Microsoft

Computer Vision API

Welcome to the Computer Vision API Forum

Categories

API – Any ideas or feedback pertaining to features or enhancements to Computer Vision API.

Documentation – Any ideas or suggestions for the API Reference or Documentation.

Language Support – Submit a request to have a particular language supported.

Samples & SDK Request – Let us know if you would like to see a Code sample or SDK provided.

Custom/Sample Images – Have an image you’ve tested and not getting the results you are seeking? Upload the image and describe the information or tags you would like to be included.

How can we improve Computer Vision API?

(thinking…)

Enter your idea and we'll search to see if someone has already suggested it.

If a similar idea already exists, you can support and comment on it.

If it doesn't exist, you can post your idea so others can support it.

Enter your idea and we'll search to see if someone has already suggested it.

  • Hot ideas
  • Top ideas
  • New ideas
  • My feedback
  1. Add support to Berber languages

    The Berber language is a very old language.

    There are many benefits of supporting this languages.

    For example, there are a lot of very old books that one may want to digitize and index in order to allow millions of Berber-speakers to access to those resources online for example.

    There is a lot of effort to do that, but the first step is the have a tool that can perform Optical Character Recognition.

    1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  0 comments  ·  Language Support  ·  Flag idea as inappropriate…  ·  Admin →
  2. Object recognition for retail

    I would like to be able to match objects in shelf. This functionality has great value for retail, on stock availability, face count, etc

    6 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  1 comment  ·  Custom/Sample Images  ·  Flag idea as inappropriate…  ·  Admin →
  3. Support PDF input in OCR function

    As stated in the title, I'd like to see the OCR function support PDF files. The only supported formats right now are images like JPG, PNG, etc.

    43 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  6 comments  ·  Text Recognition  ·  Flag idea as inappropriate…  ·  Admin →
  4. Need more metadata about image

    Need more metadata about images so we can find duplicate or similar images using that metadata.

    it will help to take image processing application to new heights

    2 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Image Analysis  ·  Flag idea as inappropriate…  ·  Admin →
  5. Handwriting almost never recognized

    I tried it with several handwritten pieces, none of them worked.

    1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    1 comment  ·  Custom/Sample Images  ·  Flag idea as inappropriate…  ·  Admin →
    Completed  ·  Raymond responded

    We have just implemented this capability into Computer Vision. Please continue to share your experience and feedback with us.

    Check out:
    • The new handwriting OCR demo: https://www.microsoft.com/cognitive-services/en-us/computer-vision-api (scroll down to handwriting)
    • Documentation: https://docs.microsoft.com/en-us/azure/cognitive-services/computer-vision/home#RecognizeText
    • SDKs: Python, Windows, Android
    API reference:
    o https://westus.dev.cognitive.microsoft.com/docs/services/56f91f2d778daf23d8ec6739/operations/587f2c6a154055056008f200
    o https://westus.dev.cognitive.microsoft.com/docs/services/56f91f2d778daf23d8ec6739/operations/587f2cf1154055056008f201

  6. Recognize columns of data/tabular data

    As shown in my attached image, there are two columns, but it recognizes only one of them. Strangely, the heading of column 2 is paired with data from column 1.

    4 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  0 comments  ·  Custom/Sample Images  ·  Flag idea as inappropriate…  ·  Admin →
  7. Increase width/height limits on OCR operation to handle Letter/A4

    The Image dimension limitation is a problem.

    A4 is 210 x 297 mm. At 300 dpi that’s 2480 x 3508 Pixels and 8.7 megapixels. In grayscale as a JPEG of text the page is around 1-1.5MB.

    Letter is Image 8.5 x 11 in. At 300 dpi that’s 2550 x 3300 Pixels and 8.42 megapixels. As a grayscale JPEG the size is slightly smaller than A4 (obviously).

