Scribd
Upload
39 views36 pages

Biometrics: M. Naresh Kumar Christ University, Bangalore

Biometrics is the study of methods for uniquely recognizing humans based on physical or behavioral traits. It provides identification through something the person is (e.g. fingerprints, retina). Fingerprint recognition works by scanning ridge and furrow patterns, while retina recognition analyzes the unique blood vessel patterns behind the eye. Both have very low error rates but retina recognition is more secure as it cannot be forged, though it is more invasive and difficult to capture. Biometrics provides convenient and passive identification compared to tokens or passwords.

Uploaded by

naresh19788
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
39 views36 pages

Biometrics: M. Naresh Kumar Christ University, Bangalore

Biometrics is the study of methods for uniquely recognizing humans based on physical or behavioral traits. It provides identification through something the person is (e.g. fingerprints, retina). Fingerprint recognition works by scanning ridge and furrow patterns, while retina recognition analyzes the unique blood vessel patterns behind the eye. Both have very low error rates but retina recognition is more secure as it cannot be forged, though it is more invasive and difficult to capture. Biometrics provides convenient and passive identification compared to tokens or passwords.

Uploaded by

naresh19788
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 36

Biometrics

M. Naresh Kumar
Christ University,
Bangalore
Definition
Biometrics is the study of methods for
uniquely recognizing humans based upon
one or more intrinsic physical or behavioral
traits.

Bios=“life”,metron=“measure”(ancient
Greek)
Why Biometrics
Only authorized users should access data,
places, services,….

Identity checking is mainly performed in three ways:

Something that you know


-like a password
Something that you have
-a “token” (e.g., credit card)

Something that you are


-the organs itself acts has a password.
(eg fingerprint, retina, palm etc.).
Why the Interest in Biometrics?

Convenient
Passwords are not user-friendly
Perceived as more secure
 May actually be more secure
 May be useful as a deterrent
Passive identification
A timeline of biometric
technology
•European explorer Joao de Barros recorded the first known
example of fingerprinting, which is a form of biometrics, in
China during the 14th century.
 
•In 1890, Alphonse Bertillon, a Parisian police desk studied
body mechanics and measurements to help identify
criminals.

•In the 1960s and '70s, signature biometric


authentication procedures were developed.
 
 
•2001 Super Bowl in Tampa, Florida -- each facial image of the 100,000
fans passing through the stadium was recorded via video security
cameras and checked electronically against mug shots from the Tampa
police.

•Post 9/11 -- after the attacks, authorities installed biometric


technologies in airports to ID suspected terrorists, etc.,

•July 7th, 2005 London, England -- British law enforcement is using


biometric face recognition technologies and 360-degree "fish-eye"
video cameras to ID terrorists.
 
Biometrics Recognition:

Two types of Recognition problems:

 Verification – Is this who he claims to


be?

 Identification – who is this?


Verification
Compare a sample against a single stored
template
Typical application: voice lock

?
Identification
Search a sample against a database of
templates.
Typical application: identifying fingerprints

?
Template Size
Biometric Approx Template Size
Voice 70k – 80k
Face 84 bytes – 2k
Signature 500 bytes – 1000 bytes
Fingerprint 256 bytes – 1.2k
Hand Geometry 9 bytes
Iris 256 bytes – 512 bytes
Retina 96 bytes
Enrolment and Recognition:
Biometrics Recognition
Biometric Sensor:

•Measure biometric characteristic with appropriate


device.
•The resulting data may be an image, a sound,…
•Multiple samples may be used.
•A quality measure may be associated with the measure
Feature extraction:

•Pre-processing(e.g., removal of noise, removal of unwanted


data, normalization,…)
•Failure to enroll
•Convert the data into a “numeric” feature template
•…

Matching:

•Compare the extracted template with the previously enrolled


biometric templates
•Determine a degree or similarity and output a matching score.
Decision:

•Matching scores are campare to a threshold.


