Feature
Minutiae Based Approach
Minutiae is the unique, measurable physical
point at which ridge bifurcate or ends
Ridge Ending Ridge Bifurcation
22. Fingerprint Recognition
System
Minutiae Minutiae
Extractor Matcher
Sensor
Architecture for Fingerprint Recognition System
23. Fingerprint Sensing and
Storage
Off- line scan or live scan
A special kind of off-line
images, extremely
important in forensic
applications, are the so-
called latent fingerprints
found at crime scenes
24. Live Scan Devices
Fingerprint image acquisition is
the most critical step of an
automated fingerprint
authentication system
Idea behind each capture
approach is to measure in some
way the physical difference
between ridges and valleys
Physical principles like
capacitive, optical and thermal
are used
26. Minutia Extraction
Pre-Processing
Fingerprint Image Enhancement
Fingerprint Image enhancement is to
make the image clearer for easy further
operations
Increase the contrast between ridges and
furrows and connect the broken points
27. Minutia Extraction...
Histogram Equalization
Histogram equalization is to expand the pixel value
distribution of an image so as to increase the
perceptional information
The Original Histogram of a Histogram after histogram
fingerprint image equalization
29. Minutia Extraction...
Fingerprint Image
Binarization
8-bit Gray fingerprint image
transform to a 1-bit image
with 0-value for ridges and 1-
value for furrows
Ridges in the fingerprint are
highlighted with black colour
while furrows are white
30. Minutia Extraction...
Fingerprint Image Segmentation
Region of Interest (ROI) is useful to be
recognized for each fingerprint image
Two step method is based on Morphological
methods
ROI extraction by Morphological
operations
Two Morphological operations called „OPEN‟ and
„CLOSE‟ are adopted
32. Minutia Extraction...
Minutia Extraction
Fingerprint Ridge Thinning
Ridge Thinning is to eliminate the redundant pixels of
ridges
Minutia Marking
If the central pixel is 1 and has exactly 3 one-value
neighbours, then the central pixel is a ridge branch
If the central pixel is 1 and has only 1 one-value
neighbour, then the central pixel is a ridge ending
38. The Matching Module
The matching module use a pre-processed pattern
composed by the fingerprint, it‟s minutia-file and
it‟s constellations,
These patterns are extracted from enrolled
templates
Feature extraction is done then its patterns are
compared to the reference ones
Comparison between the two fingerprints
Constellation matching
Minutiae matching
39. Constellation Matching
When a new fingerprint is scanned it is passed
by the feature extraction module, a set of
constellations and their respective parameters
are created
Comparison with the genuine constellations set
extracted during system enrolment
F1 = {C1.0, C1.1, C1.2, C1.3}
F2 = {C2.0, C2.1, C2.3, C2.4, C2.5}
Euclidean distance between the point patterns
of constellations centres
40. Constellation Matching
Rejects a fingerprint template
No constellation is matched D = 0
A unique constellation that includes less than 15
minutiae is matched D = 0
Co1.0 Co2.0
Co2.1
Co1.1
Co2.3
Co2.2
Co1.3
Co1.2
Fingerprint constellation matching
41. Minutiae Matching
Minutiae matching are performed within a
constellation
The minutiae matching are used as a second
level verification
minutiae matching algorithm proceeds as
follow
Associate minutiae points
Compute distance between minutiae
Decide
42. Minutiae Matching
Flow Chart
Start
Decision=reject Fingerprint and
constellation
Constellation files
Matching
NO
D<CTH CTH
Minutiae
Matching
NO
D<MTH MTH
Decision=Accept
END
43. Applications of Fingerprint Recognition System
Physical Access Control
Logical Access Control
Transaction Authentication
Device Access Control
Time and Attendance
Civil Identification
Forensic Identification
44. Limitations
Dirt , grime and wounds
Placement of finger
Too big database to process
Liveness important
In case of permanent finger injury
45. Barriers to Adoption
Business value is difficult to quantify in terms of
return on investment
Fingerprint recognition systems, being an emerging
technology, is sometimes confronted with unrealistic
performance
The quality varies quite dramatically from one
application to another and from one vendor to
another
Several fingerprint system vendors are not
financially stable
46. Conclusions
Most highly used methods for human recognition
Fingerprint system strongly relies on the precision
obtained in the minutia extraction process
Industrial commitment led to next generation
fingerprint technology
It has got broad acceptance from forensic to
handheld devices
Used for securing international borders
47. References
[1] FBI Fingerprint guide. Available online at
http://www.fbi.gov/hq/cjisd/takingfps.html
[2] Fingerprint. Available online at
http://en.wikipedia.org/wiki/Fingerprint
[3] Fingerprint recognition. Available online at
http://en.wikipedia.org/wiki/Fingerprint recognition
[4] Goyal, A., Study of Fingerprints Minutia Extraction and matching
Technique. Available online at
http://www.advancedcenterpunjabi.org/MTechP/Anjna%20Goyal_
M.Tech(CS).pdf
48. References...
[5] Human Fingerprints. Available online at
http://ww.fingerprinting.com/human-fingerprints.php
[6] Maltoni, D., Maio, D., Jain, A., Prabhakar, S.,(2009), Handbook of
Fingerprint Recognition, second edition, Springer Limited.
[7] Murmu, N., Otti, A., Fingerprint recognition. Available online at
http://ethesis.nitrkl.ac.in/955/
[8] Rokbani, N., Alimi, A., Fingerprint identification using minutiae
constellation matching. Avialable online at
http://www.regim.org/publications/conferences/2005/2005_MCCSIS_
RA.pdf