Machines Reading Maps
Unlocking unique information from large collections of historical maps using AI
Project maintained by machines-reading-maps
Machines Reading Maps
Machines Reading Maps (MRM) is a collaborative project between the University of Southern California Digital Library and Computer Science & Engineering Department at the University of Minnesota (US)and the Alan Turing Institute (UK). The project is funded by the United States’ National Endowment for the Humanities (NEH) and the United Kingdom’s Arts and Humanities Research Council (AHRC) under the first round of NEH/AHRC New Directions for Digital Scholarship.
MRM seeks to normalize map text as a new kind of data that can be used across the humanities and the heritage sector. To do so MRM will change the way that humanists and heritage professionals interact with digitised map images. Maps constitute a significant body of global cultural heritage, and they are being scanned at a rapid pace in the US and UK. However, most critical investigation of maps continues on a small scale, through close readings of a few maps. Individual maps communicate through visual grammars, supplemented by text. But text on maps, particularly in aggregate, is a nearly untapped source about the construction of knowledge about place (with the notable exception of the GB1900 project, which crowdsourced transcriptions of all labels on the ca.1900 6-inch Ordnance Survey maps of Britain). While we speak colloquially about reading maps, MRM concretely addresses how to make text on maps an accessible resource. We will make maps searchable and linked to other geospatial data and collections, creating the possibility for humanities research that uses map text as a primary source. Spatial searching will no longer be limited by metadata fields like place of publication, but instead allows queries based on the labeled, spatial content of visual materials.
We will share code, datasets, and more via this website.
People
- UK
- US
- Advisory Board
- Daniel van Strien, British Library (co-chair)
- Gethin Rees, British Library (co-chair)
- Ruth Ahnert, Queen Mary, University of London/The Alan Turing Institute
- Sarah Ames, National Library of Scotland
- Kaspar Beelen, The Alan Turing Institute
- Nicole Coleman, Stanford University Libraries, Stanford University
- Chris Fleet, National Library of Scotland
- Tom Harper, British Library
- Paulette Hasier, Library of Congress
- Kasra Hosseini, The Alan Turing Institute
- Hsiung-Ming Liao, Research Center for Humanities and Social Sciences at Academia Sinica
- Nathan Piekielek, The Pennsylvania State University
- Bert Spaan, Independent Researcher
- Daniel C.S. Wilson, The Alan Turing Institute
Newsletter
Target Map Collections
- National Library of Scotland and British Library Ordnance Survey historical map collections (the 1st and 2nd editions of the 6-inch and 25-inch to 1 mile sheets)
- Library of Congress Sanborn fire insurance map collection
- British Library Goad fire insurance map collection (19th- and early 20th-century)
Cultural Heritage Partners
- National Library of Scotland (NLS)
- British Library (BL)
- Library of Congress (LC)
Events
- UCGIS Webinar (5/4/2021)
- Annotation workshop (beta) (12/10/2021) 17 participants from UK, Ireland and the Neatherlands.
- Annotation Workshop (beta) (18/10/2021). 8 participants from the US
- Annotation workshop (15/12/2021), in collaboration with OS200 and part of the Linked Pasts VII Symposium. 40 international participants
- MRM Roundtable, (16/12/2021) in collaboration with OS200 and part of the Linked Pasts VII Symposium. 20 international participants
- Keynote for Linked Pasts VII (17/12/2021)
- Demo for the David Rumsey Map Collection (11/01/2022)
- Presentation on SIGSPATIAL GeoAI(02/11/2021): Slides Video
- Annotation workshop for the OS200 team (date tba)
- Geo4Lib Camp (02/02/2022)
- Public collaborative annotation event, in partnership with the National Library of Scotland, to create an historical gazetteer of the city of Edinburgh in 19th century (April 2022)
Publications
- Li, Zekun, Runyu Guan, Qianmu Yu, Yao-Yi Chiang, and Craig A. Knoblock. “Synthetic Map Generation to Provide Unlimited Training Data for Historical Map Text Detection.” In Proceedings of the 4th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery, pp. 17-26. 2021.
Blogposts
Publicly Available Code
Tutorials