•Above threshold -> match
•Below threshold -> no match

Accuracy measures:

•False Acceptance Rate(FAR) and False Rejection Rate(FRR)


 Error rates at different thresholds
 Used to set opetating threshold.
•Score Distribution
 Frequency of client and imposter scores
 Small overlap suggests and good system.
Biometrics modalities
Fingerprints
Retina Prints
Face Prints
DNA Identification
Voice Prints
Palm Prints
Handwriting Analysis
Etc…
Biometric modalities
Finger print Biometrics
Finger print Biometrics
• Among all the biometric techniques, fingerprint-based
identification is the oldest method which has been
successfully used in numerous applications.

•A fingerprint is made of a series of ridges and furrows


on the surface of the finger.

•The uniqueness of a fingerprint can be determined by


the pattern of ridges and furrows as well as the minutiae
points.
Finger-scan
A live acquisition of a
person’s fingerprint.
Image Acquisition 
Image Processing 
Template Creation 
Template Matching
Acquisition Devices:
 Glass plate

 Electronic

 Ultrasound
Fingerprint
Strengths:
 Fingerprints don’t change over
time
 Widely believed fingerprints are
unique
Weaknesses:
 Scars
Attacks:
 Surgery to alter or remove
prints
 Finger Decapitation
 “Gummy fingers”
 Corruption of the database
Block Diagram
•Most readers work by scanning the print by illuminating it
with a light source – either a laser or, more commonly, a
LED (Light Emitting Diode).

•Finger prints can be covered by callus or worn smooth


from heavy use or dirt can get into the print lines and skin
can peel, which makes print reading more difficult.

•It is important to have rapid access to all stored prints so


that multiple prints don't get associated to the same code.
Fingerprint matching
•Fingerprint matching techniques can be placed into two
categories:

•Minutiae-based techniques first find minutiae points and


then map their relative placement on the finger. 
•Correlation-based techniques require the precise location
of a registration point and are affected by image
translation and rotation.
Retina Recognition
•Retina scans require that the person removes their
glasses, place their eye close to the scanner, stare at a
specific point.

• A retinal scan involves the use of a low-intensity


coherent light source, which is projected onto the retina
to illuminate the blood vessels which are then
photographed and analysed.

•A coupler is used to read the blood vessel patterns.


•A retina scan cannot be faked as it is currently
impossible to forge a human retina.

•A retinal scan has an error rate of 1 in 10,000,000,


compared to fingerprint identification error being
sometimes as high as 1 in 500.
Retina Scan
Image Acquisition 
Image Processing 
Template Creation 
Template Matching
Uses to date:
 Physical access

control
 Computer

authentication
Retina Scan:
Strengths:
 300+ characteristics; 200 required for match

Weaknesses:
 Fear

 Discomfort

 Proprietary acquisition device

 Algorithms may not work on all individuals

 No large databases

Attacks:
 Surgery (Minority Report )
How retina recognition works
•The Retina is an internal organ of the eye -- perhaps the only
internal organ of the body that is routinely visible from outside
–

•The Retina is located behind the posterior of the eye, The


network of blood vessels in the retina is so complex.

•The blood vessels within the retina absorb light more readily
than the surrounding tissue and are easily identified with
appropriate lighting.
• Because Retinal blood vessels are more absorbent or
this light than the rest of the eye, the amount of reflection
varies during the scan.

•The pattern of variation is converted to computer code


and stored in a database.
Advantages
•Highly protected, internal organ of the eye

•Externally visible; patterns imaged from a distance

• search speed: 100,000 RetinaCodes per second on


300MHz CPU

•Image analysis and encoding time: 1 second

•Encoding and decision-making are tractable


Disadvantages
•Small target (1 cm) to acquire from a distance (1 m)

•Moving target ...within another... on yet another

•Located behind a curved, wet, reflecting surface

•Obscured by eyelashes, lenses, reflections

•Partially occluded by eyelids, often drooping


Thank you……

You might also like