Hi Everyone, I am sure this has been discussed multiple times on the list before, but I'd nonetheless be grateful if someone could help me with this. I use Fine Reader 11. More than 60% of the documents I receive at work are inaccessible PDFs which I have to convert into word. While I am able to obtain reasonably accurate results, the text appears up in a badly jumbled fashion in some portions of the document. For instance, the definitions clause of a lot of contract appears in the result in such a way that all the terms appear together and all the definitions appear together, so it becomes difficult to figure out which definition relates to which term. Further, some paras are often incomplete. Clause numbers are often missing. This high rate of inaccuracy makes one doubt even the correctness of the portion that does appear properly.
Will migrating to the latest version of Fine Reader help with this, or is this attributable to inherent weaknesses of the OCR process? Further, would switching over to another OCR engine produce better results? If so, which OCR engine should I use, and where might I be able to get it? I'd be happy to send a couple of sample documents to those of you using OCR engines apart from Fine Reader which you think would work better. Best, Rahul The list has now migrated to www.accessindia.inclusivehabitat.in You should now post to the id: a...@accessindia.inclusivehabitat.in Search for old postings at: http://www.mail-archive.com/accessindia@accessindia.org.in/ To unsubscribe send a message to accessindia-requ...@accessindia.org.in with the subject unsubscribe. To change your subscription to digest mode or make any other changes, please visit the list home page at http://accessindia.org.in/mailman/listinfo/accessindia_accessindia.org.in Disclaimer: 1. Contents of the mails, factual, or otherwise, reflect the thinking of the person sending the mail and AI in no way relates itself to its veracity; 2. AI cannot be held liable for any commission/omission based on the mails sent through this mailing list..
