Hebrew Optical Character Recognition

Albert H Sadler
Albert H Sadler Member Posts: 2
edited November 20 in English Forum

Does Logos have any help with the following problem?

Perhaps some one can give me advice. I am a Seminary student studying Hebrew. I currently have  the ability to scan English documents and create text in Word from the scanned image. It would help me immensly if I had the same capability to scan Hebrew documents and run an OCR program whch would create Hebrew text in a Word document.

Can you give me any advice on this problem?

Thanks for any help.

Albert Sadler

Comments

  • MJ. Smith
    MJ. Smith MVP Posts: 53,185


    Can you give me any advice on this problem?

    When I wished to use OCR on my HP in Asian languages, I called an HP sales rep who passed the problem on to a technical person. I was then directed to a driver that supported a multitude of languages. My advice: contact the manufacturer of your scanner.

    Orthodox Bishop Alfeyev: "To be a theologian means to have experience of a personal encounter with God through prayer and worship."; Orthodox proverb: "We know where the Church is, we do not know where it is not."

  • Rosie Perera
    Rosie Perera Member Posts: 26,202 ✭✭✭✭✭

    Does Logos have any help with the following problem?

    Perhaps some one can give me advice. I am a Seminary student studying Hebrew. I currently have  the ability to scan English documents and create text in Word from the scanned image. It would help me immensly if I had the same capability to scan Hebrew documents and run an OCR program whch would create Hebrew text in a Word document.

    Can you give me any advice on this problem?

    Logos doesn't do this. But if you do a Google search on hebrew ocr you'll find several hits of software products that can convert an image into Hebrew text for Word.

    Try these ones that have free trial versions and see which one works best for you:

    ABBYY FineReader 10 Professional (probably pretty good; I've been very pleased with ABBYY Screenshot Reader -- it blows away the couple of other screen OCR products I've tried)


    Ligature 6.8 Hebrew OCR Software

    Yiddish/Hebrew OCR program (totally free)

    No free trial:

    Dagesh PRO

    Readiris Pro 12 Middle East

  • Mark Barnes
    Mark Barnes Member Posts: 15,432 ✭✭✭

    ABBYY's pretty good. It's particularly excellent at scanning mixtures of Greek/Hebrew/English. But remember that these OCR programs will expect modern Hebrew, and therefore the dictionary won't work particularly well.

    So you can see what Abbyy's quality is like, I've attached two files. One is a graphic of Genesis 1-2. The second is a word document of Abbyy's default output (with no corrections made by me other than to change the font). You'll see the Hebrew output is unpointed.

    1030.gen.doc

    image

     

    This is my personal Faithlife account. On 1 March 2022, I started working for Faithlife, and have a new 'official' user account. Posts on this account shouldn't be taken as official Faithlife views!

  • Hopefully someone is still checking this thread... Has anyone using Abbyy tried user patterns to train it to recognize Nikud?

    Sarah Blake LaRose

    http://www.night-light.org

     

    Lenovo Thinkpad, 8GB RAM, 1.50GB quad core processor, Win 7, Logos 6

     

  • Ken M. Penner
    Ken M. Penner Member Posts: 23 ✭✭

    Yes, I have tried training ABBYY FineReader to recognize nikud. It can work fine (but time consuming to train) unless ABBYY decides the dots under the line of text are themselves a line of text.

  • Philipp Meier
    Philipp Meier Member Posts: 1

    Hey, you could check the following service in future: OcrGeek.com - Online OCR . It works also very well for Hebrew and gives reliable results I am also working as a teacher and quite save some work buy that :-) Hope, that helps... The only important thing is that you do not forget to select "Hebrew" as language right at the beginning, otherwise you would get non-sense results...

  • zerkalo.st
    zerkalo.st Member Posts: 1

    Ken, could you, please, upload the file with FineReader training. AFAIK it is possibe to save the training results to a file.