ES

V I C
D E
R I C
E T
I O M
B

1
 DEFINITION
• Biometrics - (Classical Definition) Identification of
living things based on physiological and/or
behavioral characteristics
• Biometrics - (ISO Definition) A measurable, physical
characteristic or personal behavioral trait used to
recognize the identity, or verify the claimed identity,
of an enrollee.
• Biometric System – (ISO Definition) An automated
system capable of:
– capturing a biometric sample from an end user;
– extracting biometric data from that sample;
– comparing the biometric data with that contained in one
or more reference templates;
– deciding how well they match; and
– indicating whether or not an identification or verification
of identity has been achieved. 2
 HISTORY OF BIOMETRICS
• Used since man first walked upright
– We all use facial recognition on a daily basis
– We use voice recognition during conversations to
identify the other party (e.g. Telephone)
• Fingerprints have been used in forensics for over 100
years by police investigators
• Babies registered at birth using palm/foot prints
• Dental records and X-rays have long been used to identify
decomposed bodies
• The hand written signature is a form of behavioral
biometric identification
• DNA is one of the latest advances used in identification

3
Your body as password?? 4
 HOW BIOMETRIC DEVICES WORK
• With all biometric systems there are 3 steps :
– Data Capture
• All biometrics start with a piece of raw analogue
data (e.g. fingerprint, voice sample,
face/hand/retina image)
– Signal Processing
• This raw data is digitized so that computers can
process it
• The computer software extracts the critical
features (e.g. minutiae) and discards those
elements that are irrelevant to making a
successful comparison (i.e. creates template)
– Decision
• The stored and live templates are compared and
if they match (i.e. within set threshold) user will
be accepted 5
6
 BIOMETRIC APPLICATIONS

• Depending on the application, biometrics can be used for

security, privacy, convenience, fraud reduction, or to deliver
enhanced services. Applications include:
– Physical security and access control (e.g. borders, airports)
– Computer/Network logins (e.g. laptops with fingerprint
sensors built in)
– Business transactions (e.g. ATM withdrawals)
– Credit and debit card protection
– Voting
– Receiving government benefits (e.g. welfare, pension)
– Healthcare services (e.g. patient ID)
– Law enforcement (e.g. drivers licenses, vehicle registration,
smart guns, criminal identification systems)
– Identification Documents (e.g. Visas, passports, SIN cards,
Military/Govt/Corporate ID cards)
– Registering race horses, research animals, pets and other
wildlife
– Data protection (e.g. biometric tokens) 7
 FINGER/THUMB PRINT READERS
• Most widely used
• Most systems rely on classifying the
differences between ridges and
valleys in the patterns of the print
and at ridge bifurcations or ridge
endings (i.e. minutiae)
• Produces one of the largest
templates (aprox 1KByte)
depending on the method used
• Devices are very reliable in use but
in some cases other techniques
may be required
• Several types (e.g. optical,
capacitive, ultrasound, RF)
8
 FINGERPRINT (continued)
• Fingerprint matching techniques can be placed into two
categories: minutiae-based and correlation based.
– Minutiae-based techniques first find minutiae points and
then map their relative placement on the finger. However,
there are some difficulties when using this approach.
• It is difficult to extract the minutiae points
accurately when the fingerprint is of low quality.
• Also this method does not take into account the
global pattern of ridges and furrows.
• More subject to wear and tear, and false minutiae.

9
The correlation-based method is able to
overcome some of the difficulties of the
minutiae-based approach. However, it has
some of its own shortcomings.
Correlation-based techniques (i.e. pattern
matching) require the precise location of a
registration point and are affected by image
translation and rotation.
Larger templates (often 2 – 3 times larger than
minutiae-based)

10
 FINGERPRINT
• Intrusive procedure
(continued)
• In 1997 the stamp-sized fingerprint reader on a
microchip was introduced which has led to the potential
for many new applications (e.g. securing smartcards)
• A much smaller “scrolling” sensor is now available which
has made even more applications possible and has
addressed some of the security concerns with latent
prints
• Some more advanced readers can differentiate between
live and dead tissue
– by checking for pulse
– by sensing oxygen level
– by checking capacitance of the biometric sample
11
 Issues and Concerns
With Biometrics becoming available, individuals
could:
– Plant DNA at the scene of a crime
– Fool a fingerprint detector with a piece of tape
– Fool an iris detector with a picture of an eye
– Break into the system and make a “fail” code a
“pass” code
 Matsumoto’s Technique

