Many maps scanned into large historical collections can be difficult to use in their current digitized form. The ML4GIS team understands how map collections could be easier to work with, but the current processing time is not feasible for these extremely large collections. This team will investigate computer vision approaches and apply them to the map collections to enhance the valuable information they contain. The project strives to make the map data more effective and widely available for civic uses, such as historical reference for modern project planning and University research.


Project team: Aaron Choate (University of Texas Libraries), Michael Shensky (UT Libraries and Department of Geography and the Environment), Danna Gurari (School of Information), William Doolittle (Department of Geography and the Environment), Ross Clark (City of Austin Water), Jennifer Hecker (City of Austin History Center) and Mike Miller (Cityof Austin History Center)