Hacker News new | past | comments | ask | show | jobs | submit login

> besides the scientific (or at least practical, at the current level of OCR/machine learning) impossibility

I'd hardly say impossible. It's being done, today. See this article:https://www.uni-wuerzburg.de/en/sonstiges/meldungen/detail/a... or these papers: http://pages.jh.edu/~dighamm/version2/research/2003_10_digit... and https://graphics.stanford.edu/papers/cuneiform/cuneiform-300...

These describe scanning of ancient clay tablets, for archival and information retrieval purposes. Note that the Johns Hopkins research on archiving is from 2003. I suspect the blocker may be money, rather than practicality; these aren't simple flatbed scanners, the tables must be scanned in 3D to recover the full detail required. But, it's an incredibly fascinating area of research to read about.

EDIT - So, I did some more reading, and it seems that the Johns Hopkins work I referenced above is part of The Digital Hammurabi Project which is doing exactly this, archiving cuneiform tablets, described here: http://pages.jh.edu/~dighamm/version2/research/2003_03_Museu... with more information on the projects website: http://www.jhu.edu/digitalhammurabi/




Join us for AI Startup School this June 16-17 in San Francisco!

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: