home   |  research   |  members   |  projects   |  publications   |  conferences of interest   |  downloads   |  contact & impressum   |  privacy information

Ground truth for the STUMLA_HMT fingervein database (STUMLA-GR)

This is "The Multimedia Signal Processing and Security Lab", short WaveLab, website. We are a research group at the Artificial Intelligence and Human Interfaces (AIHI) Department of the University of Salzburg led by Andreas Uhl. Our research is focused on Visual Data Processing and associated security questions. Most of our work is currently concentrated on Biometrics, Media Forensics and Media Security, Medical Image and Video Analysis, and application oriented fundamental research in digital humanities, individualised aquaculture and sustainable wood industry.


Ehsaneddin Jalilian, Andreas Uhl, "Improved CNN-Segmentation-Based Finger Vein Recognition Using Automatically Generated and Fused Training Labels", in Andreas Uhl, Christoph Busch, Sebastien Marcel, Raymond Veldhuis, editors, Handbook of Vascular Biometrics, pp. 200-223, Cham, Switzerland, Springer Nature Switzerland AG, 2019

Groundtruth Database

On this page we provide the ground-truth masks for a part (634 samples) in the SDUMLA-HMT fingervein database for direct use (i.e. training segmentation-based CNNs).

Note that the SDUMLA-GR database only contains ground-truth not the original images. The source databases to which the ground truths apply can be found at: http://mla.sdu.edu.cn/info/1006/1195.htm

If you are using this ground-truth masks in your work, please cite the paper:


@incollection{ Jalilian19c,
      author = {Ehsaneddin Jalilian and Andreas Uhl},
      title = {Improved CNN-Segmentation-Based Finger Vein Recognition Using Automatically Generated and Fused Training Labels},
      booktitle = {Handbook of Vascular Biometrics},
      editor = {Andreas Uhl and Christoph Busch and Sebastien Marcel and Raymond Veldhuis},
      year = {2019},
      chapter = {8},
      publisher = {Springer Nature Switzerland AG},
      doi = {https://link.springer.com/chapter/10.1007/978-3-030-27731-4_8},
      isbn = {978-3-030-27731-4},
      pages = {200-223},
      address = {Cham, Switzerland}




This package only contains the masks already extracted from the STUMLA-HMT database.

Download STUMLA-GR:

The data/code is available upon request:

email address: