Of course it depends on what kinds of texts you're looking at, but my experience with text-only academic articles/books and 240-300 dpi scans is that with a little clean-up, OCR is very good already. I'd recommend playing with your scanner settings up front to minimize background noise and make sure your text is mostly black or nearly black pixels. Save to tiff or png, if you can. You're right that jpeg will hurt.
(I even have some scripts that use ImageMagick to clean the scans, and I'm not the only one. :-) : https://github.com/Jmuccigr/scripts ) -- A list of frequently asked questions is available at: http://wiki.panotools.org/Hugin_FAQ --- You received this message because you are subscribed to the Google Groups "hugin and other free panoramic software" group. To unsubscribe from this group and stop receiving emails from it, send an email to hugin-ptx+unsubscr...@googlegroups.com. To view this discussion on the web visit https://groups.google.com/d/msgid/hugin-ptx/a6fb9890-bec1-4214-a1b4-5c9eda1d3fcd%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
