OCR recognition settings

[hbkidd_navy]

I'm using Acrobat Pro Xl to convert jpeg to searchable multiple page PDF. 

The project involves the scanning of 1000+ pages of "very aged" historic documents.   The documents contain lists of, 20K names / serial #s / military units,.

Due to the document condition, age/discoloration/ faded type/etc, the Character Recognition engine identifies 98% plus of the data as suspect.   Hi gh percentage of the suspect data is actually correct.  We are willing to accept a lower accuracy rate to capture an higher percentage names, serial #s, etc.

The question is - can we adjust the OCR confidence levels, or is there a way to globally accept all the suspect items.   The suspect by suspect review is not feasible.

Thank You,

[YatharthS]

Hi hbkidd_navy,

Would request you to please set the option for 'Editable Text & Image' under settings for Recognize Text .You may also set the Down sample value to 600 DPI.

Regards,

Yatharth