Project Details

The art historic objective of VISTORY is to revive the study of stylistic development of painting with the help of computer learning. It will do so by developing a visual analytics framework in which we leverage the best of both worlds: Automatic analysis of large scale datasets by the computer, combined with the unique ability of art history experts to make detailed assessments of small sets of images. We will research how image features can be optimized by incorporating knowledge on the creation process and characteristics of materials.

image_vis

From there, we will consider how to visualize the results in such a way that art historians can interactively annotate and re-group the paintings. Machine learning methods will then be developed which use those interactions to improve the model of painting similarity the system has. Integrating the resulting data-driven similarities among the paintings with existing structured metadata about the paintings yield our stylistic histories in terms of visual characteristics, place, and time. The resulting suite of tools will be made available to the community as open source software.

Researchers

strezoski

Gjorgji Strezoski

PhD candidate at the Informatics Institute of the University of Amsterdam. My current focus is applying multimedia analytics in the art domain with deep nets. Graduated at the Ss. Cyril and Methodius university at the Faculty for Computer Science and Engineering in Skopje in 2014 and obtained a Masters degree in Software Engineering at the same institution in 2015.

In November 2016 I started my PhD at the University of Amsterdam under supervision of Marcel Worring on Visual Analytics for paintings.

marcel

Marcel Worring

Associate professor in the Informatics Institute and a full professor at the Amsterdam Business School. He is associate director of Amsterdam Data Science a collaboration between Amsterdam University of Applied Sciences, Center for mathematics and computer science, and the computer science departments of the VU university Amsterdam and the University of Amsterdam on the broad topic of data science.

His research focus is on multimedia analytics combining multimedia analysis, machine learning, and information visualization to yield results surpassing man and machine intelligence.

arjan

Arjan de Koomen

Assistant professor Art History at the University of Amsterdam, with the Early Modern Period as his principle domain. In addition, he is program director of the Master Technical Art History, which starts in September 2015. He received his PhD from the University of Utrecht in 2000, and worked for several years in Italy, at the Vrije Universiteit, as curator of sculpture at the
Rijksmuseum, and at the Ministry of Culture.

Presently, his main field of interest is art technology, specifically the history of making processes in art production.

rob

Rob Erdmann

PhD is currently Senior Scientist at the Rijksmuseum, Amsterdam; Professor of Physics and Conservation Science at the University of Amsterdam; and holds the chair for the Visualization of Art History at Radboud University in Nijmegen. He was formerly Associate Professor in the Department of Materials Science and Engineering and in the Program in Applied Mathematics at the University of Arizona. His broad research interests include software development, visualization, and multi-scale image processing and materials science and engineering. He is the developer of algorithms and techniques for automated canvas analysis and for automated multi-scale stitching and registration for multi-wavelength imaging. He has worked extensively with Dutch museums to apply computational approaches to solving problems in art conservation and technical art history.

cecile

Cecile van der Harten

Cecile van der Harten has been the manager of the Image Department at the Rijksmuseum since 2006. She supervises eight photo studios and the Rijksmuseum’s entire photography archive that supplies images to internal and external clients. The Image Department is responsible for the systematic digitization of the Rijksmuseum collection comprised of approximately one million objects. The aim of the Image Department is to have the entire collection digitized online by 2020. A high-quality standards-based workflow and a Digital Asset Management (DAM) system has been established to accomplish this ambition. The Image Department is also responsible for the implementation of a centralized workflow in SharePoint for the museum to order and search images in the DAM system.
She is the project leader for the movement of the Rijksmuseum repository from Lelystad to a new building under construction in Amersfoort called the Collection Center Netherlands (CCNL), which will be shared with the collections from Het Loo Palace National Museum, the Cultural Heritage Agency of the Netherlands and the Holland Open Air Museum in 2019.
In 2015 Cecile organized the first successful international heritage photography conference 2and3D Photography–Practice and Prophecies, in the Rijksmuseum. The “sequel” 2and3D Photography-Practice, Prophecies and Beyond has taken place in May 2017.

charles

Charles van den Heuvel

Charles van den Heuvel studied Art History at Groningen University with a specialization in the history of architecture, town planning and planning sciences. ( PhD 1991). After a stay in Florence (Italy) where he worked as a librarian and researcher at the Dutch Institute for Art History, he held the position of senior-researcher at the universities of Groningen, Utrecht and Maastricht in the Netherlands. He published regularly on themes of the Dutch history of science and technology of the 16th and 17th centuries. His most important publication was a (re-)construction of an unpublished treatise of the Dutch scholar Simon Stevin on architecture and town planning, De Huysbou-A reconstruction of an unfinished treatise on architecture, town planning and civil engineering by Simon Stevin, History of science and scholarship in the Netherlands. volume 7 Edita,Amsterdam 2005. Furthermore, he was as an Inspector of Cultural Heritage for the Dutch Ministry of Education, Culture and Sciences and a curator of the cartographical collections of Leiden University Library. At the Maastricht McLuhan Institute and the Virtual Knowledge Studio of the Royal Netherlands Academy of Arts and Sciences he worked on several projects in the domain of digital humanities.

Research interests are history of art, architecture and town planning, history of cartography, history of science and the history of library and information sciences. In 2010 he was employed as a Regents’ Lecturer at the University of California, Berkeley. At the moment he participates in research in the Alfalab and the e-Humamities Research Group of the Royal Netherlands Academy of Arts and Sciences focusing on the use of annotation and visualization in the (digital) humanities. His most recent research within the Huygens ING Institute Huygens ING deals with relations between the history of classification and of (universal) knowledge and the use of digital means and methods in the history of science.

OmniART

OmniART – a new large scale artistic dataset containing more than 1.1M visual entries with rich metadata is being released this month.

omniart.png

Contact

Any thoughts or comments? Get in touch and send us an email!

Contact email “]