RECOD Mobile Presentation-Attack Dataset (RECOD-MPAD)
<p>=============<br> Introduction</p> <p>The RECOD Mobile Presentation-Attack Dataset (RECOD-MPAD) is intended for the study of presentation attacks (PAs, also known as spoof attempts) to facial recognition systems in mobile devices.<br> It consists of frames depicting genuine attempts of unlocking a smartphone, as well as two types of presentation attacks: using printouts of the user face; or using electronic displays showing the user's face.</p> <p>More details can be found in the accompanying paper:<br> <em>Detecting face presentation attacks in mobile devices with a patch-based CNN and a sensor-aware loss function</em><br> Waldir R. Almeida, Fernanda A. Andaló, Rafael Padilha, Gabriel Bertocco, William Dias, Ricardo da S. Torres, Jacques Wainer, Anderson Rocha<br> PLoS ONE, 2020 (https://doi.org/10.1371/journal.pone.0238058)<br> <br> This dataset was developed as part of a research project at the RECOD lab of the Institute of Computing, University of Campinas, Brazil.</p> <p><br> ==========<br> Statistics</p> <p>Number of users: 45<br> Men: 30/45<br> Glasses: 14/45<br> Beard: 13/45<br> Age range: 18-50</p> <p><br> =============================<br> Basic metadata and file names</p> <p>Name format:<br> <device>_<session>_<user>_<label>_<frame></p> <p>Label: <br> 0: real, genuine access attempt<br> 1: printout attack - recaptured indoors<br> 2: printout attack - recaptured outdoors (more light)<br> 3: screen attack - large display (CCE TV)<br> 4: screen attack - medium-sized display (HP monitor)</p> <p>Device:<br> 1: motog3<br> 2: xt1572</p> <p>Session:<br> 1: outdoors natural direct light<br> 2: outdoors natural diffuse light/shadow<br> 3: indoors, top main light<br> 4: indoors, side light (sunlight coming through window or door)<br> 5: indoors, low-light / noisy</p> <p>Example:<br> 1_5_20_00_0050</p> <p><br> ======================<br> Additional information</p> <p>In each sequence, the volunteers followed the same instructions:<br> - Hold the phone as if using it normally, but keep close-to-frontal viewing angles<br> - Rotate slowly (to change lighting and background)</p>
ShareScore
12/100
Overall dataset sharing score
Score breakdown
These five areas show where the dataset supports — or may limit — practical reuse.
- Stewardship
- 8
- Harmonization
- 4
- Access
- 0
- Reuse readiness
- 0
- Engagement
- 0
Topics
Dataset details
- Repository
- zenodo
- Published
- April 11, 2020
- License
- Not reported
- DOI
- 10.5281/zenodo.3749308
Scored with release 0.9.0
ScienceDex for faculty
Your academic CV and NIH biosketch
Make your CV in your school's format and your NIH biosketch from it, then download both as Word files.