Update: Microsoft will be moving away from UserVoice sites on a product-by-product basis throughout the 2021 calendar year. We will leverage 1st party solutions for customer feedback. Learn more here.

Azure Cognitive Services

Customer Feedback & Ideas for Azure Cognitive Services

Share your ideas for making Cognitive Services and the accompanying APIs work better for the applications you develop.


Catch up on the latest News and Updates


Share your Ideas and Feedback

To share your ideas on how we can make Cognitive Services better, click one of the categories underneath "Give Feedback" located in the sidebar menu to access the forum.


Documentation

API documentation available here. Within, you'll find:

§  Getting started samples
§  API References
§  Testing Consoles

Using one or more of the APIs as a "Free" preview?  Be sure to read our Terms of Service.

Contact Support

UserVoice is intended for product feedback. If you need product support, please contact either: Azure support (https://azure.microsoft.com/en-us/support/plans/) or ask a question on stack overflow (https://stackoverflow.com/questions/tagged/microsoft-cognitive)


Become a Cloud Design Insider!

Join Cloud Design Insiders, and help shape the future of Cognitive Services! As an insider, you’ll speak with program managers, designers & researchers, see new designs and ideas, provide feedback through surveys, and try out prototypes. Take the short survey to join the Cloud Design Insiders now, and we’ll see you in the community.


  1. We would like Form Recognizer's Supported locales of Pre-built Receipt v2.1 to add European languages.

    We would like Form Recognizer's Supported locales of Pre-built Receipt v2.1 to add European languages. Especially, French, German, Dutch, Spanish and Italian.

    11 votes

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Vision  ·  Flag idea as inappropriate…  ·  Admin →
  2. We would like Form Recognizer's Supported locales of Pre-built "Invoices" v2.1 to add European languages.

    We would like Form Recognizer's Supported locales of Pre-built "Invoices" v2.1 to add European languages. Especially, French, German, Dutch, Spanish and Italian.

    8 votes

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Vision  ·  Flag idea as inappropriate…  ·  Admin →
  3. After tagging an image the UI should return to the same page you left from, rather than resetting to Page 1.

    e.g. if you tag an image on page 630 of your selected Training Images as soon as you close the tagging dialog box the page view resets to Page 1. To get back to where you were tagging now requires hundreds of clicks to get back to the same page you were tagging, to continue.

    After the tagging dialog box the UI should return to the training images page you left.

    7 votes

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    We’ll send you updates on this idea

    2 comments  ·  Vision  ·  Flag idea as inappropriate…  ·  Admin →
  4. "Visualization of the current progress of the training" and "Function to stop training" in Custom Vision

    If the following features are available, training can be executed with Cutom Vision without any worries.


    • Visualization of the current progress of the training

    • Function to stop training

    6 votes

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Vision  ·  Flag idea as inappropriate…  ·  Admin →
  5. Add «cheque» to prebuilt models

    It would be really useful to have a prebuilt model for cheques, which are much more bound to a standard than current prebuilt models (invoices, business cards and receipts).

    6 votes

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Vision  ·  Flag idea as inappropriate…  ·  Admin →
  6. Magnetic Ink Character Recognition (MICR) for cheques

    Right now, Azure Form Recognizer mistakenly interpret MICR special encoding characters as regular characters, as you can see in the attached screenshot. It would be very userful that it ignore/handle those special characters.

    6 votes

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Vision  ·  Flag idea as inappropriate…  ·  Admin →
  7. Export Training dataset with labels and bounding boxes in customvision.ai

    Hi,

    Would be great to add an option, in addition to export models, to save a backup of the training set: data (images) and metadata (image id, label, bounding box)

    Thanks !

    4 votes

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    We’ll send you updates on this idea

    1 comment  ·  Vision  ·  Flag idea as inappropriate…  ·  Admin →
  8. Add Go to End '>>', and Go to the Beginning '<<' action for Training Images displayed in Custom Vision.

    When there are many thousands of images tagged in the Training Images view of a Project there is no quick way to get the the end of the data set, or back to the beginning. It can take a great many clicks, 60 images at a time.

    A Go to End '>>', and Go to the Beginning '<<' action on this interface would help.

    4 votes

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Vision  ·  Flag idea as inappropriate…  ·  Admin →
  9. Add support for rotating images in CustomVision.ai portal

    Allow users of the portal to rotate prediction images.

