jochre icon indicating copy to clipboard operation
jochre copied to clipboard

Published 20 hours ago • verified publisher icon urieli

OCRed text cut too narrow - how to correct or report

Open mirjam-amsterdam opened this issue 5 years ago • 1 comments

in this snippet an nun went missing. (or instead of nor) most probably the text-width of the scanned book was set too narrow. Should I just add the nun, or should I report such cases to github?

https://archive.org/stream/nybc203972#page/n176/mode/1up

too narrow letter missing

mirjam-amsterdam avatar Oct 03 '19 09:10 mirjam-amsterdam

No, do not correct such cases, because the text will no longer correspond to the image within the word boundaries. It's better to report this on Github. Hopefully such issues will be vastly reduced in Jochre 3, better segmentation being our first objective.

urieli avatar Oct 05 '20 20:10 urieli