• Only a few dollars’ worth of materials

13
 Making the Actual Clone

You can place the “gummy finger” over your real finger. Observers
aren’t likely to detect it when you use it on a fingerprint reader.
(Matsumoto)
14
Hand geometry is a form of physiological biometrics that uses the
shape of the hand for authentication purposes. Various traits of
the hand, such as finger length, width and curvature, as well as
unique features may be used for identification. [1] Hand geometry
scan require that users place their hands onto a surface with 5
pegs. This aligns the hand so that the scanner can get a
consistent reading on each scan. The scan is then compared to
the database for verification. A typical scan will take two pictures
of the hand: one of the top and one of the side.
15
Hand geometry is not a unique form
of biometric security. More than one
person may have the same or very
similar hand shapes. This limits the
usefulness of hand geometry to
verification, not identification.
Combining hand geometry with
another form of biometric security,
such as fingerprint biometrics, would
provide a very secure identification
system. A system where hand
geometry was used to verify the
fingerprint input would add an
additional layer of security and create
a very effective identification system.
16
Technology + -

Fingerprint •Popular •Less Accurate

•Cheapest

Voice •Non invasive •Least Accurate

Iris & Retinal •Very accurate •Invasive

•Expensive
•Sensitive

Palm Vein •Non-invasive •Unfamiliar

•Relatively Cheap
•Accurate

17
 HOW IT WORKS

•Takes snapshot of palm veins

•Converts into algorithm
•Compares with database

18
 Accuracy
TECHNOLOGY FALSE ACCEPTANCE RATE FALSE REJECTION RATE

Palm Secure .00008% .01%

Fingerprint 1-2% 3%

Iris .0001% - .94% .99% - .2%

Voice 2% 10%

• Vein patterns
– Distinctive and unique to individuals, even left and right
hands. Difficult to steal or forge
• False acceptance rate : A rate at which someone other
than the actual person is falsely recognized.
• False rejection rate : A rate at which the actual person is
not recognized accurately. 19
 Practical Application
• ‘Palm Secure’ is now widely
used in various fields.
– ATM
• 92% of all Japanese ATMs
• 18,000+ ATM machines for
Bank of Tokyo - Mitsubishi
– School ID, Entry Key to ATM Machine
private property, Log-in to
PCs or servers
– Potential is limitless
• PalmSecure mouse with a
build-in sensor in 2007
– easily installed to personal
computer.

Portable Mouse
20
 FACIAL RECOGNITION
• Considered by some as an intrusive system
• Uses high resolution cameras (several types) to take
pictures of the face for comparison
• The four primary methods traditionally employed by
facial scan vendors to identify and verify subjects
include eigenfaces, feature analysis, neural network,
and automatic face processing
• New systems are being developed that measure three
dimensional characteristics of the face
• One of the fastest growing areas in biometric industry

21
 FACIAL (continued)
Source: MIT Face Recognition Demo Page

Source: biometrics.cse.msu.edu/info.html

22
 FACIAL (continued)
• Eigenface: "one's own face," a technology patented at MIT that uses
2D global grayscale images representing distinctive characteristics of
a facial image. Most faces can be reconstructed by combining
features of 100-125 eigenfaces. During enrollment, the user's
eigenface is mapped to a series of numbers (coefficients). Upon a 1:1
match, a "live" template is matched against the enrolled template to
obtain a coefficient variation. This variation either accepts or rejects
the user.
• Local Feature Analysis (LFA): also a 2D technology, though more
capable of accommodating changes in appearance or facial aspect
(e.g., smiling, frowning). LFA uses dozens of features from different
regions of the face; incorporates the location of these features.
Relative distances and angles of the "building blocks" of the face are
measured. LFA can accommodate 25-degree angles in the horizontal
plane and 15 degrees in the vertical plane. LFA is a derivative of the
eigen face method and was developed by Visionics, Corp.
23
 FACIAL (continued)
• Automatic Face Processing (AFP): This 2D
technology uses distances and distance ratios
between eyes, nose, and corners of mouth. Not as
robust as the other technologies, but may be more
affective in dimly lit, frontal image capture
situations.
• Neural Networks: use algorithms that use as much
of the face as possible. These algorithms run as
the human brain would in cognition to learn about
facial features. Neural networks are a step up from
LFA.
24
 FACIAL (continued)
• New Volumetric-based 3D Processing Systems: Create a
template of the face that is based on tens-of-thousands of
points on the face, thus forming a very high-resolution
interpretation of the subject.
– A 3D laser camera takes a picture of the face and
represents it within a virtual cube.
• The input starts as a digital image and does not
need to be converted
– The secret to a true 3D method lies in the ability to use
direct measurements to compare individuals.
• That is, rather than the traditional method of an
indirect search for facial features on an image,
these systems look at specific points within a
millimeter apart.. 25
 Eye biometric
 Retina:
–back inside of the eye
ball.
–pattern of blood vessels
used for identification.

