A Data Capture Framework and Testbed for Cultural Heritage Materials: NSF Proposal

The proposed research will result in a fully automated robotic system for on-demand and batch scanning of print materials (“CAPM”) and an open-source software framework for document analysis that can be trained and calibrated by humanists (“GAMERA”). The resulting system will include an inter-linked mechanism between CAPM and GAMERA. To evaluate different techniques for document analysis, including GAMERA, we will build a testbed of digital images. The project team features an international multidisciplinary team of humanities faculty and post-docs, librarians, a usability specialist, and interdisciplinary digital library researchers. The personnel represent JHU, Tufts University, Edinburgh University, and the University of Oxford. Additionally, the British Library has agreed to provide resources for this project.