Login

MAD@IJCB-2020

MAD@IJCB-2020 is a face morphing attack detection competition based on the FVC-onGoing SMAD and DMAD benchmark areas, organized in conjunction with the International Joint Conference on Biometrics (IJCB 2020).
The competition is supported by EU funded projects iMars and SOTAMD in joint efforts of:

  • The University of Bologna (Italy)
  • The Norwegian University of Science and Technology (Norway)
  • The Darmstadt University of Applied Sciences (Germany)
  • The University of Twente (The Netherlands)
  • The Dutch Ministry of the Interior and Kingdom Relations
  • The Federal Criminal Police Office of Germany
This MAD competition in conjunction with IJCB 2020 will employ the newly created SOTAMD database [1] for testing algorithms submitted for evaluation.

Motivation

This competition is framed into the context of face recognition in machine-readable travel documents (eMRTD) where biometric recognition has been widely introduced to increase the security in the border control procedures, and to enable automatic verification at dedicated gates (Automated Border Control systems - ABC gates). Recent studies show that the current ePassport infrastructure presents some security threats. One of the main problems is related to the possibility offered by many countries of creating the user template from printed/digital photos provided by the citizen rather than from images acquired live during enrolment; in this scenario digital image alterations could severely affect the recognition results of a face recognition system. In particular, image morphing alteration (obtained by digitally mixing face images of two subjects) can cause an increment of the false acceptance rate and consequently of the possibility that a criminal succeeds to bypass border controls. The need for effective morphing detection techniques is quite stringent and practical solutions are requested by the member states to address this critical issue. Many researchers are currently working on face morphing detection and assessing the current state of the art is important both to understand the main limitations of the existing approaches and to promote future research.

Benchmarks

MAD@IJCB-2020 is based on the following benchmarks:

SMAD-SOTAMD_PM_D-1.0 SMAD-SOTAMD_UC_P&S-1.0
The benchmark consists of a subset of the digital face images collected in the SOTAMD project. In particular, it contains only manual post-processed morphed images.
More details......
The benchmark consists of a subset of the printed and scanned face images collected in the SOTAMD project. In particular, it contains only uncompressed images.
More details......
DMAD-SOTAMD_PM_D-1.0 DMAD-SOTAMD_UC_P&S-1.0
The benchmark consists of a subset of the digital face images collected in the SOTAMD project. In particular, it contains only manual post-processed morphed images.
More details......
The benchmark consists of a subset of the printed and scanned face images collected in the SOTAMD project. In particular, it contains only uncompressed images.
More details......

How to participate

All algorithms evaluated under the above benchmarks before the deadline specified below, will be included in MAD@IJCB-2020. Submission and evaluation of the algorithms follow the standard FVC-onGoing rules (see Sumbission and Publication policy).
Note that, in order to be included in MAD@IJCB-2020, evaluation results must be published by the participants before the deadline.

Deadline (expired)

Algorithms' results must be published on the FVC-onGoing website within July 15th, 2020.

Results

No algorithm was published in this benchmark area before the deadline.

Organizers

  • M. Ferrara
  • A. Franco
  • D. Maltoni
  • C. Busch
  • R. Raghavendra
  • K. Raja
  • L. Spreeuwers
  • R. Veldhuis
  • I. Batskos
  • C. Rathgeb
  • U. Scherhag

Bibliography

[1] K. Raja, M. Ferrara, A. Franco, L. Spreeuwers, I. Batskos, F. de Wit, M. Gomez-Barrero, U. Scherhag, D. Fischer, S. Venkatesh, J. M. Singh, G. Li, L. Bergeron, S. Isadskiy, R. Ramachandra, C. Rathgeb, D. Frings, U. Seidel, F. Knopjes, R. Veldhuis, D. Maltoni, C. Busch, "Morphing Attack Detection -- Database, Evaluation Platform and Benchmarking", arXiv 2006.06458, June 2020 (Submitted to IEEE-TIFS).

For information or suggestions: fvcongoing@csr.unibo.it Copyright © 2020 Biometric System Laboratory