I OCR books, so they are not a good sample. I would want to compare at least 10 pages per sample, with more typical problems such as skewed, rounded pages from photos, artifacts, damaged source pages (tears and creases) etc. They do reproduce some problems with changing fonts and layout, but a big piece of the puzzle is custom dictionaries and layout training. It's fine for a once over, but not a deep dive.
What are your favorites overall for book scanning? I'm building a DIY scanner and have only briefly considered the actual software I'll use in the processing pipeline. FOSS or API tooling preferred unless proprietary packages are significantly better.
ABBYY has been much better than anything else due to its abilities to fine tune layout, recognition, and export parameters. I follow threads like this, always looking for the latest and greatest, but nothing else is worth the time for a smaller organization. We scan several languages. If you are English only, I can't answer about recognition since I don't look. But layout and export are mission critical, and worth a few hundred bucks if you can afford it.
Thanks for the response. Which ABBYY product(s) is this? I'm a little confused by their website, seems like they offer quite a lot of combinations of things.
