Proposed solution: Provide a mechanism (Gadget or via Wikimedia OCR) that will allow users to demarcate columns and specific areas that need to be OCRed together, and store these areas against the Index page so they don't need to be repeated for every page.
@Sohom data: Just to clarify: the 'profile' here would be e.g. an index-page level store of rectangular page regions that could then be used on all pages to do the OCR, without users having to re-select the same regions over and over again on each page (as they can currently do, and what's more they do it via the Advanced options form and then have to copy and paste the text). Is that right? SWilson (WMF) (talk) 00:50, 1 February 2023 (UTC)[reply]
Support Yes! This would be very helpful for works containing manual annotations as well, or older books where the margins are tight and can confuse the ORC. Waldyrious (talk) 09:55, 11 February 2023 (UTC)[reply]