 Iris:
–coloured portion of the
eye surrounding the pupil.
– complex iris pattern used
for identification.
26
 Retina
• The retina is a thin layer of cells at the back of the eyeball
of vertebrates.
• It is the part of the eye which converts light into nervous
signals.
• The retina contains photoreceptor cells (rods and cones)
which receive the light; the resulting neural signals then
undergo complex processing by other neurons of the retina,
and are transformed into action potentials in retinal ganglion
cells whose axons form the optic nerve.
• The retina not only detects light, it also plays a significant
part in visual perception.
• In embryonic development, the retina and the optic nerve
originate as outgrowths of the brain.
• The unique structure of the blood vessels in the retina has
been used for biometric identification.

27
 II.Retina recognition

• The pattern of blood vessels that emanate

from the optic nerve and disperse throughout
the retina depends on individuals and never
changes.
• No two retinas are the same, even in identical
twins.
• Commercial products: Retinal Technologies

28
 RETINA SCANNERS
• Rely on the uniqueness of the pattern of blood vessels
lining the retina
• Users place their eyes a few inches from an incandescent
light beam and the sensor maps the capillary pattern by
measuring reflected light
• People with high blood pressure, diabetes or glaucoma
may give inconsistent readings
• Template aprox 35 Bytes and extremely reliable
• Primary use is in high security access control

29
RETINA SCANNERS (continued)

Camera Enrollment device

Source: Biometrics Store Website

30
RETINA SCANNERS (continued)

Main retina features Actual photo of retina

Source: American Academy of Ophthalmology

31
Iris scans offer some marked improvement
over retinal scans.  The iris has a mesh-like
texture with many overlays that produce
crypts, furrows, ridges, striations, and other
unique characteristics that overall provide a
unique blueprint of the iris. Unlike retinas,
which can change with age due to diseases
such as diabetes or glaucoma, the iris does
not change during a person’s lifetime. 

32
Iris recognition is becoming very popular in
security applications because of its ease of
use, accuracy, and safety but also because
the technology only takes a few seconds to
deliver results, whereas DNA or fingerprint
identification will take weeks or even months.
  An iris pattern is extremely accurate
because it uses more than 240 points of
reference in a basis for a match whereas a
fingerprint only uses seven to 24 references. 
Wearing glasses or contact lenses does not
change or affect the imaging results or the
identification process.  Many airports and
schools are testing the iris scan as a part of
their security systems.

33
 IRIS SCANNERS
• High resolution cameras capture image from up to 3 feet away
(usually 10 to 12 inches)
• Converts picture of the distinctive fibers, furrows, flecks,
crypts, rifts, pits and coronas of the iris into a bar-code like
identifier
• Template around 256 Bytes in size
• Human iris is distinct with 250 differentiating features
• The recognition of irises by their IrisCodes is based upon the
failure of a test of statistical independence.
– Any given IrisCode is statistically guaranteed to pass a test of
independence against any IrisCode computed from a different eye;
but it will uniquely fail this same test against the eye from which it
was computed. Thus the key to iris recognition is the failure of a test
of statistical independence.
34
 Iris properties
• Iris pattern possesses a high degree of randomness:
extremely accurate biometric.
• Genetically independent: identical twins have
different iris pattern.
• Stable throughout life.
• Highly protected, internal organ of the eye.
• Patterns can be acquired from a distance (1m).
• Patterns can be encoded into 256 bytes.

