Description

The MSU GenPalm Dataset, was created to synthesize highly realistic, contactless palmprint images with multiple images per generated identitiy. Currently, it consists of 12,000 unique, syntheticly generated palmprint identities with 20 images each, for a total of 240,000 images. Fig. 1 presents some example GenPalm-generated 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: Example images from the MSU GenPalm Dataset. Each row shows genuine pairs of the same palm, whereas each row is a different generated identity.

Details

Download Instructions

To download the MSU GenPalm 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{grosz2024genpalm,
  title={GenPalm: Contactless Palmprint Generation with Diffusion Models},
  author={Grosz, Steven A and Jain, Anil K},
  journal={arXiv preprint arXiv:2406.00287},
  year={2024}
}