Convert scanned Cyrillic characters from PDF to Word

[josian]

Hi, I would like to check with a support however after trying to use the Support Center, I gave up as there's no contacts to any such resource. Basically, I am an IT Support Analyst who got a request for a solution to Convert scanned Cyrillic characters from PDF to Word from one of our Directors. So naturally, I tried to do it with our purchased Adobe Acrobat DC professional. However, the output was pretty terrible and didn't manage to capture most of the words that mattered. I heard about issues like this but didn't expect it to be that terrible. Can anyone (Adobe support or not) give some advice on this? Due to the confidential nature of the documents, I am not able to provide the source files etc. However, I tried converting other PDFs with Cyrillic characters and it seems to be consistently bad. Thanks in advance.

[try67 · Accepted solution]

OCR is an extremely tricky process. The results will vary widely based on the quality of the paper, the quality of the scan, the quality of the scanner, the way the paper was created (typewriter? printed? hand-written? etc.), and of course the algorithm of the OCR application itself. You have no control over the latter, and maybe not over some of the former, so improve what you can and try out different OCR engines until you find one that works for you, but keep in mind that if the source material is problematic the results will be as well.