The Reconstruction of Torn Documents

(bundesarchiv.de)

27 points | by jacquesm 2 days ago ago

3 comments

  • bbor 18 minutes ago

    Wow, fascinating! I hope I’m not the only OCR-minded soul on here that immediately started thinking of pipelines for this one could assemble from all our new DL-enabled toys… it’s a shame that “some American kid” probably doesn’t meet their contracting requirements.

    One thing that kinda baffles is that it sounds like the snippets (I bet that German word is fun) haven’t been scanned(/photographed…?) yet. No matter who they contract with, wouldn’t that necessarily be step #1? Or is the scanning the part that needs contracting, and the “e-Puzzler” name was just a lil melodramatic?

    For one thing, I feel like it’ll be wildly helpful that they’re on a variety of papers, not challenging like they imply. Once that and bag index have narrowed down neighbor candidates, you’ve got rules and glyphs to go off of, much less recognizable form layouts. It feels like the Vesuvius scrolls but actually tractable…

  • esafak 38 minutes ago

    There's nothing technical to discuss; where's the meat? This 2012 article at least has pictures: https://www.bbc.com/news/magazine-19344978

    I speculate the problem is not technical but financial or otherwise; the ML to do this was up to the task at least ten years ago.

  • lifestyleguru 42 minutes ago

    "We simply rehired all Nazi's and Stasi's but here there is a sophisticated technical problem to keep you busy."