|
|
|
Sponsors:
|
The workshop
is organized by the Information Access Division of the Information
Technology Laboratory (ITL) at the National
Institute of Standards and Technology
(NIST).
The workshop is supported by the Department of Homeland Security
(DHS), the Department of State (DOS), the Federal Bureau of Investigation
(FBI), and the Department of Defense, Biometric Task Force.
|
|
Audience:
|
Government
Agencies, Industry, and Academia concerned with development, deployment
and use of biometric quality infrastructure. |
|
Format:
|
Workshop
with breakout sessions. |
|
Purpose:
|
The
workshop is aimed at improving accuracy of biometric systems by
incorporating quality assessment technologies into the sample acquisition
process. It aims to assess current quality measurement capabilities
and to identify technologies, factors, operational paradigms, and
standards that can measurably improve quality.
The workshop will be held over two days: Day One will consider operational
needs and acquisition issues for finger, face and iris capture.
Day two will consider quality calibration, quality evaluation and
research and development for all modalities. |
|
Topics:
|
Quality
by Design
To what extend does sensor design affect quality?
How to provide effective feedback to users at the time of capture?
Should SC37 consider adding Best Capture Practice to existing
data format standards?
Given that data format standards are under revision, should it
be considered to revise or add quality-related clauses (e.g. compression
limits) to data format standards so that conformance to those
standards ensures quality?
Quality
Calibration
Quality Calibration
(QC) aims at quality score interpretation and interoperability
by relating quality scores to performance. QC maps the output
of a quality assessment algorithm to performance of a given matcher.
Therefore, QC provides:
- Interpretation
(or context) to quality scores computed by a quality assessment
algorithm, and
- Interoperability
of quality scores computed by two or more quality assessment
algorithms.
Quality calibration
can be performed for a specific matching algorithm so that quality
scores are indicative of performance of that particular matcher,
or calibration can be done for general use.
Quality
Annotated Datasets
Would sequestered or public quality annotated corpora be useful
in quality interoperability or quality evaluation?
If these are useful and needed, how to build a quality reference
data set?
Would a standard reference algorithm for each modality be useful?
Quality
Evaluation
What
are the relevant performance metrics?
How should speed of operation be considered?
Is standardized performance testing of quality measurement algorithms
needed?
Is certification of quality measurement algorithms needed?
|
|
Registration
Contact:
|
Teresa
Vicente, NIST, phone: 301/975-3883, email: Teresa
Vicente |
|
Technical
Contact:
|
Elham Tabassi,
NIST, phone: 301/975-5292, email: tabassi@nist.gov
Patricl Grother,
NIST, phone: 301/975-4157, email:pgrother@nist.gov
|
|
Website:
|
Homepage |
|
Registration:
|
On-Line
Registration
Registration
Fee: $235
Registration closed on 10/31/2007.
All
request for cancellation and refund must be submitted in writing,
prior to October 31, 2007.
|
|
Accommodation:
|
A block of
rooms has been reserved for the nights of November 6-7, 2007
at the Holiday Inn
Gaithersburg, Two Montgomery Village Avenue, Gaithersburg, MD
20879. The special rate is $109.00 per night plus
12% tax.To make your reservation, please contact the hotel directly
at 301/948-8900 by October 17, 2007, and mention that you
are attending the "NIST Biometric Quality Workshop ".
|
|
