FINGERPRINT LIVENESS DETECTION COMPETITION 2009 (LivDet2009)
The widespread use of personal verification systems based on fingerprints
has shown some weaknesses related to the problem of security.
Among the others, it is well-known that a fingerprint verification system can be deceived by submitting
artificial reproductions of fingerprints made up of silicon or gelatine to the electronic capture device
(optical or capacitive). These images are then processed as "true" fingerprints.
Therefore, a recent issue in the field of security in fingerprint verification (remote especially)
is known as "liveness detection". The standard verification system is coupled with additional hardware
or software modules aimed to certify the authenticity of the submitted fingerprints. Whilst the
hardware-based solution are the most expensive, the software-based ones attempt to measure liveness
from characteristics of images themselves by simply applying image processing algorithms.
The problem of vitality detection is treated as a two-class classification problem (live or fake):
an appropriate classifier is designed in order to extract the probability of the image vitality
given the extracted set of features.
This LFC-2009 competition is open to all academic and industrial institutions which have a
solution for software-based fingerprint vitality detection problem.
Each participant is invited to submit its our algorithm in an Win32 console application.
The performance will be evaluated by utilizing a very large data set of "fake" and "live"
fingerprint images captured with three different optical scanners.
The performance rank will be compiled and published in this site and the best algorithm w
ill win the "Best Fingerprint Liveness Detection Algorithm Award" at ICIAP 2009. A Special
Session of ICIAP 2009 will be devoted to present and discuss the experimental results.
Goal of the competition is to compare different methodologies for
software-based fingerprint liveness detection with a common experimental
protocol and data set. The ambition of the competition is to become the reference
event for academic and industrial researches.
The competition is not defined as an official system for quality certification of the
proposed solutions, but impact the state of the art in this crucial field,
with reference to the general problem of security in biometric systems.
The competition is open to academic and industrial institutions. Each user will receive,
after his registration and information about the competition rules, an password to
enter into the site and managing his personal information and uploaded files.
In order to finalize the registration, it is necessary to fill the license agreement of the data
set use. The filled and signed agreement must be sent through fax and by mail.
Once a signed consent form is obtained, a link for downloading the training set will be given.
Each participant must give their preference on whether to enter as anonymous.
All results will be included in the final report, in regard to the anonymity of the participant.
With regard to this aspect, it is worth to point out that results published at
LivDet2009 cannot be used for commercial purposes. The goal of the competition
is merely to make the point on the state-of-the-art.
Declaration of the Winner
The winner will be awarded by simple averaging the overall classification errors on
the three sensors. Only one winner will be awarded. The declaration will be made during
the social dinner of ICIAP 2009.
A Special Session of ICIAP 2009 will be devoted to present and discuss the perfomance
of the proposed algorithms.
LivDet Registration Deadline: February, 28
Deadline for exe-files submission: April, 30
Prof. Fabio Roli, University of Cagliari (Italy), email@example.com
Prof. Stephanie Schuckers, University of Clarkson (USA), firstname.lastname@example.org
Dr. Gian Luca Marcialis, University of Cagliari (Italy), email@example.com
For more details, please refer to the
LivDet 2009 Official Site