Natural Historical Archives as Digital Challenge and Opportunity
Feb 08, 2017 05:30 PM
End: Feb 08, 2017 06:30 PM
Location: Room G31, Foster Court, UCL, Gower Street, LONDON, WC1E 6BT
In the first half of the nineteenth century, the Indonesian Archipelago witnessed various attempts to describe, classify and manage local natural resources. Next to a large number of detailed reports on the cultivation of cash crops, this resulted in a unique collection of fieldnotes, field diaries and drawings documenting the area’s variegated flora and fauna. Over the last decade, many of these handwritten manuscripts, drawings and specimens have been digitized and are now stored on servers of natural history museums in the Netherlands and beyond. However, owing to their heterogeneous character and complex structure, the material has never been fully disclosed and interlinked.
In order to address this challenge, we are currently developing a user-friendly and technologically advanced digital environment which is meant to facilitate the work of historians, biologists, and curators interested in disclosing digitized natural historical and other illustrated handwritten collections. At the core of our digital environment is MONK. MONK is a state of the art word retrieval system achieving a high level of accuracy on a wide range of script styles. The MONK system uses shape-based feature vector methods that have very few assumptions concerning the content and style of the material. Because of its visual approach, MONK can handle the diversity of material that we encounter in our use case and in historical collections in general: handwritten text, drawings, and images. Next to a demonstration of MONK and reflections on recent developments in automated handwriting recognition, our presentation discusses the digital environment’s basic layout and sketches its realization in the period 2016-2020. The project is financed by a major grant of the Netherlands Organization for Scientific Research (NWO) and the publishing house BRILL.
All welcome and there will be drinks and discussion after the talk. Please note that registration is required.
Lambert Schomaker is professor of Artificial Intelligence and director of the Institute of Artificial Intelligence and Cognitive Engineering (ALICE), both at Groningen University, the Netherlands. He is the main developer of the MONK system.
Andreas Weber is a postdoctoral researcher of the project Making Sense of Illustrated Handwritten Archives (2016-2020). He is based at the University of Twente, also in the Netherlands. Much of his research focusses on naturalists who investigated the flora and fauna of maritime Southeast Asia in the first half of the nineteenth century.