Robert G. Erdmann spoke at the Seminar in Renaissance and Early Modern Material Culture on Tuesday, October 22, at 6 pm. His talk was entitled “The Secret Life of Art: Data Science for Art History and Art Conservation.”

The simultaneous advent of super high-resolution imaging, high-speed internet, and massive data storage capacities have moved us from a world in which we didn’t have enough technical data about art objects to one in which we risk drowning in a data deluge. The use of machine learning tools such as image recognition and segmentation with deep convolutional neural networks can help us to draw insight from this torrent of data in many ways. Combining different imaging techniques, such as visible photography, UV-induced visible fluorescence, infrared reflectography, and scanning x-ray fluorescence (MA-XRF), we can see under the surface of a painting to directly observe pentimeni, the effects of restoration, and even the chemistry and stratigraphy of a painting. For 3D objects, multiple photos from different angles can be fused together to create 3D models of art objects and to make precise comparisons across different objects to see their relation to each other. Several novel web-based interactive visualization techniques developed by Erdmann allow us to zoom into an object to inspect it in extraordinary detail or to zoom out from it to see it in the context of entire oeuvres, time periods, or entire museum collections. These new techniques are demonstrated interactively using a variety of artworks, including masterpieces from Bosch, Van Vianen, De Vries, Rembrandt, Vermeer, Frans Hals, and Van Gogh.


Prior to earning his PhD from the University of Arizona in 2006, Robert Erdmann started a science and engineering software company and worked extensively on solidification and multiscale transport modeling at Sandia National Laboratories. He subsequently joined the faculty at the University of Arizona in the Program in Applied Mathematics and the Department of Materials Science and Engineering as Assistant Professor and then Associate Professor, where he worked on multiscale material process modeling and image processing for cultural heritage. After a 2013 Resident Fellowship at the Netherlands Institute for Advanced Study, in 2014 he moved permanently to Amsterdam to focus full-time on combining materials science and computer science to help the world access, understand, and preserve its cultural heritage. From 2014–2016, he was Special Professor for the Visualization of Art History at Radboud University. Since 2014 he has served as Senior Scientist at the Rijksmuseum, and as Full Professor of Conservation Science in the Faculties of Science and of Humanities at the University of Amsterdam. He is a recipient of the Europa Nostra Award (Grand Prix), the highest prize for cultural heritage in the European Union for his work on the Bosch Research and Conservation Project. He is the inventor of the “Curtain Viewer” visualization technique, which is featured at http://boschproject.org and elsewhere, and has worked extensively on automated canvas analysis for easel paintings.