Building Inspector

Public engagement tool for the extraction, correction and analysis of data from historical maps

Building Inspector is an open tool that promotes public engagement for the extraction, correction and the analysis of data provided by historical maps. As volunteers  inspect polygons, the API endpoints below get updated on a daily basis to reflect the latest data (both the perfect and the imperfect bits). The New York Public Library (NYPL) is training computers to recognize building shapes and other data on digitized insurance atlases. Via these easy, bite-sized tasks, you can help check the computers’ work and capture other valuable information

The maps in Building Inspector come from historical atlases of New York City which, rather than being one big map, are split into pages as they’re in books. Polygons come from atlas sheets which are scanned one at a time and then geo-rectified via the NYPL Map Warper. The vectorizer goes through each map sheet and extracts buildings as best it can. And it’s not good enough; that’s why this site exists: to validate and improve the output of the vectorizer.

Currently, there are four different types of inspections users can perform. Each is designed to extract a particular type of data from the maps, as it can be seen below:

  • Check Footprints – This establishes a baseline (literally!). We show you the buildings the computer identified, one outline at a time. You tell us whether it is right, wrong, or close but in need of fixing.
  • Fix Footprints – Take those slightly imperfect footprints identified by your fellow inspectors and get them into shape to be recorded for history.
  • Enter Addresses – Getting those original street numbers will help us to reference specific buildings in their historical context (and, eventually, to see who lived/worked there).
  • Classify Colors – The original mapmakers color-coded the buildings to indicate construction materials and use types (residential vs. commercial). Identifying the colors helps us index these important details.

Currently, this application is used by the New York Public Library Labs.