DS07 - Société de l'information et de la communication

Enhancing Heritage Image Databases – EnHerit

Submission summary

In recent years, computer vision has made several breakthroughs by using very large databases to train deep Convolutional Neural Networks (CNNs). In parallel, a lot of efforts have been invested to digitalize heritage artifacts, such as museum collections or archive images, that are now publicly accessible. CNNs have been successfully tested on these heritage data, but mainly for standard classification tasks, inside a closed database. On the contrary, this project aims at using of the most recent advances in computer vision, and in particular in deep learning, to develop innovative applications that are made possible by the availability of large databases. In particular, we will target tasks such as invariant pattern discovery in large image databases and 3D reconstruction from historical depictions.

Breakthrough progress on these problems would have profound implications both in human sciences such as art history and archaeology, and in their understanding by the public.

Project coordination

Mathieu AUBRY (Laboratoire d'Informatique Gaspard-Monge)

The author of this summary is the project coordinator, who is responsible for the content of this summary. The ANR declines any responsibility as for its contents.


LIGM Laboratoire d'Informatique Gaspard-Monge

Help of the ANR 289,656 euros
Beginning and duration of the scientific project: March 2018 - 48 Months

Useful links

Explorez notre base de projets financés



ANR makes available its datasets on funded projects, click here to find more.

Sign up for the latest news:
Subscribe to our newsletter