tags 599181 pending thanks > Recognition of a scanned text within gscan2pdf using ocropus > results in a worse quality than running e.g. ocrodjvu afterwards. > Besides the general quality problems, umlauts like äöü are not > recognized at all, e.g. ü is always replaced with ii. This makes > the OCR feature impractical for german language texts.
This was due to ocropus not honouring the tesslanguage option. An ocrodjvu user pointed me at the workaround that ocrodjvu uses, which I have implemented upstream and which you will see in the next release. -- To UNSUBSCRIBE, email to [email protected] with a subject of "unsubscribe". Trouble? Contact [email protected]
