Microsoft

Computer Vision

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.

  • Hot ideas
  • Top ideas
  • New ideas
  • My feedback
  1. Choose to detect printed text or handwritten text

    It would be great if we can specify a parameter for OCR to just read printed or handwritten text. In the case of scanned documents it would improve the accuracy and reduce the API's workload.
    It would also make it easier to visualize the detection and read/check the accuracy of large batches of tests

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

    We’ll send you updates on this idea

    Resolved  ·  2 comments  ·  Text Recognition  ·  Flag idea as inappropriate…  ·  Admin →
  2. Add ability detect checkboxes or radio buttons to OCR and Handwritten text

    I've successfully been able to use vision to extract handwritten text out of fixed forms by knowing the coordinates of each form field. However many of my forms have checkboxes and/or radio buttons that the users will be filling in with pen. It doesn't seem that vision has a way to detect this type of content.

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

    We’ll send you updates on this idea

    3 comments  ·  Text Recognition  ·  Flag idea as inappropriate…  ·  Admin →
  3. Compare two images and return confidence and heatmap of difference areas

    You have two images like tax forms. Compare the two images. Return a confidence they are the same. Return a set of cords for the image where the primary differences occur. PDF as well as jpg and bmp support would be nice.

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

    We’ll send you updates on this idea

    Under Review  ·  2 comments  ·  Image Analysis  ·  Flag idea as inappropriate…  ·  Admin →
  4. Support for Offline OCR like Firebase ML Kit

    Firebase started offering offline on-device image recognition.

    https://firebase.google.com/products/ml-kit/

    Are there any plans to allow use to do something like OCR offline like Google does?

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

    We’ll send you updates on this idea

    2 comments  ·  On-Premises Solution  ·  Flag idea as inappropriate…  ·  Admin →
  5. [API] Is it possible for Computer Vision API - v2.0 /OCR to return also a font/font size along text and bounding rectangle?

    In the OCR API from Computer Vision API - v2.0, for every word I get the text and the bounding rectangle. Would it be posible to also get the font type and optionally font size/other parameters?
    Usage scenario: overlay new text over the old one, for example live translate.

    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  ·  2 comments  ·  Text Recognition  ·  Flag idea as inappropriate…  ·  Admin →
  6. Allow Tagging of Multiple Images After Upload

    After uploading, I would like to select multiple images and add/change their tags.

    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  ·  0 comments  ·  Web UI  ·  Flag idea as inappropriate…  ·  Admin →
  7. Categories, tags, captions are inconsistent

    My application is trying to determine images with people in them. I thought I would just be able to look for a certain tag or category but these do not seem to be consistent, even within the one result.

    For example, I have a result with the caption "a close up of a person". It has a category of "people", score: 0.75 and category of "outdoor", score: 0.003. So far so good. However, it only has 1 tag of "outdoor", confidence: 0.99. There is no person/people tag (at the high level - there are description tags but without…

    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  ·  1 comment  ·  Image Analysis  ·  Flag idea as inappropriate…  ·  Admin →
  8. add tools to support adjusting image quality

    My applications allows end-users to upload images that are used on the site. Users do not understand how to upload images with the correct aspect ratio, size, pixel ratio, etc. I need tools to allow me to process these images and correct these issues. I am currently using Cloudinary but would consider this Azure service if you can add these features.

    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  ·  Web UI  ·  Flag idea as inappropriate…  ·  Admin →
  9. 1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Resolved  ·  2 comments  ·  Image Analysis  ·  Flag idea as inappropriate…  ·  Admin →
  10. 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  ·  2 comments  ·  Custom/Sample Images  ·  Flag idea as inappropriate…  ·  Admin →
  11. Posts a locally stored JPEG image to Microsoft Computer Vision in java

    How to send a local image instead of URL to Microsoft Computer Vision API using JAVA

    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  ·  1 comment  ·  Samples & SDK Request  ·  Flag idea as inappropriate…  ·  Admin →
  12. Symbols or individual characters not recognized.

    MS Handwriting recognition is best-in-class in reading poor handwriting, but seems algorithm chooses not to recognize individual symbols or characters by themselves. All text is not written in full words.

    The following examples never process the same symbol correctly on successive lines. Symbols, or even "0" or "o" are ignored when left by themselves.

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

    We’ll send you updates on this idea

    3 comments  ·  Custom/Sample Images  ·  Flag idea as inappropriate…  ·  Admin →
  13. Provide a way to migrate an existing custom vision application (at customvision.ai/projects) into the Azure portal

    I have trained a project at customvision.ai/projects. How can I migrate / import this to my production Azure subscription?

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

    We’ll send you updates on this idea

    0 comments  ·  Documentation  ·  Flag idea as inappropriate…  ·  Admin →
  14. Include DBpedia id in Celebrity and Landmark Models

    To disambiguate similar names, include a DBpedia graph id in the response. This will help more with categorizing results and using the data in more meaningful ways.

    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 →
  15. Add a unique id to recognized celebrities

    To avoid homonymy problems, it would be very useful to add a unique identifier to recognized celebrities in the api response

    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  ·  Face Detection  ·  Flag idea as inappropriate…  ·  Admin →
  16. 5 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 →
  17. Add support for tires/wheels/rims

    I went online and got a bunch of random pictures of cars and piles of tires, etc.

    Each time I did a search, I get 0 tags relating to tires, wheels, rims, etc.

    Google Cloud Vision does detect these items though, with the following tags:
    tire
    alloy wheel
    automotive tire
    rim

    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  ·  Image Analysis  ·  Flag idea as inappropriate…  ·  Admin →
  18. How could I use http post enquery of C languege to get the Computer Vision API ?

    postRequest =(String)("POST ") +"/vision/v1.0/analyze?https://upload.wikimedia.org/wikipedia/commons/1/12/BroadwayandTimesSquareby_night.jpg HTTP/1.1\n"
    + "visualFeatures: Categories,Description,Color"
    + "language: en\n"
    + "Content-Type: application/json"
    + "Ocp-Apim-Subscription-Key: {mysub key}\n"
    + "Host: westus.api.cognitive.microsoft.com\n"
    + "Content-Length: 152\r\n\r\n";

    As shown above, I'll get an error number of 401,which means Access denied due to missing subscription key , how do I organize the content of my post request ?

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

    We’ll send you updates on this idea

    Resolved  ·  1 comment  ·  Samples & SDK Request  ·  Flag idea as inappropriate…  ·  Admin →
  19. Pattern definition

    We have some standard forms that are in handwritten format but the pattern of the text is always the same (I think this can apply to a large number of scenarios). Allowing the handwritten recognizer to be configured with a expected pattern via a simple regex could improve a lot of scenarios.

    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  ·  Text Recognition  ·  Flag idea as inappropriate…  ·  Admin →
  20. Offer relative position in 3D-space between two or more images

    If I take two photos of a subject, I would love to be able to know where the second photo was taken in real space relative to the first. In the example of handheld smartphone photography, if the first image is a baseline then I would love to know the xyz offset of the second image. Even if I believe that I'm holding a smartphone in the same position without moving it, it's likely moving at least an inch in multiple dimensions just due to hand shake. However, I might also take a side profile and it would be just…

    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 →
  • Don't see your idea?

Feedback and Knowledge Base