Support multilingual OCR
Created by: VorpalBlade
Tesseract has support for using more than one language at the time (according to the man page they should be separated by a +). It would be an useful feature to add to Paperwork since my use case involves processing documents where there could be a mix of Swedish and English on the same page even.
I do not know if other OCR engines can do this.
Edited by Jerome Flesch