About

AIKON-demo is a platform to run computer vision experiments on user-defined datasets. It is tailored to historical document analysis and offers state of the art algorithms for region extraction (image, diagram or text detection), similarity retrieval, watermark detection and image clustering.

Once you have selected the experiment to run, AIKON-demo has a 3-step workflow:

  1. Pick a dataset, or upload a new one
  2. Configure the experiment (which algorithm and parameters)
  3. Run the experiment and visualize results

AIKON-demo is developped cojointly with the AIKON platform, which offers research projects a collaborative environment for historical corpora management, computer vision and document analysis.

If you enjoy the project, you can cite our work:

Albouy, S., Norindr, S., Kervegan, P. et al. AIKON: a modular computer vision platform for historical corpora. IJDAR 29, 801–814 (2026). https://doi.org/10.1007/s10032-026-00581-x

@article{albouy2026aikon,
    title={{AIKON : A Modular Computer Vision Platform for Historical Corpora}},
    author={
        Albouy, Ségolène and
        Norindr, Somkeo and
        Kervegan, Paul and
        Aouinti, Fouad and
        Delanaux, Rémy and
        Champenois, Robin and
        Grometto, Clara and
        Lazaris, Stavros and
        Guilbaud, Alexandre and
        Husson, Matthieu and
        Aubry, Mathieu
    },
    url={https://doi.org/10.1007/s10032-026-00581-x},
    year={2026},
    month={June},
    journal={International Journal on Document Analysis and Recognition (IJDAR)},
    keyword={Digital Humanities, Computer Vision, Historical Documents, Visual Analysis},
}

AIKON-demo is developped at the École nationale des Ponts et chaussées's IMAGINE lab as part of the ERC project DISCOVER funded by the European Union’s Horizon Europe Research and Innovation program under grant agreement No. 101076028.