The Architecture of
Biometrics Systems
Bojan Cukic
1
Biometric Systems Segment
Organization
 Introduction
 System architecture
2-2
Introduction

Biometrics




Engineering Definition and Approaches
Definition, Criteria for Selection
Survey of Current Biometrics and Relative Properties
Introduction to socio-legal implications and issues
2-3
Recap –
Identification in the 21st Century




Dispersion of people from their “Natural ID
Centers”
Social units have grown to tens of thousands
or millions/billions.
Need to assure associations of identity with
end-to-end transactions without physical
presence
Project your presence (ID) instantly,
accurately, and securely across any distance
2-4
Identification Methods



We need to achieve this recognition
automatically in order to authenticate
our identity.
Identity is not a passive thing, but
associated with an act or intent involving
the person with that identity
Seek a manageable engineering
definition.
2-5
Biometric Identification

Pervasive use of biometric ID is enabled by
automated systems



Biometric systems are one solution to increasing
demand for strong authentication of actions in a
global environment.


Enabled by inexpensive embedded computing and sensing.
Computer controlled acquisition, processing, storage, and
matching using biometrics.
Biometrics tightly binds an event to an individual
A biometric can not be lost or forgotten, however a
biometric must be enrolled.
2-6
What is an Automated Biometric
System?


An automated biometric system uses
biological, physiological or behavioral
characteristics to automatically authenticate
the identity of an individual based on a
previous enrollment event.
For the purposes of this course, human identity
authentication is the focus. But in general, this need
not necessarily be the case.
2-7
Characteristics of a Useful Biometric

If a biological, physiological, or behavioral
characteristic has the following properties…




Universality
Uniqueness
Permanence
Collectability
….then it can potentially serve as a
biometric for a given application.
2-8
Useful Biometrics

1. Universality



Universality: Every person should possess
this characteristic
In practice, this may not be the case
Otherwise, population of nonuniversality
must be small < 1%
2-9
Useful Biometrics

2. Uniqueness



Uniqueness: No two individuals possess the same
characteristic.
 Genotypical – Genetically linked (e.g. identical
twins will have same biometric)
 Phenotypical – Non-genetically linked, different
perhaps even on same individual
Establishing uniqueness is difficult to prove
analytically
May be unique, but “uniqueness” must be
distinguishable
2 - 10
Useful Biometrics

3. Permanence

Permanence: The characteristic does not change
in time, that is, it is time invariant



At best this is an approximation
Degree of permanence has a major impact on the
system design and long term operation of biometrics.
(e.g. enrollment, adaptive matching design, etc.)
Long vs. short-term stability
2 - 11
Useful Biometrics

4. Collectability

Collectability: The characteristic can be quantitatively
measured.

In practice, the biometric collection must be:

Non-intrusive
Reliable and robust

Cost effective for a given application

2 - 12
Current/Potential Biometrics









Voice
Infrared facial thermography
Fingerprints
Face
Iris
Ear
EKG, EEG
Odor







Gait
Keystroke dynamics
DNA
Signature
Retinal scan
Hand & finger geometry
Subcutaneous blood vessel
imaging
What is consensus evaluation of current
biometrics based on these four criteria?
2 - 13
System-Level Criteria


Our four criteria were for evaluation of the
viability of a chosen characteristic for use as a
biometric
Once incorporated within a system the
following criteria are key to assessment of a
given biometric for a specific application:



Performance
User Acceptance
Resistance to Circumvention
2 - 14
Central Privacy, Sociological,
and Legal Issues/Concerns

System Design and Implementation must
adequately address these issues to the
satisfaction of the user, the law, and society.




Is the biometric data like personal information (e.g.
such as medical information) ?
Can medical information be derived from the
biometric data?
Does the biometric system store information
enabling a person’s “identity” to be reconstructed or
stolen?
Is permission received for any third party use of
biometric information?
2 - 15
Central Privacy, Sociological,
and Legal Issues/Concerns (2)

Continued:


What happens to the biometric data after the
intended use is over?
Is the security of the biometric data assured
during transmission and storage?



Contrast process of password loss or theft with that of a
biometric.
How is a theft detected and “new” biometric recognized?
Notice of Biometric Use. Is the public aware a
biometric system is being employed?
2 - 16
Biometric System Design

Target Design/Selection of Systems for:





Acceptable overall performance for a given
application
Acceptable impact from a socio-legal perspective
Examine the architecture of a biometric
system, its subsystems, and their interaction
Develop an understanding of design choices
and tradeoffs in existing systems
Build a framework to understand and quantify
performance
2 - 17
Automated Biometric Identification: A Comprehensive View
Biometric
Signature
Selection
Biometric
Signature
Acquisition
Data Reduction Template Storage
Classification Database Search
Processing
Match, Retrieval
Identity
Arrhythmia,
SIDS,
Iris, Hand,
Face, …
Databases,
Minutia
extraction
Camera(s),
Si CMOS
System-ona- chip
Time series
data
Data Mining
Statistical
Modeling…
Voice, Electrophysiological
Lab on a chip,
Implantable
med. device…
Biological
Agents,
Microbial Musculo-skeletal,
pathogens...
Molecular, DNA
Microbial …
M
A
T
C
H
?
0.0
0.5
1.0
1.5
2.0
Filtering,
FFT,
wavelets,
Fractals…
2.5
Action…
Logical/Phys.
Access (IA,
medical, bio)
2 - 18
Biometric Systems Segment
Organization
 Introduction
 System Architecture
2 - 19
System Architecture




