The Measurement of Images: Computational Approaches in the History and Theory of the Arts

The #dhnord colloquium brings together the digital humanities community every year at the Maison Européenne des Sciences de l'Homme et de la Société in Lille. The theme chosen for 2020 considers computational approaches to images in the history and theory of the arts. This conference will bring together for the first time in France the leading specialists in artificial intelligence applied to the arts. The history of arts and culture, as well as aesthetics, have greatly benefited in recent years from the results of heritage digitization campaigns. Since 2013, digital art history has experienced unprecedented growth, particularly in the Anglo-Saxon spheres and in Europe (Joyeux-Prunel, Drucker 2013, Zorich 2012). While the analysis of texts has long been favored by the digital humanities, it is now becoming possible to carry out computational analyses on the very matter of images, or even on 3D objects, which constitutes a major turning point. This colloquium will explore how computational methods are renewing traditional questions of art history, aesthetics and visual culture (creative process, style, form, attribution, iconology, circulation of works, etc.) and raising new research questions for our disciplines (visual arts, architecture, theatre, cinema, photography, etc.) at a time when new tools are becoming available to researchers.


DHNord’s 2020 edition will take place entirely online, as a result of the sanitary crisis provoked by COVID-19.  Confirmed Speakers are: Taylor Arnold (University of Richmond), Peter Bell (University of Erlangen-Nürnberg), Emmanuelle Bermès (BnF), Dominique Cardon (Sciences Po), Johanna Drucker (University of California, Los Angeles), Nicolas Gonthier (Télécom Paris), Leonardo Impett (University of Durham), Béatrice Joyeux-Prunel (University of Geneva), Pierre-Carl Langlais (Université Paul-Valéry Montpellier 3, Sorbonne Université), Stefaan Van Liefferinge (Media Center for Art History at Columbia University), Isabella di Lenardo (EPFL), Matthew Lincoln (Carnegie Mellon University), Lev Manovich (City University of New York), Nanne van Noord (University of Amsterdam, Netherlands Institute for Sound and Vision), Emily L. Spratt (Data Science Institute at Columbia University), Lauren Tilton (University of Richmond) and Timothy R. Tangherlini (University of California, Berkeley).


We believe that posters are still a necessary and important part of our conference, so we will be maintaining our poster session, sharing them on the conference website. During the conference, November 17-20, they will also be tweeted out from the official @MESHS_Lille account with the hashtag #dhnord2020, and we encourage you to follow along and participate as well.

Papers may address the following topics: uses of artificial intelligence (especially deep learning and machine learning) applied to image corpora, data construction, and processing issues, epistemological questions related to the selection of training corpora and the use of tools, historical evolution of the field, renewal of research questions, availability of corpora, reproducibility of research and sharing of models.

Posters may be submitted in English or French. Owing to this completely-online format, we are changing from the traditional poster format (one large portrait) to a four slide landscape presentation of your research. Please note that your submissions should be the final product, there will be no period for revisions. You may find templates (for use in Powerpoint or Impress) for posters, which you must use, HERE.


Please submit your poster at:




11/09/2020: publication of call

15/10/2020: poster submission deadline

01/11/2020: notification of accepted posters

05/11/2020 : publication of posters on MESHS website


Chairs: Clarisse Bardiot and Emmanuel Château-Dutier

Scientific Committee:

Elise Baillieul (ULille)

Clarisse Bardiot (UPHF, MESHS)

Emmanuel Château-Dutier (Université de Montréal, CRIHN)

Antoine Courtin (INHA)

Océane Delleaux (ULille)

Béatrice Joyeux-Prunel (University of Geneva)

Nicolas Hervé (INA)

Kristin Tanton (Université de Montréal, CRIHN)

Nicolas Thély (University of Rennes, MSHB)



Indicative bibliography

Arnold, Taylor et Lauren Tilton. s. d. « Distant Viewing: Analyzing Large Visual Corpora ». Digital Scholarship in the Humanities.

Cardon, Dominique, Jean-Philippe Cointet et Antoine Mazières. 2018. « La revanche des neurones: L’invention des machines inductives et la controverse de l’intelligence artificielle ». Réseaux 211 (5) : 173.

Drucker, Johanna. 2013. « Is There a “Digital” Art History? » Visual Resources 29 (1-2, Digital Art History). Routledge : 5-13.

Ellis, Margaret Holben et C. Richard Johnson Jr. 2019. « Computational Connoisseurship: Enhanced Examination Using Automated Image Analysis ». Visual Resources 35 (1-2, Digital Art History). Routledge : 125-140.

Fyfe, Paul et Qian Ge. s. d. « Image Analytics and the Nineteenth-Century Illustrated Newspaper ». Consulté le 16 janvier 2019.

Moretti, Franco et Leonardo Impett. 2017. « Totentanz. Operationalizing Aby Warburg’s Pathosformeln. Pamphlets 16 ». Literary Lab, Stanford.

Joyeux-Prunel, Béatrice. 2010. L’art et la mesure : histoire de l’art et méthodes quantitatives. Actes de la recherche à l’Ens 5. Paris : Éditions Rue d’Ulm ; Presses de l’École normale supérieure.

Klinke, Harald et Liska Surkemper, éds. 2016. Visualising big image data. International Journal of Digital Art History.

Manovich, Lev. 2012. « How to Compare One Million Images? » Dans Understanding Digital Humanities, édité par David M. Berry, 249-278. London : Palgrave Macmillan UK.

Rodríguez-Ortega, Nuria. 2020.  « Image processing and computer vision in the field of digital art history. » Dans The Routledge Companion to Digital Humanities and Art History. Brown, Kathryn, éd. Routledge Art History and Visual Studies Companions. New York : Routledge.

Seguin, Benoit. 2018. « The Replica Project: Building a Visual Search Engine for Art Historians ». XRDS 24 (3) : 24–29.

Shen, Xi, Alexei A. Efros et Mathieu Aubry. 2019. « Discovering Visual Patterns in Art Collections with Spatially-consistent Feature Learning ». arXiv:1903.02678 [cs], mars.

Vane, Olivia. 2019. Timeline Design For Visualising Cultural Heritage Data. PhD Thesis, Innovation Design Engineering, Londres : Royal College of Art.

Wevers, Melvin et Thomas Smits. s. d. « The Visual Digital Turn: Using Neural Networks to Study Historical Images ». Digital Scholarship in the Humanities.



Online user: 1