Advertisement
If you have a new account but are having problems posting or verifying your account, please email us on hello@boards.ie for help. Thanks :)
Hello all! Please ensure that you are posting a new thread or question in the appropriate forum. The Feedback forum is overwhelmed with questions that are having to be moved elsewhere. If you need help to verify your account contact hello@boards.ie
Hi there,
There is an issue with role permissions that is being worked on at the moment.
If you are having trouble with access or permissions on regional forums please post here to get access: https://www.boards.ie/discussion/2058365403/you-do-not-have-permission-for-that#latest

OCR Challange!!

  • 25-05-2006 6:02pm
    #1
    EvilGeorge
    Closed Accounts Posts: 875 ✭✭✭


    I have some documents dating back from the late 1800's, A3, which I am using a BookEye scanner to scan in.
    Then using Acrobat 7.0 Pro I am trying to scan them using its OCR option but with no success - seems to work on any modern document fine (used A4 sheets).
    I'm not 100% sure how OCR works - surely it can recognise beyond the scope of normal everyday fonts!

    I've was going to attach a sample scanned in at 150 dpi (I have tried up to 600 but gives me the same result and is too big to attach here, might try just a paragraph if no one has any luck with this), but its just over 500k, exceeding this sites limit - so if someone needs to look at it PM me and I'll mail it to you. I would scan in part of it but the scanner is at uni and I can't seem to select part of it without compromising the dpi settings (why I dont know).

    Any help is appreciated - cheers guys.


Comments

  • #2
    bpmurray
    Registered Users, Registered Users 2 Posts: 1,275 ✭✭✭bpmurray


    The problem is that most OCR readers are really only happy with monospaced fonts. You need something that's specifically designed for OCR, rather than a graphics program. Acrobat is OK, but it certainly isn't famous for its OCR abilities. Try one of the more advanced programs - you'll want one that can "learn" new fonts - Google for FineReader which I remember is pretty good at this kind of thing.


  • #3
    Capt'n Midnight
    Moderators, Recreation & Hobbies Moderators, Science, Health & Environment Moderators, Technology & Internet Moderators Posts: 93,563 Mod ✭✭✭✭Capt'n Midnight


    If you have office 2003 then there is a OCR package built in

    simple OCR isn't great but it's free.

    I can't remember the link but there is a university in the US that you can submit multipage tiff's to and their engine scans it


    What you really want is an OCR package that can learn the font you are using.

    another option would be to photocopy it first to try and improve the contrast ??


  • #4
    Alun
    Registered Users, Registered Users 2 Posts: 21,499 ✭✭✭✭Alun


    I've got Abby Fine Reader Pro ... you can email it to me if you like and I'll give it a whizz, no guarantees though. PM me for my email address if you want.


  • #5
    JDxtra
    Registered Users, Registered Users 2 Posts: 5,965 ✭✭✭JDxtra


    If you send me a sample TIFF, I can run it through the OCR process on our document management system. It's typically very good, but again - results may vary depending on quality of image and font used.


Advertisement