Application
Authentication Vs. Identification
Enrollment, Verification Modules
Architecture Subsystems
20
Biometric Applications
Four general classes:
 Access (Cooperative, known subject)
 Logical Access (Access to computer networks, systems, or
files)

Physical Access (access to physical places or resources)
Transaction Logging

Surveillance

Forensics

(Non-cooperative, known subject)
(Non-cooperative or unknown subject)
2 - 21
Biometric Applications (2)












Transactions via e-commerce
Search of digital libraries
Computer logins
Access to internet and local networks
Document encryption
Credit cards and ATM cards
Access to office buildings and homes
Protecting personal property
Tracking and storing time and attendance
Law enforcement and prison management
Automated medical diagnostics
Access to medical and official records.
2 - 22
System Architecture

Architecture Dependent on Application:

Identification: Who are you?




Authentication: Are you who you say you are?



One to Many (millions) match (1:Many)
One to “few” (less than 500) (1:Few)
Cooperative and Non-cooperative subjects
One to One Match (1:1)
Typically assume cooperative subject
Enrollment and Verification Stages common to
both.
2 - 23
System Architecture (2)
Enrollment : Capture and processing of user biometric
data for use by system in subsequent authentication
operations.
Acquire and Digitize
Biometric Data
Extract
High Quality Biometric
Features/Representation
Formulate
Biometric
Feature/Rep Template
Database
Template
Repository
Authentication/Verification : Capture and processing of
user biometric data in order to render an authentication
decision based on the outcome of a matching process of
the stored to current template.
Acquire and Digitize
Biometric Data
Extract
High Quality Biometric
Features/Representation
Formulate
Biometric
Feature/Rep Template
Template
Matcher
Decision
Output
2 - 24
System Architecture (3)

Authentication Application:

Enrollment Mode/Stage Architecture
Require new acquisition of
biometric
Biometric
Data Collection
Transmission
Additional image preprocessing,
adaptive extraction or
representation
Signal Processing,
Feature Extraction,
Representation
No
Quality
Sufficient?
Yes
Approx 512 bytes of
data per template
Database
Generate Template
2 - 25
System Architecture (4)

Authentication Application:

Verification/Authentication Mode/Stage Architecture
Require new acquisition of
biometric
Biometric
Data Collection
Transmission
Additional image preprocessing,
adaptive extraction/representation
Signal Processing,
Feature Extraction,
Representation
No
Quality
Sufficient?
Yes
Generate Template
Approx 512 bytes of
data per template
Database
Yes
Template Match
Decision
Confidence?
No
2 - 26
Architecture Subsystems






Data Collection
Transmission
Signal Processing/Pattern Matching
Database/Storage
Decision
What comprises these subsystems and how
do they interact with other elements (what
are their interface and performance
specifications?)
2 - 27
Architecture Subsystems (2)

Data Collection Module

Biometric choice, presentation of biometric,
biometric data collection by sensor and its
digitization.
Recollect
Biometric Data Collection
Biometric Presentation Sensor
Transmission
Signal Processing
Feature Extraction
Representation
2 - 28
Architecture Subsystems (3)

Transmission Module

Compress and encrypt sensor digital data, reverse
process.
Recollect
Decompress
Decryption
Transmission
Compression
Biometric Presentation Sensor
Encryption
Transmission
Biometric Data Collection
Signal Processing,
Feature Extraction,
Representation
2 - 29
Architecture Subsystems (4)

Signal Processing/Matching Module

Be aware of potential transmission prior to match
Reprocess
Recollect
Decompress
Decryption
Transmission
Encryption
Compression
Transmission
Signal Processing
Feature Extraction,
Representation
No
Quality
Control
Yes
Generate Template
Database
Yes
Template Match
Decision
Confidence?
No
2 - 30
Architecture Subsystems

Database module

In what form is biometric stored? Template or raw data?
Recollect
Reprocess
Expansion
Decryption
Transmission
Encryption
Transmission
Compression
No
Signal Processing
Feature Extraction,
Representation
Quality
Control
Yes
Generate Template
Database
Biometric Template: A file
holding a mathematical
representation of the identifying
features extracted from the raw
biometric data.
Templates
Images
Yes
Template Match
Decision
Confidence?
No
2 - 31
Architecture Subsystems

Decision module

Is there enough similarity to the stored information to
declare a match with a certain confidence ?
Reprocess
Recollect
Decompress
Decryption
Transmission
Encryption
Transmission
Compression
No
Signal Processing
Feature Extraction,
Representation
Quality
Control
Yes
Generate Template
Database
Templates
Images
Yes
Template Match
Decision
Decision
Confidence?
Confidence?
No
2 - 32