Algorithm Specifications

Each submitted algorithm must be a Win32 or Linux console application with the following list of parameters:

Synopsis:    [nameOfAlgorithm].exe [ndataset] [templateimagesfile] [probeimagesfile][livenessoutputfile] [IMSoutputfile]

  • [nameOfAlgorithm].exe

It is the executable name. Format: Win32 or Linux console application (es. .exe)

  • [ndataset]

It is the identification number of the dataset to analyse.
Legend:

1=GreenBit
2=DigitalPersona
3=Orcanthus

  • [templateimagesfile]

A text file with the list of absolute paths of each template image registered in the system. Each image is in the same format of own training-set.

Exemple of a [templateimagesfile] called GreenBit_template.txt:

...
G:\Works\LivDet2017\TemplateImages\GreenBit\0123.png
G:\Works\LivDet2017\TemplateImages\GreenBit\1323.png
G:\Works\LivDet2017\TemplateImages\GreenBit\0033.png
G:\Works\LivDet2017\TemplateImages\GreenBit\0954.png
G:\Works\LivDet2017\TemplateImages\GreenBit\2154.png

...

  • [probeimagesfile]

A text file with the list of absolute paths of each image to analyse. Each image is in the same format of own training-set.

Exemple of a [probeimagesfile] called GreenBit_probe.txt:

...
G:\Works\LivDet2017\ProbeImages\GreenBit\0123.png
G:\Works\LivDet2017\ProbeImages\GreenBit\1323.png
G:\Works\LivDet2017\ProbeImages\GreenBit\0033.png
G:\Works\LivDet2017\ProbeImages\GreenBit\0954.png
G:\Works\LivDet2017\ProbeImages\GreenBit\2154.png

...

  • [livenessoutputfile]

The text file with the liveness output of each processed image, in the same order of "probeimagesfile". The output is a posterior probability of the live class given the image, or a degree of “liveness” normalized in the range 0 and 100 (100 is the maximum degree of liveness, 0 means that the image is fake).

Scores [0, 50) classify fingerprint image as "fake" while scores [50,100] classify fingerprint image as "live"(in Fig.1 in blue "livenessoutput").

In the case that the algorithm has not been able to process the image, the correspondent output must be -1000 (failure to enroll).

Exemple of a [livenessoutputfile] called GreenBit_liveness_results.txt:

...
100
54
-1000
32
78
...

  • [IMSoutputfile]

The text file with the integrated match score output of each processed image, in the same order of "probeimagesfile". The output is a combined posterior probability of the live class and the belonging of the claimed identity given the image, normalized in the range 0 and 100 (100 means that the image is live and belonging to the declared user, 0 means that the image is fake or belonging to an attacker).

Scores [0, 50) classify fingerprint image as "fake or attacker" while scores [50,100] classify fingerprint image as "live and genuine" (in Fig.1 in red "IMSoutput")

In the case that the algorithm has not been able to process the image, the correspondent output must be -1000 (failure to enroll).

Exemple of a [imsoutputfile] called GreenBit_ims_results.txt:

...
100
54
-1000
32
78
...

esempio funz2

Fig.1 Block diagram of a possible Integrated Match System.

Each parameter related to the dataset configuration must be set before submission. Each user can configure his algorithm by the training-set available after the registration. Only Win32  or Linux console applications with the above characteristics will be accepted for the competition.

Participants are recommended to send a description of their algorithm.

They may publish also the source code of their algorithm, but this is not mandatory.