Aikon logo AIKON: A Modular Computer Vision Platform for Historical Corpora

Ségolène Albouy1, Somkeo Norindr2, Paul Kervegan1, Fouad Aouinti3, Clara Grometto2, Robin Champenois1, Alexandre Guilbaud3, Matthieu Husson2, Stavros Lazaris4, Mathieu Aubry1

1 LIGM - Imagine team, École des Ponts, Univ Gustave Eiffel, CNRS, Marne-la-Vallée, France
2 LTE, Observatoire de Paris-PSL, CNRS, Paris, France
3 ISCD, Institut de mathématique de Jussieu, Sorbonne Université, Paris, France
4 Orient & Méditerranée - UMR 8167, Collège de France, EPHE, Sorbonne Université, Paris, France
AIKON is a modular computer vision platform that enables historians to build, process, and analyze visual corpora at scale. The platform guides users through a complete workflow from corpus construction to algorithmic processing and result validation, without requiring technical expertise. Built on IIIF standards and featuring a flexible data model, AIKON supports collaborative research while maintaining full user control over automatic processing. Its modular architecture allows easy integration of new computer vision algorithms and visualization tools, making it adaptable to diverse research needs across historical document analysis.

Platforms

AIKON Platform

Main platform for computer vision analysis of historical documents

AIKON Demo

Demo version showcasing platform capabilities

Technical article Case Studies Presentation

Overview

Aikon capabilities

At its core, Aikon allows researchers to describe their sources, import scans, request automatic processing, and manually refine results. Built on proven technologies and interoperable formats, including established standards such as IIIF, the platform's architecture supports a wide range of visual materials. Aikon's data model, centered around the concepts of Series, Witness, and Content, provides a flexible framework capable of describing diverse source materials while facilitating alignment across varied corpora.

The platform's modular structure enables easy integration of additional functionalities, with current applications including illustration extraction, similarity search, and vectorization. Aikon is not tied to any predetermined analysis methods; all stages can be performed manually or automated, with specialized models customizable to specific datasets. This approach ensures adaptability to various research needs while maintaining reproducibility. By fostering interdisciplinary collaboration and sustainability across digital humanities projects, Aikon aims to assist researchers to explore corpora at an unprecedented scale, helping bridging the gap between advanced computational methods and the nuanced requirements of humanities research.

Key Features

Aikon workflow

Collaborating Projects

VHS

Computer Vision and Historical Analysis of Scientific Illustration Circulation

ANR-21-CE38-0008

EiDA

EdIter et analyser les Diagrammes astronomiques historiques avec l'intelligence Artificielle

ANR-22-CE38-0014

DISCOVER

Discovering and Analyzing Visual Structures

ERC-101076028

Platform Interface

To get an account on aikon.enpc.fr to try all platform features, don't hesitate to contact us.

Similarity exploration interface

Get Involved

Explore the Aikon project and contribute to its development on GitHub .

Bibtex

@article{albouy2025aikon,
    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
        Lazaris, Stavros and
        Guilbaud, Alexandre and
        Husson, Matthieu and
        Aubry, Mathieu
    },
    url={https://hal.science/hal-05248250},
    year={2025},
    month={Sep},
    number={hal-05248250},
    journal={HAL Pre-Print},
    keyword={Digital Humanities, Computer Vision, Historical Documents, Visual Analysis},
}