Main Page/Methodology: Difference between revisions
From HBMa
(Created page with "Digitization of scanned registry books uses modern machine learning methods like layout segmentation, handwritten text recognition ([https://kraken.re/main/index.html Kraken], [https://gitlab.com/scripta/escriptorium eScriptorium]) and [https://happytransformer.com/text-to-text/ text-to-text transformers]. Tools") |
No edit summary |
||
| Line 1: | Line 1: | ||
Digitization of scanned registry books uses modern machine learning methods like layout segmentation, handwritten text recognition ([https://kraken.re/main/index.html Kraken], [https://gitlab.com/scripta/escriptorium eScriptorium]) and [https://happytransformer.com/text-to-text/ text-to-text transformers]. | [[Project:Digitization|Digitization]] of scanned registry books uses modern machine learning methods like layout segmentation, handwritten text recognition ([https://kraken.re/main/index.html Kraken], [https://gitlab.com/scripta/escriptorium eScriptorium]) and [https://happytransformer.com/text-to-text/ text-to-text transformers]. | ||
[[Project:Nástroje|Tools]] | [[Project:Nástroje|Tools]] | ||
Latest revision as of 14:06, 21 December 2023
Digitization of scanned registry books uses modern machine learning methods like layout segmentation, handwritten text recognition (Kraken, eScriptorium) and text-to-text transformers.