    The image dimension limit is a bit…silly? Unless there is some overarching technical reason you should increase the maximum dimensions to 3510 x 3510 – so scanned 300 DPI grayscale A4 pages can be…

    4 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  0 comments  ·  Service Limits  ·  Flag idea as inappropriate…  ·  Admin →
  8. 3 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  0 comments  ·  Thumbnail Generation  ·  Flag idea as inappropriate…  ·  Admin →
  9. 2 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  0 comments  ·  Text Recognition  ·  Flag idea as inappropriate…  ·  Admin →
  10. Recognize if object on picture is displayed completely or partially

    Would be great if I could see if object is completely displayed on picture or partially.
    Say, I upload a picture of car.
    I get correct tags, correct description (car parked on a parking lot, car parked on street, car parked outside, etc) but I want to know if picture shows full, complete car or just a part of it (like say, driver's door or rear side of car).

    My explanation is specific to car but I think it will be useful for many other objects like building, person, etc.

    1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  0 comments  ·  Image Analysis  ·  Flag idea as inappropriate…  ·  Admin →
  11. Provide a way to access uploaded images.

    I want to see the images being uploaded by my users for OCR processing. Maybe add an option to store them in blob storage.

    3 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  0 comments  ·  Image Analysis  ·  Flag idea as inappropriate…  ·  Admin →
  12. Add Wolof Language support in OCR API

    I need your OCR API to support the Wolof language (https://en.wikipedia.org/wiki/Wolof_language) which alphabet is pretty close to French except for a few characters. Thus, I think it should be easy to integrate it the OCR API

    1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  0 comments  ·  Language Support  ·  Flag idea as inappropriate…  ·  Admin →
  13. "Adult" image detection needs more training

    Specifically, many close-ups of male privates are not identified as either Adult or Racy. A bit of a shocker..

    Can't post examples here for obvious reasons..lol

    3 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  0 comments  ·  Custom/Sample Images  ·  Flag idea as inappropriate…  ·  Admin →
  14. Specify more precisely what I am looking for in an image.

    I want to detect any evidence of a person. Neither gender, nor face recognition is important. I get some of this in description tags, but often get false positives when the image contains no persons. For example, in the attached image "man" shows up as a description tag. It seems like if I specified "person" in the request, the algorithm might give fewer false positives.

    1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  0 comments  ·  Image Analysis  ·  Flag idea as inappropriate…  ·  Admin →
  15. Return rectangle for smart cropped thumbnail

    Since the quality of the returned thumbnails is far from anything useful for most use cases, it would be amazing to get just the rectangle the API would have used. This would be tremendously useful to roll our own resizing/cropping clients, with our preferred quality settings and file formats.

    9 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  4 comments  ·  Thumbnail Generation  ·  Flag idea as inappropriate…  ·  Admin →
  16. Count Persons and Items

    It would be great to be able to count the number of persons or items in a image no matter what angle the picture was taken... from above, frontal, back, or any other angle.

    Is this possible today?

    8 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  3 comments  ·  Object Detection  ·  Flag idea as inappropriate…  ·  Admin →
  17. 11 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  API  ·  Flag idea as inappropriate…  ·  Admin →
  18. Increase rate limit for standard tier

    I have a concern using the Standard tier in a production environment.

    My users can select and upload multiple images and I'd like to make 3 calls per image (1 analyzer, 2 thumbnails), naturally preferring to make those API calls concurrently.

    Doing so, even with a single user uploading 4 images, when done concurrently, I'm over the 10/sec rate limit and this doesn't even begin to factor in multiple users trying to upload at the same time.

    With rate limits so low I'm either going to have to make a bunch of Vision API accounts and do some kind of…

    7 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  0 comments  ·  Service Limits  ·  Flag idea as inappropriate…  ·  Admin →
  19. Number not recognized

    Why isn't this number recognized?

    1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  0 comments  ·  Custom/Sample Images  ·  Flag idea as inappropriate…  ·  Admin →
  20. Is it possible to recognize bar code inside an image ?

    Recognize text and bar codes as well !!!!

    9 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  0 comments  ·  Text Recognition  ·  Flag idea as inappropriate…  ·  Admin →
  • Don't see your idea?

Feedback and Knowledge Base