Compositional Approach to V&V - National Center for Border ...

spotlessstareSecurity

Nov 29, 2013 (3 years and 4 months ago)

38 views

Biometric Measures for Human
Identification

D. Adjeroh, B. Cukic, L. Hornak, A. Ross


Lane Department of CSEE

West Virginia University


NC
-
BSI, December 2008

NC


BSI 2008

2

Problem Statement


Current biometric systems at the US borders rely
on fingerprint and face recognition (US
-
VISIT).
We will analyze the use of other biometric
modalities (iris, palm, face, voice) and their
combinations for border security.


Methodology



Lab and field experiments to study the
maturity,
reliability, cost, performance, and feasibility

of
new biometric modalities in the context of border
security.

NC


BSI 2008

3

Risk function

Systems Approach: Port of Entry

Traveler Queues

Watch Lists / Identity DB


Legend

=Required Signal

=Optional Signal

= Movement

Public Key Directory


Secondary Inspection /
Detainment

Border Access

=Optional Movement

Inspection Stations

(w/ biometric )

after Cukic et al.

Local,
distributed,
or central?

Modality,
quality,
scalability,
update, access ?

Acceptance,
modality,
quality?

Modality,
FMR,
vulnerability,
exceptions,
throughput?

False Match Rate,
Inconvenience acceptance?

False Non Match Rate

NC


BSI 2008

4

Error Rates

Test

Test Parameter

False Reject
Rate

False Accept
Rate

Fingerprint

FVC

[2004]

Exaggerated distortion

2%

2%

FpVTE

[2003]

US govt. operational
data

0.1%

1%

Face

FRVT

[2002]

Varied lighting,
outdoor/indoor

10%

1%

FRGC

[2006]

Time lapse, varied
lighting/expression,
outdoor/indoor

10%

0.1%

Iris

ITIRT
[2005]

Indoor environment,
multiple visits

0.99%

0.94%

Voice

NIST

[2004]

Text independent,
multi
-
lingual

5
-
10%

2
-
5%

NC


BSI 2008

5

NIST FRVT 2006 Results

NC


BSI 2008

6

Sensor Interoperability

A. Ross and R.
Nadgir, "A
Calibration Model
for Fingerprint
Sensor
Interoperability",
Proc. of SPIE
Conference on
Biometric Technology
for Human
Identification III
,
(Orlando, USA),
April 2006.

NC


BSI 2008

7

Multimodal Biometric Systems


Multiple sources of biometric information are integrated to
enhance matching performance


Increases
population coverage

by reducing failure to enroll rate


Anti
-
spoofing;
difficult to spoof

multiple traits simultaneously

Fingerprint

Face

Hand geometry

Iris

NC


BSI 2008

8

Deployment Problems


Sensor Interoperability


Missing information from some modalities


Non
-
ideal capture


Non
-
cooperative subjects or capture problems


surveillance scenarios, i.e., identifying risk early


Varying risk tolerance


Maximizing identification rates while minimizing
inconvenience and disruption of border crossing
flow.




NC


BSI 2008

9

Leverage


The Center for Identification Technology Research
(NSF I/UCRC)


Biometrics: Performance, Security and Social
Impact, (NSF and DHS


Human Factors)


Performance analysis, multimodal biometric database
collections, familiarity with port of entry applications.



WVU is academic partner with the FBI Center of
Excellence in Biometrics


Large scale data collection for the New Generation Identification
project.


NC


BSI 2008

10

Deliverables


Year 1:


Analysis of existing performance studies,


Defining specific border application scenarios and their
requirements,


Definition of lab experiments


Definition of field experiments.



Years 2
-
5:


Experimental results


Modality recommendations


Multi
-
modal fusion,


System aspects and recommendations.