In the terms of computer security, biometrics refers
to authentication techniques that rely on measurable
physiological and individual characteristics that can be
A Biometric System is a system for the automated
recognition of individuals based on their behavioral
and biological characteristics.
Depending on the context, in a biometric system, there
are two different ways to resolve a person’s identity
Verification:- Comparing a sample against a single
stored template is called verification
Identification :- Search a sample against a database of
1) Physical biometrics:
Fingerprint—Analyzing fingertip patterns
Facial recognition/face location—Measuring facial
Hand geometry—Measuring the shape of the hand
Iris scan—Analyzing features of colored ring of the eye.
Retinal scan—Analyzing blood vessels in the eye
Vascular patterns—Analyzing vein patterns
DNA—Analyzing genetic makeup.
Earprint—this method is based on geometric distances, force
It actually have
The distance between eyes
Size of mouth
It is sensitive to environmental variables such as dust
and lighting and other factors such as facial expression,
facial hair, hats and spectacles.
Templates are typically between 80 and 1,000 bytes in
The colored ring surrounding
The pupil of the eye
Iris patterns are formed in the eighth month of age and,
remain stable throughout the life of the individual
The iris can have approximately 270 distinct
characteristics including meshwork, striations, rings,
high-quality black and white image of the iris is taken
for processing into a template that is typically around
256 bytes in size.
Retinal scans record the pattern of blood vessels at the
back of the eyeball
The biometric sensor projects a light into the eye and
requires close proximity and a high degree of user cooperation.
Retinal patterns are affected by medical conditions, for
example high blood pressure or eye disease
Retinal scan templates are typically 40 to 100 bytes in
2) Behavioral biometrics:
Speaker/voice recognition—Analyzing vocal
Keystroke/patterning—Measuring the time spacing of
It’s a habitual speaking recognition.
Voice recognition systems analyze differences such as
in pitch, and tone.
This biometric is also sensitive to environmental
conditions such as background noise.
Template size can vary significantly according to the
length of the pass phrase.
This biometric analyses signature characteristics such
as total time, speed, acceleration, character direction,
stroke order, stroke count, pressure and contact with
the writing surface.
These templates are typically 50 to 300 bytes in size.
Similar to signature verification, this measures the
characteristics of an individual’s input of a pass phrase
or password. Characteristics may include total time,
speed with particular keys and pressure.
Again the template size can vary significantly
depending on the length of the password or phrase.
◦ User’s characteristic must be presented to a sensor
◦ Output is a function of:
The way it is presented
Technical characteristics of sensor
2. Signal Processing
◦ Feature extraction
◦ Extract the desired biometric pattern
remove noise and signal losses
discard qualities that are not distinctive/repeatable
Determine if feature is of “good quality”
3. Pattern matching
◦ Sample compared to original signal in database
◦ Closely matched patterns have “small distances” between them
◦ Distances will hardly ever be 0 (perfect match)
◦ Decide if the match is close enough
↓ false non-matches leads to ↑false matches
(token: key, card)
Something you know:
(Password, Pin )
Something you are:
(biometric :physiological, behavioral)
Task( identification, verification)
Number of users
Biometrics is a rapidly evolving technology that is being
widely used in forensics, such as criminal identification and
prison security, and that has the potential to be used in a large
range of civilian application areas.
Biometrics can be used to prevent unauthorized access to
ATMs, cellular phones, smart cards, desktop PCs,
workstations, and computer networks.
It can be used during transactions conducted by telephone and
Internet (electronic commerce and electronic banking).
In automobiles, biometrics can replace keys with keyless entry
Vertical markets that are using biometrics:
Government—Passports, national identification (ID) cards, voter cards,
driver’s licenses, social services, and so on
✓ Transportation—Airport security, boarding passes, and commercial
✓ Healthcare—Medical insurance cards, patient/employee identity cards
✓ Financial—Bankcards, ATM cards, credit cards, and debit cards
✓ Security—Access control and identity verifications, including time and
✓ Education—Student/teacher identity verification and access control.
Biometrics are now being implemented in large-scale ID systems around
Biometrics cannot be lost, stolen or forgotten. Barring
disease or serious physical injury, the biometric is
consistent and permanent.
It is also secure in that the biometric itself cannot be
socially engineered, shared or used by others.
There is no requirement to remember passwords, or
PINs, thus eliminating an overhead cost. The biometric
is always available to the individual;
Coupled with a smart card, biometrics provide strong
security for any credentials on the smart card.
Biometric system provide a high degree of confidence
in user identity.
Organizations can implement recognition systems to
obviate the need to log onto a system manually.
While the reliability and the accuracy of biometric
devices continues to improve.
Biometric systems must be able to accommodate
changes to the biometric over time which may be
caused by ageing, illness or injury.
The effectiveness of the sample collection process is
strongly influenced by environmental conditions, user
training and usability. For example, lighting, facial
orientations, expression, image resolution and the
wearing of hats can affect the quality of the sample.