17 October, 18h30-19h30
Room 011, Lipsiusbuilding
Cleveringaplaats 1, Leiden
With the latest techniques in the field of computer vision, machine learning, image processing, materials science and visualization theory Robert Erdmann works to preserve, understand and make accessible visual artistic heritage. As a member of the Bosch Research and Conservation Project, he contributes to the development of a new generation of computing and visualization techniques that has been applied to the entire body of work of Hieronymus Bosch.
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 of the pigments a painter used. 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 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.
Please register via S.P.M.Bussels@hum.leidenuniv.nl
Image: Rembrandt’s Isaac and Rebecca, c. 1665, Rijksmuseum