OCR document with tables

[Singh1]

Acrobat OCR doesn't retain information in tabular form even when tables are clearly defined by lines and boxes. I tested it with Microsoft word OCR and tables are well managed though text recognition is better with Acrobat OCR. It would be even better if it can recognize tally marks and dots or other symbols in tables. Also, I would like to skip OCR where there is image  as I don't want captions and other text in image to break or separate and it should be possible with well scanned document automatically or I should be able to manually tell acrobat where there is image. I'm looking to reformat high quality scanned document so I can easily view it on my smartphone.

[Abambo · Accepted solution]

Discussion successfully moved from Adobe Creative Cloud to Scanning & OCR

OCR on Acrobat is not meant to replace a full fledged OCR system. It's meant to create searchable PDF files with the text behind function. If you need text recognition at the level you describe, you need to buy specialised software for that domain.

[Rami27098271q7i5]

if we manually tag table cells would this improve text recognision?