Description

The MSU GenPrint Dataset, was created to synthesize highly realistic, diverse fingerprint impressions with multiple impressions per generated identity in any acquisition, sensor, fingerprint class, and quality type. Currently, it consists of 100,000 unique, synthetic fingerprint identities with 15 impressions each, for a total of 1,500,000 images. Fig. 1 presents an overview of the GenPrint architecture and some example GenPrint fingerprint images. The database was produced at Michigan State University’s Pattern Recognition and Image Processing (PRIP) Lab, in East Lansing, MI, US. This dataset may be augmented later with additional synthetic fingerprint identities and more impressions per identity.

Figure 1: Overview of the GenPrint architecture and example images generated for the MSU GenPrint Dataset.

Details

Download Instructions

To download the MSU GenPrint dataset, please first print out, fill and sign the Agreement and send it to: Steven Grosz (groszste@gmail.com). 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{grosz2024universal,
  title={Universal Fingerprint Generation: Controllable Diffusion Model with Multimodal Conditions},
  author={Grosz, Steven A and Jain, Anil K},
  journal={arXiv preprint arXiv:2404.13791},
  year={2024}
}