The situation is:
I have Data Manager all set up and working. I also have a Microsoft OCR license, and I can use the OmniPage OCR free, as it requires no license.
I have Invoices, that I want to label and extract data using Data Manager. Some of those invoices are in English and some of them are in Cyrillic (Bulgarian).
The problem is:
The invoices in English are being read perfectly, but when I try to process those that are in Cyrillic, lets say, if in the Invoice is “Описание”, the OCR reads it as “OnncaHne” (using Microsoft OCR) which is absolutely incorrect.
When using OmniPage OCR “Описание” is read as “OnIcaHNe”.
Can you suggest how to make the OCR work not only for English but for Cyrillic too.