The fundamental design of a generic biometric system is presented in this presentation.

1. Biometric Identification
systems: introduction
Dr. Suryakant Mishra
Assistant Professor (for Forensic Science)
Department of Zoology
Kurukshetra University

2. The term "biometrics" is derived from the Greek words
bio (life) and metric (to measure).
“Biometric technologies” are automated methods of
verifying or recognizing the identity of a living person
based on a physiological or behavioral characteristic.
These characteristics are unique to individuals hence can
be used to verify or identify a person.
INTRODUCTION

3. Common methods of identification:
• An individual’s identity can be established by object or token that
the person possesses, something that the person knows, or a
physical characteristic of the person.
• Keys, identification cards, and credit and debit cards are all
examples of objects that can be used to establish the identity and
authorize our access to our cars, workplaces, and credit.
• Physical objects are often effective means of identification, but
they can be lost, stolen, copied, or counterfeited.

4. Problems with current security systems
• With increasing use of IT technology and need to protect data,
we have multiple accounts/passwords.
• We can not remember so many passwords, so we end up
using things to create them like birthdays, wife/ husband /friends
name etc.
• Its is easy to crack passwords, because most of our passwords
are weak.

5. What Kinds of Information Can Be Used by Biometric
Systems to Identify Individuals?
Identification can be based on physiological characteristics – such
as fingerprints, the shape of the hand, or the characteristics of the
face or eye – or on behavioral characteristics – such as voice
patterns, signature, or typing dynamics.

6.  Facial imaging and
thermo-grams
 Fingerprint
 Voice recognition
 Palm-print
 Hand Geometry
 Iris recognition.
 Retina Scan
 DNA
 Signatures recognition
 Gait pattern
 Key strokes/typing dynamics
 Odour
Different Biometrics systems

7. A System Model of biometrics system
The operations performed by a generic biometric system are the
capture and storage of enrollment (reference) biometric samples
and the capture of new questioned samples and their comparison
with corresponding reference samples.
A biometric authentication system divided into five subsystems:
data collection, transmission, signal processing, decision and data
storage.

8. 1. Data Collection
Biometric systems begin with the measurement of a
behavioral/physiological Characteristic.
The user’s characteristic must be presented to a sensor.
The presentation of any biometric characteristic to the sensor
introduces a behavioral (and, consequently, psychological)
component to every biometric method.

9. Fig: A System Model of biometrics system

10. 2.Data Transmission
• Some biometric systems collect data at one location but
store and/or process it at another. Such systems require data
transmission.
• Standards currently exist for the compression of
fingerprints facial images (JPEG), and voice data.

11. Signal Processing -acquired and transmitted a biometric
characteristic, for matching with other like measures.
Signal-processing subsystem complete four tasks:
1. Segmentation,
2. Feature extraction,
3. Quality control, and
4. Pattern matching.
3. Signal Processing

12. 4. Storage
After signal processing the remaining subsystem stored the data.
There will be one or more forms of storage used, depending
upon the biometric system.
Templates or models from enrolled users will be stored in a
database for comparison by the pattern matcher to incoming
feature samples.
Internal or external device could be used for data storage.

13. 5. Decision
The decision subsystem implements system policy by directing
the database search, determines “matches” or “non-matches”
based on the distance or similarity measures received from the
pattern matcher, and ultimately makes an “accept/reject”
decision based on the system policy.

14. Biometrics and privacy.
 Unlike more common forms of identification, biometric
measures contain no personal information and are more difficult
to forge or steal.
 Biometric measures can be used in place of a name or Social
Security number to secure anonymous transactions.
 Some biometric measures (face images, voice signals and
“latent” fingerprints left on surfaces) can be taken without a
person’s knowledge, but cannot be linked to an identity without a
pre-existing invertible database.
 A Social Security or credit card number, and sometimes even a
legal name, can identify a person in a large population.

15.  Like telephone and credit card information, biometric
databases can be searched outside of their intended purpose
by court order.
 Unlike credit card, telephone or Social Security numbers,
biometric characteristics change from one measurement to
the next.
 Searching for personal data based on biometric measures is
not as reliable or efficient as using better identifiers, like
legal name or Social Security number.
 Biometric measures are not always secret, but are
sometimes publicly observable and cannot be revoked if
compromised.

16. Limitation of biometric systems:
Change in biometric feature:
Behavioral biometric information may change over time, the process
used to judge whether two biometrics come from the same
individual is difficult and may be prone to error.
Vulnerability to fraud:
The types of fraud that may be committed depend on whether the
application is cooperative or non cooperative.
In cooperative applications (i.e., the impostor tries to obtain a false
match), technologies may be fooled by devices such as pictures, tape
recordings, or artificial limbs.

17. Accuracy:
There are two types of error that a biometric identification
system can make:
(1) it can assess that two samples from different individuals
are the same, and
(2) it can assess that two samples from the same individuals
are different.
The first of these errors is termed a false match or a false
accept error. The second of these errors is termed a false
non-match or a false reject error.

18. Applicability to entire population.
There are some people who cannot provide the biometric
information required by the technology.
Example : roughly .5 to 1% of the population cannot provide
finger images, either because of accident or injury, or because
their fingerprints distorted due to their occupation or age.

19. Terminology
Identification:
Match a person’s biometrics against a database to figure out his
identity by finding the closest match.
Verification:
 The person claims to be ‘Deepak’, system must match and
compare his biometrics with ‘Deepak’s stored Biometrics data.
 If they match, then user is ‘verified’ or authenticated that he is
indeed ‘Deepak’
 Typically called as 1:1 matching.

20. References
1. James Wayman, Anil Jain, Davide Maltoni and Dario Maio. (2005)
Biometric Systems Technology, Design and Performance Evaluation.
2. Paul J. Sticha, J. Patrick Ford. 1999. Introduction To Biometric
Identification Technology: Capabilities and Applications to the
Food Stamp Program. R. Lewis & Company, Inc.

21. THANK YOU