PreviewNot yet reviewed. Cards on this preview are seed data waiting for the editors’ approval, so check anything before you cite it.

Preview · 19 tools · 6 datasets · 75 projects · seeded October 2026

The tools and datasets historians actually used, and where.

Pull out a drawer to see what’s filed inside. Every card separates research that used a tool from the benchmarks that tested it.

The drawers

A tool can be filed in more than one drawer
  • DRAWER II

    OCR & Handwriting

    Turning page images into searchable text, from printed newspapers to manuscript hands.

    Guide cards

    Counts research and corpus-building uses in the window, plus “I’m using this now” check-ins. Benchmarks don’t count.

    • tool · No. 012

      Tesseract

      Free, long-standing program that turns images of printed pages into searchable text. Best on clean, high-resolution scans; old or damaged print usually needs clean-up first.

      At a glance
      Maker
      HP Labs, then Google; now community-maintained
      Released
      Open-sourced 2005
      Licence
      Open source (Apache-2.0)
      Cost
      Free
      Runs
      Your own machine (Linux, Windows, macOS)
      Skill
      Some code
      Historian’s notes
      Where your sources go Fully local. Nothing leaves your computer.
      How it’s been tested Error rates of 10–17% on historical US newspapers (Dell et al. 2023); about 83% word accuracy on Finnish newspapers, 1869–1918.
      Known problems on historical sources Struggles with skew, smudges and uneven backgrounds; reads column borders as characters. Whole multi-column newspaper pages do worse than pages split into regions.
      Used in research0

      No published research uses found yet. Using it in a project? Tell us.

      Used to build corpora2
      Tested in6

      Nobody has said they’re using it in 2026 yet. “I’m using this now” asks you to sign in with ORCID. One count per person per year; it adds to Trending, and names are never shown.