35
 IRIS (continued)
• Idea for iris scanning has been around since 1936
• Processing time is very quick (less than 2 secs)
• Does not use any special beams or lighting
instead uses a camera with a high quality lens
• Works well with people wearing contact lenses or
glasses and at night with normal lighting
• Advances in refractive and cataract surgery and
cornea transplants don't change iris’ aspects
Note: New contact lenses with artificial iris patterns, etc. have
potential to defeat these systems, however, security mechanisms
can be built in to protect against these attacks (i.e. perform
“liveness” tests) 36
IRIS (continued)

Condominium
residents in Tokyo
gain entry to the
building by their iris
patterns, and the
elevator is
automatically
called and
programmed to
bring them to their
residential floor.
Source: biometrics.cse.msu.edu/info.html
37
 IRIS (continued)
Frequent Flyers at
Schiphol Airport (NL)
may enroll in the
"Privium" programme,
enabling them to enter
The Netherlands
without passport
presentation. Instead
they are recognised by
an iris camera, avoiding
lines and delays at
Immigration Control.
Source: biometrics.cse.msu.edu/info.html

38
 I. DNA
• DNA has been called the “ultimate identifier”
• Identify information from every cell in the body in a
digital form
• Not yet fully automated, not fast and expensive
• Theoretical limitation: Identical twins have the same
DNA
• Privacy issue – DNA contains information about race,
paternity, and medical conditions for certain disease

39
 DNA TESTING
• Perhaps the ultimate identifier (what about
twins/clones?)
– Recent cloning experiments raise questions about its suitability
as a unique identifier
– Identical twins have identical DNA
• Obviously very intrusive
• Not practical for everyday authentication or verification,
only for very high stakes situations
– Criminal forensics
– Paternity
• Process is currently not automated
• Time intensive
– Process takes from 2-4 hours 40
How DNA recognition works?
The cells that contain DNA share genetic
material (information) through chromosomes.
Humans have 23 chromosomes that house a
person’s DNA and their genes. Of the 46 total
chromosomes, 23 come from each parent of
an offspring. 99.7% of an offspring’s DNA is
shared with their parents. The remaining .3%
of an individuals DNA is variable repetitive
coding unique to an individual. This repetitive
coding is the basis of DNA biometrics. DNA
recognition uses genetic profiling, also called
genetic fingerprinting, to isolate and identify
these repetitive DNA regions that are unique
to each individual to either identify or verify a
person’s identity.
41
 VOICE VERIFICATION
• A completely non-intrusive technique
• Examines tonal wave patterns that cannot be imitated
by other individuals (voice patterns of impersonators
are different than the real voice pattern)
• Analog recordings cannot reproduce accurate tone
patterns, but digital recordings may be able to do so
– Random question and answer techniques, and pattern
matching (i.e. comparing successive voice samples) may help
to prevent reply attacks based on digital voice recordings
• Most appropriate method for telephone use
• People with colds & laryngitis can affect FRR
– although slight variations can be compensated for
• Signal quality can introduce errors (e.g. bad phone line,
noise in background)
42
 VOICE VERIFICATION (continued)
A complete signal has an
overall pattern, as well as a
much finer structure, called
the frame. This frame is the
essence of voice verification
technology.

It is these well-formed, regular

patterns that are unique to
every individual. These patterns
are created from the size and
shape of the physical structure
of a person's vocal tract. Since
no two vocal tracts are exactly
the same, no two signal
patterns can be the same.
 VOICE VERIFICATION (continued) Hard palate Tongue

These unique features Soft palate Nasal

consist of cadence, Cavity

pitch, tone, harmonics, Phayngeal Nostral

cavity Lip

and shape of vocal tract. Larynx

Teeth

Oral (or
Buccal)

The image at right Esophagus Cavity

shows how Jaw

characteristics of voice Trachea

actually involve much Lung

more of the body than Diaphram

just the mouth.

44
 SIGNATURE ANALYSIS
• These devices quantify speed, pressure, angle-of-attack
and stroke characteristics (40 plus)
• A typical system will take up to 100 elements of speed,
pressure, etc to characterize an individual
• User stress can affect the accuracy of this device
• Signatures tend to change over time
• These types of devices are now starting to make their way
into practical everyday use

45
 SIGNATURE ANALYSIS (continued)
Built-in sensors register the dynamics of the act of writing. These dynamics include
the 3D-forces that are applied, the speed of writing, and the angles in various
directions.

