Personal tools
You are here: Home Dataset fvspoofingattack

The Spoofing-Attack Finger vein Database

The Spoofing-Attack Database for finger vein spoofing consists of 440 index finger images attempts to 110 clients. This Database was produced at the Idiap Research Institute in Martigny, in Switzerland.

Database Description

The data is split into 3 sub-groups comprising:

1. Training data ("train"), to be used for training your anti-spoof classifier;
2. Development data ("dev"), to be used for threshold estimation;
3. Test data ("test"), with which to report error figures;

Clients that appear in one of the data sets (train, devel or test) do not appear in any other set.

All the attacks have been recorded using the same open finger vein sensor used to record the Idiap Research Institute VERA Fingervein Database.

Images are labeled as follow: ID_index_shot.png where "ID" is a 3 digits number that stands for client's ID, "index" stands for the considered index finger which can be "R" or "L" ("Right" or "Left"), and "shot" stands for the considered shot number which can be "1" or "2" (2 shots per finger).

Images from the same client are regrouped into a single folder labeled as follow: ID-Gender, where "ID" is a 3 digits number that stands for client's ID and "Gender" stands for client's gender which can be "M" or "F" ("Male" or "Female").

The format of the images is PNG.
Size of the full images is 665 x 250 pixels.
Size of the cropped images is 565 x 150 pixels.
Size of the files is around 80 kbytes per images.

* Example of the nomenclature for the real images from the client #29:
* real/029-M/029_L_1.png
* real/029-M/029_L_2.png
* real/029-M/029_R_1.png
* real/029-M/029_R_2.png

* Example of the nomenclature for the spoofing images from the client #29:
* spoof/029-M/029_L_1.png
* spoof/029-M/029_L_2.png
* spoof/029-M/029_R_1.png
* spoof/029-M/029_R_2.png

 

Protocols for Spoofing Attacks

Attack protocols are used to evaluate the (binary classification) performance of counter-measures to spoof attacks. The database can be split into 2 different sub-tasks according to the visual information available: full printed images and cropped printed images. This classification scheme makes-up a total of 2 protocols that can be used for studying the performance of counter-measures to finger vein attacks. Both `full` and `cropped` protocols are designed to use prior information based on trained classifiers or non trained approaches where the decision is taken based just on the input.

The table bellow details the amount of images in each protocol.

Distribution of images per attack-protocol in the Finger Vein spoofing database.

===========    ===== === ====  ====== === ====
               Real Access     Printed Attacks
-----------    --------------  ---------------
Protocol       train dev test  train  dev test
===========    ===== === ====  ====== === ====
full            120  120  200    120  120  200
cropped         120  120  200    120  120  200
===========    ===== === ====  ====== === ====

 

protocol_examples.png

Competition Results

The Competition results are published in the paper below. You can reproduce all the results using the source code publicly available at: https://github.com/bioidiap/antispoofing.fvcompetition_icb2015 or https://pypi.python.org/pypi/antispoofing.fvcompetition_icb2015. This package contains all the submissions and generates all the competition results.

Acknowledgement

If you use this database, please cite the following publication:

@inproceedings{Tome_ICB2015_AntiSpoofFVCompetition,
             author = {Tome, Pedro and Raghavendra, R. and Busch, Christoph and Tirunagari, Santosh and Poh, Norman and Shekar, B. H. and Gragnaniello, Diego and Sansone, Carlo and Verdoliva, Luisa and Marcel, S{\'{e}}bastien},
        keywords = {Biometrics, Finger vein, Spoofing Attacks, Anti-spoofing},
             month = may,
                 title = {The 1st Competition on Counter Measures to Finger Vein Spoofing Attacks},
         booktitle = {The 8th IAPR International Conference on Biometrics (ICB)},
                year = {2015},
          location = {Phuket, Thailand},
                  url = {http://publications.idiap.ch/index.php/publications/show/3095}
   }

 

Dr. Pedro Tome
Dr. S├ębastien Marcel

 

Idiap Research Institute
Centre du Parc - rue Marconi 19
CH-1920 Martigny, Suisse
Phone: +41 27 721 7727
Fax: +41 27 721 7712

 

Document Actions