IBM Watson™ Ideas

Welcome to the IBM Watson™ Ideas Portal


We welcome and appreciate your feedback on IBM Watson™ Products to help make them even better than they are today!


If you are looking for troubleshooting help or wondering how to use our products and services, please check the IBM Watson™ documentation. Please do not use the Ideas Portal for reporting bugs - we ask that you report bugs or issues with the product by contacting IBM support.


Before you submit an idea, please perform a search first as a similar idea may have already been reported in the portal.


If a related idea is not yet listed, please create a new idea and include with it a description which includes expected behavior as well as why having this feature would improve the service and how it would address your use case.

Document Text Recognition / OCR

Would like the specific ability to be able to recognize text in documents, such as PDFs.

  • Kevin Gong
  • Sep 28 2017
  • Already exists
  • Attach files
  • Wolfgang von Drews commented
    November 13, 2017 11:09

    this is highly demanded from my clients as well. Microsoft and others have this capability already consumable on the cloud.

    Therefore enhance visual recognition with this feature.

  • Admin
    ALLIE MILLER commented
    November 13, 2017 19:20

    Wolfgang, this feature exists in IBM land, just not within Watson Visual Recognition. It is under the "DataCap" team, since it is more doc processing and outside image/video/face detection and recognition.

  • Wolfgang von Drews commented
    November 13, 2017 20:30

    Thank you Allie for your swift response.

    I know DataCap and have used it - however I needed a classic
    infrastructure for it - there is nothing to my knowledge that makes a OCR
    service being consumable on the IBM cloud (other than installing DataCap
    on a virtual machine in the IBM cloud).
    In contrast others have already comparable services:

    https://cloud.google.com/vision/

    https://azure.microsoft.com/en-us/services/cognitive-services/computer-vision/

    What about having DataCap Service running and exposing some services in
    the IBM cloud?



    Mit freundlichen Grüßen / with kind regards


    Wolfgang von Drews
    Leading Technical Sales Professional
    IBM Certified IT Architect

    Client Technical Architect

    IBM Deutschland GmbH
    Hollerithstr. 1
    D-81829 München

    für Commerzbank AG und Sparda Gruppe

    wmayle@de.ibm.com
    Mobile: +49 (0)7034-643-1336
    Notes: MAYLE@IBMDE

    IBM Financial Services

    WW IT Infrastructure CoP Co-Leader
    The Open Group Master Certified IT Architect
    Member of TEC Central Region

    IBM Deutschland GmbH - Vorsitzender des Aufsichtsrats: Martin Jetter -
    Geschäftsführung: Martina Koederitz (Vorsitzende), Norbert Janzen, Stefan
    Lutz, Nicole Reimer, Dr. Klaus Seifert, Wolfgang Wendt
    Sitz der Gesellschaft: Ehningen - Registergericht: Amtsgericht Stuttgart,
    HRB 14562 - WEEE-Reg.-Nr. DE 99369940

    Beachten Sie bitte, dass jede Form der unautorisierten Nutzung,
    Veröffentlichung, Vervielfältigung oder Weitergabe des Inhalts dieser
    E-Mail nicht gestattet ist.Diese Nachricht ist ausschliesslich fuer den
    bezeichneten Adressaten oder dessen Vertreter bestimmt. Sollten Sie nicht
    der vorgesehene Adressat dieser E-Mail oder dessen Vertreter sein, so
    bitten wir Sie, sich mit dem Absender der E-Mail in Verbindung zu setzen.
    Any form of unauthorised use, publication, reproduction, copying or
    disclosure of the content of this e-mail is not permitted. This message is
    exclusively for the person addressed or their representative. If you are
    not the intended recipient of this message and its contents, please notify
    the sender immediately.

  • PHILIPPE COMTE commented
    November 30, 2017 13:58

    Hello , I would say that it was once a beta feature of the Visual Recognition service .. It still is but has the status of Black Beta (if you don't know it exists , you won't find it !) Any plan to incorporate an OCR capability in VR ?

  • VINCENT PERRIN commented
    December 01, 2017 08:09

    yes, it is in the near roadmap. BTW, I have played with the dark beta and it works pretty well (tested on my pay sheet)...

  • SHANTENU AGARWAL commented
    December 02, 2017 00:12

    The new Text Model will not be optimized for documents, but focus on larger text you may find on boxes, street signs etc.

  • Admin
    ALLIE MILLER commented
    December 04, 2017 17:52

    @Wolfgang - I would reach out to the DataCap team to hear about their Cloud plans. Full-document reading is not in our current roadmap. As Shantenu said, we are focused on text within photos someone might take (text should generally be 5% of screen...currently optimized for full English words...)

  • Raghu Srinivasan commented
    31 Jan 01:49

    Hi Allie, Is the capability for Handwriting/Text Recognition now available within Watson, I see there is NLP/NLU capabilities, wondering if there was a more updated status on this..

    Thanks