    3 votes

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Vision  ·  Flag idea as inappropriate…  ·  Admin →
  10. Form Recognizer – Tables - pass in expected column headings to improve row/column indexing

    In order to help the parsing of table data it would be good if I could have an option to pass the expected table column headings text, so that the row/column indexing can be improved

    2 votes

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Vision  ·  Flag idea as inappropriate…  ·  Admin →
  11. Form Recognizer - Return tables that span multple pages as one table

    It would be good to have an option where tables that span multiple pages, return as a single table item. This is especially useful where the continuation page does not contain the table headings.

    2 votes

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Vision  ·  Flag idea as inappropriate…  ·  Admin →
  12. Create model that recognises a frame or video clip using a model trained with videos

    Azure computer vision provides an impressive and helpful image recognition service at the following web site;-
    https://portal.azure.com/#create/Microsoft.CognitiveServicesCustomVision
    It would be very valuable to users if Azure was to provide a service that can detect and classify an uploaded image by comparing that with uploaded video clips. Basically have a service that trains a model using video clips, not individual images, and then predicts when presented with another image or video clip, using the same simple and helpful interface that already exists.

    2 votes

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Vision  ·  Flag idea as inappropriate…  ·  Admin →
  13. Embed predictions to Power App

    Ability to import large volumes of data via an image library and then represent the prediction, boundary box and the categories it hit on to a model driven app.

    I.e.
    Are there lakes: no result
    Are there trees: 75% (image available with boundary box)
    Are there cargo ships: no result
    Are there Cars 80% (image available with boundary box)

    2 votes

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Vision  ·  Flag idea as inappropriate…  ·  Admin →
  14. Extract multiple forms in multipage pdf's.

    I have a multi page pdf, a it has two forms.The form recognizer is able to only extract data from one form while other is skipped.

    1 vote

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Vision  ·  Flag idea as inappropriate…  ·  Admin →
  15. Batch Prediction

    I think it is a real set back that Azure Custom Vision does not support batch prediction. There are cases like classifying between surgical instruments where instrument body is the same but the tips are different. Tips are very fine and cannot be seen clearly unless the photo is taken closely. The only way to classify between such images is to take one photograph of the whole instrument and the other one of the tip. Azure Custom Vision should use these two photos instead of one to make a more accurate prediction. Batch prediction is necessary to solve real world…

    1 vote

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Vision  ·  Flag idea as inappropriate…  ·  Admin →
  16. Documentation is missing the resource selection part

    When I first time login to Custom Vision and create a project, it's mandatory to choose a resource. On you documentation you don't have any instructions for the resource selection step. How can I know if I need to choose cognitive services, training or prediction? I was trying to select the training but get an error: "One of your Azure accounts seems to have issues

    Contact your Azure administrator and make sure you have access"

    How can I fix this?

    I just want to test how to train a model to be used on my Jetson Nano

    Screenshot attached.

    1 vote

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Vision  ·  Flag idea as inappropriate…  ·  Admin →
  17. Export Training Dataset with Labels and Bounding Boxes

    I don't use Custom Vision past prototyping specifically for this reason.

    "Hi,

    Would be great to add an option, in addition to export models, to save a backup of the training set: data (images) and metadata (image id, label, bounding box)

    Thanks !"

    1 vote

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Vision  ·  Flag idea as inappropriate…  ·  Admin →
  18. keep scroll position after editing bounding boxes

    I like that I can edit the bounding boxes on my images via the web page at https://www.customvision.ai/projects/4c5a58d2-c79c-48d2-8fd9-27702c7662a6#/manage, but after doing so it loses the scroll position. This is a big hassle when editing more than 9 images. Would be cool if the page did not refresh, but instead it keeps the scroll position.

    1 vote

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Vision  ·  Flag idea as inappropriate…  ·  Admin →
  19. Allow System Managed Identity to access private Blob Storage

    I would like to be able to read files in private Blob storage with the managed identity of my Computer Vision Cognitive Service. The account is granted Reader and Storage Blob Data Reader, but still has no Access to the Blob unless I make it fully public.

    1 vote

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Vision  ·  Flag idea as inappropriate…  ·  Admin →
  20. Read API recognising some text twice

    Fix a bug within the Azure Computer Vision Read API 3.0 that leads to some text being recognised twice.

    An example is attached.

    1 vote

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Vision  ·  Flag idea as inappropriate…  ·  Admin →
← Previous 1
  • Don't see your idea?

Feedback and Knowledge Base