🚀 go-pugleaf

Hello I am working on a project with bound journals from 1910 to 1950. We are scanning the images as 600dpi TIFF's. And then using Adobe Capture 3.0 to: Zone Image, Capture, Bind, Export to PDF and Store the files.

My problem is that Capture is not recognizing the entire page as text and is leaving large portions of the page not OCR'ed... sometimes. Other times it does a fine job. I have adjusted the Suspect Confidence from 95% to 75% to 50%. I then rescanned the problem pages with no success.

I think Capture is missing part of the page becuase the bound spine prevents the page from setting flat on the scanner bed. The sections of the page being missed are not always close to the spine and can include parts of the page that do lie flat on the scanner bed??

If I have to I can disbind the issues and scan them flat but this is a last resort. Does anyone have some tips or ideas to help me with this problem?

Thank you.