How to do OCR with images

alsaqer002alsaqer002 Member Posts: 5 Contributor II
edited November 2018 in Help
Hello all,

I want to do OCR on images in order to get text.

I already installed the (image Miner extension, Text processing extension, Aylien Text Analysis extension, and Feature Selection extension)

after I use the "Open Color Image" or "Open Gray-scale Image" operators, which operator should I use to recognize and extract the text and features from image file?

Any help will be appreciated.



  • Options
    ljlj Member Posts: 10 Contributor II

    Hi. I'm new in here and maybe lucky to ask my question in the right place?

    So what' s the matter? I have a highly aggregated pdf-file containing images, tables and metadata as text. Doing it manually, I would do some save as tables with the selectes tables within the pdf-file, save as image with the selected images and save as csv on the rest. Everything with the Adobe ...

    After some cleaning i would have three seperated files: xlsx, csv and jpeg. The first two can be read in natively in RM the third, i suppose an extension working fine with it.

    How can i do it better? The mentioned elemets appear always at the same position. Horthonworks and Zapier could be integrated to the process.

    I'm looking forward to your contributions. Thank you in advance.




  • Options
    ljlj Member Posts: 10 Contributor II


    The mentioned file looks like the pictures above.


  • Options
    VaclavVaclav RapidMiner Certified Expert, Member Posts: 23 Maven


    you need OCR for this, but even if you are able to convert image to text, it will be big problem with structure of the text and extract specific values. You can use Tesseract for OCR. If you are satified with output, you can order custom development of extension for RapidMiner.


    Best wishes


  • Options
    ljlj Member Posts: 10 Contributor II


    I somehow didn't notice Your reply. Sorry. And then, as always the time.

    I'll take a look on Tesseract.

    Thank You.

    Beste Whishes


  • Options
    Thomas_OttThomas_Ott RapidMiner Certified Analyst, RapidMiner Certified Expert, Member Posts: 1,761 Unicorn

    There is a new extension on the Marketplace that RM just developed called PDF Table Extraction. Maybe that can help?





  • Options
    ljlj Member Posts: 10 Contributor II

    Hi Thomas,

    Wow, that sounds good. I'm excited.Thank You a lot.

    I will leave a feedback after having tried it out.

    Best whishes.




Sign In or Register to comment.