Description

The MSU Fingerprint Presentation Attack Dataset (MSU-FPAD), was created to simulate presentation attacks on fingerprint readers. Currently, it utilizes two different 500 ppi fingerprint readers, namely, CrossMatch Guardian 200 and Lumidigm Venus 302. There are a total of 9,000 bonafide images and 10,500 presentation attack images captured using these two readers and 4 different spoof fabrication materials, namely, ecoflex, playhoh, 2D printed on matte paper, and 2D printed on transparency film. The selection of the fingerprint readers and the spoof materials is based on the requirements of IARPA ODIN program evaluation. Fig. 1 presents some example fingerprint images, and Table I presents a summary of the MSU Fingerprint Presentation Attack Dataset. The database was produced at Michigan State University’s Pattern Recognition and Image Processing (PRIP) Lab, in East Lansing, MI, US. This dataset will be further augmented with additional subjects, spoof fabrication materials, and fingerprint readers.

Figure 1: Example images from MSU Fingerprint Presentation Attack Dataset (MSU-FPAD) acquired using (a) CrossMatch Guardian 200, and (b) Lumidigm Venus 302 fingerprint readers. Note that Lumidigm reader does not image PlayDoh (orange) spoofs.

Summary of the MSU Fingerprint Presentation Attack Dataset (MSU-FPAD). * In the cooperative subject scenario, a subject willingly provides a negative impression of the fingerprint as a mold, while in the non-cooperative subject scenario, the fingerprint mold is created by using the latent fingerprint lifted off a surface touched by the subject.

Details

Download Instructions

To download the MSU FPAD, please first print out, fill and sign the Agreement and send it to: Tarang Chugh (chughtar@msu.edu). You will receive a download link upon approval of your usage of the database.

Acknowledgements

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


@ARTICLE{chugh2018fingerprint,
author={Tarang Chugh and Kai Cao and A.K. Jain},
journal={IEEE Transactions on Information Forensic and Security},
title={{ Fingerprint Spoof Buster: Use of Minutiae-centered Patches}},
year={2018},
month={September},
volume={13},
number={9},
pages={2190 - 2202},
}