This signing pattern is unique for each individual, and thus allows for strong
authentication. It also protects against fraud since it is practically impossible to
duplicate "how" someone signs.
Source: Biometrics Store Website and Smart Pen

46
 KEYSTROKE DYNAMICS
User typing pattern
• Speed
• Press and Release Rate
• Unique patterns are generated
• comparisons
• These devices sample typing patterns up to one
thousand times per second and continuously keep track
of the speed, sequence and rhythm of a users typing
• Both NIST and the National Science Foundation studies
have shown that typing patterns are unique
• Verification occurs seamlessly as the person types
• Still in research and development phase
47
 OTHER TYPES OF DEVICES
• Systems that measure body odor
• Systems that measure knuckle creases
• Palm-vein and wrist-vein recognition
systems
• Acoustic head measurement devices
• Researchers are continually looking for
the ideal biometric device…one that is
universally applicable, totally non-
intrusive, inexpensive, provides
continuos authentication and is extremely
accurate
48
 IX. Body odor
• It’s absolutely clear that people with
differing immunity genes produce
different body odors
• Electronic/artificial noses: developed as a
system for the automated detection and
Prometheus (Alpha
classification of odors, vapors, gases. Mos) ,
an example of electronic
nose
• Artificial noses
are not yet
sophisticated
enough to do all
Schematic Diagram of Artificial nose the job 49
 VI. Ear recognition
• Ear geometry recognition uses
the shape of the ear to perform
identification
• Suggestions have been made
that the shapes and
characteristics of the human
ear are widely different
• An infrared image can be used
to eliminate hair
• Might be recognized at a
distance

50
in the future your ear may become your new
password?   Although recently reports have started to
discredit ear imprints as a valid form of biometric
identification there is another aspect of the ear that
seems to be unique to individuals.  Mammalian, and
hence human, ears emit noises in response to
certain types of audio stimuli; these emitted noises,
called optoacoustic emissions (OAE), may be used
to distinguish individuals because they are thought to
be unique.

51
 VII. Skin reflection

• Lumidigm Inc. has established that the absorption

spectrum of the skin depends on the individuals.
• In a range of wavelengths over 6mm patch,
several LEDs send light into the skin, and
photodiodes read the scattered light, which is
analyzed to perform the authentication.

52
 VIII.Lip motion

• Compares the characteristic lip motions of

people while they speak.
• Helps identification associated with speaker
recognition.
• Different imaging conditions: Infrared (high
security & cost) and Near Infrared (cheap,
normally used for active sensing)

53
54
 NEGATIVE ISSUES
• Some opthamologists warn that a simple retina scan could
indicate that a person has AIDS or uses drugs, which may
have severe privacy impact
• The prospect of interoperable networked databases of
biometric data raises concerns that our templates can be
bought and sold like SIN and credit card numbers, but unlike
those, we cannot change our biometric characteristics if
they become compromised
• Belief that biometric systems are way to difficult and
expensive to implement
• Fears that criminals, etc., will cut off victim’s fingers and
hands or take out eyeballs to defeat systems based on these
technologies
55
 NEGATIVE ISSUES
• In any large scenario some portion of the general
population is likely to be physiologically unable to use
one or more technique
• Certain cultures and religions prohibit or look with great
disfavor upon photographing of individuals.
• One of the most frightening concerns is that these
systems will be used to constantly track us as individuals
by govt., police, etc.
• People value their privacy and fear this technology will
inhibit their ability to preserve their anonymity while
undertaking certain transactions (e.g. buying XXX videos)
• Biometrics may lead to personal profiling by marketing
and other groups
56
 SOCIAL ISSUES (positive)
• People are frustrated having to remember several
passwords and PINs for each system
• Truly non-intrusive continuos systems will allow us to
work without distraction
• Biometric mechanisms will enable the detection of
individuals who are abusing current systems
• Biometric identifiers can’t be forgotten, lost or stolen
as is the case with keys, passwords and tokens
• Implemented correctly will improve security and
privacy

57
 REFERENCES
• http://www.biometrics.org
• http://www.biometricidforum.org/
• www.recogsys.com
• www.iriscan.com
• www.infosecuritymag.com
• http://iosoftware.com
• www.biodigest.com
• www.biometritech.com
• www.ibia.org
• http://www.nationalbiometric.org/
• http://www.biometrics.dod.mil/
• http://www.biometricgroup.com/
• http://www.speechtechmag.com/
58