OCR naked bit strings in PDF files

  • Last Post 03 February 2015
russr posted this 23 January 2015

I have constructed pdf files that contain rows of ones and zeros and spaces nothing else. The font is a single old IBM font. The PDF files were created from scanned 60 year old IBM engineering documents produced on IBM 60s era high speed printers. Files containing say up to 10 rows of ones and zeros and spaces do pretty well. But when the number of rows inceases to around 40 the results are all over the map and unworkable.

Order By: Standard | Newest | Votes
Julia Anikushina posted this 26 January 2015

In order we could better assist you please send an example of such document to cloudcrsdk@abbyy.com in case you use ABBYY Cloud OCR SDK or to SDK_Support@abbyy.com in case you have some other ABBYY SDK product (if so, please also add your serial number). Also please specify which settings you use for recognition.

russr posted this 03 February 2015

Thanks for answering my post. I have decided on a different approach and am no longer seeking a solution using your software. Again thanks for you offer of help.