Microsoft

Face

Welcome to the Face Forum

Categories

API – Any ideas or feedback pertaining to features or enhancements to Face 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.

                               Attention!





We have moved our Customer Feedback & Ideas for Azure Cognitive Services portal to the Azure Feedback Forum.





Please go to the link below to access our new Feedback and Ideas Page.



  1. On celebslike.me focus more on facial features like nose shape and size if lips as these are the most common differences in 'similar' faces

    The algorithm of celebslike.me doesn't accurately match the shape and size of nose and lips of the image and the similar celebs which doesn't seem to make sense as u cannot find any similarity between yourself and them.
    Regards,
    Nimesh

    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  ·  API  ·  Flag idea as inappropriate…  ·  Admin →
  2. Internal scaling of Emotion service

    The current quotas for 2 per minute for video processing can be got around by spinning up multiple API instances in Azure Portal. Could (or indeed is) this be internalised so performance is managed by a single instance of the service? I have 30000 videos to process, so creating and deleting multiple instances of the service, and managing keys in my app is less attractive to me than paying for a faster rate of processing.
    The current model costs me no more per video it just adds to coding incnvenience.

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

    We’ll send you updates on this idea

    0 comments  ·  Flag idea as inappropriate…  ·  Admin →
  3. How can I prevent you from using my photos publicly on this website https://www.celebslike.me/ Please, I want a solution sooner

    After using my pictures to entertain .. I noticed late to this sentence: Your photos, but no personal info, may be used to improve matches .. What is the solution, please?

    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  ·  API  ·  Flag idea as inappropriate…  ·  Admin →
  4. Include Detection process into Identify process

    Please consider putting the Detecting process into the Identifying process. This way, we can shorten our code and have less request to your api.

    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  ·  1 comment  ·  API  ·  Flag idea as inappropriate…  ·  Admin →
  5. How to use the EMOTION API features in our own android app?

    I have seen the EMOTION API on Github and used the sample but i am making a smart music app of my own in which i wish to use the emotion recognition. Is there any way through which i use the emotion features of cognitive services in my own way in my android application?

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

    We’ll send you updates on this idea

    0 comments  ·  Flag idea as inappropriate…  ·  Admin →
  6. Please add support for video that would work just like the emotion API.

    This is currently unusable for video at a decent framerate because of pricing, and the complexity of doing things frame by frame. Why not support video just like the Emotion API? Also, bonus points for allowing us to pipe output of the Face API into the Emotion API to cut down on processing time, if that's plausible.

    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  ·  API  ·  Flag idea as inappropriate…  ·  Admin →
  7. I would like a sleepiness detection function using Vision API

    I'm looking for the solution to detect if human (e.g., a driver) is sleeping or not, so I would like a sleepiness function using Vision API.

    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  ·  Flag idea as inappropriate…  ·  Admin →
  8. photo from infrared camera

    would be excellent to process photos from an infrared camera, this could be useful in Safety things like the Fatigue status requested above

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

    We’ll send you updates on this idea

    0 comments  ·  Flag idea as inappropriate…  ·  Admin →
  9. Fatigue status

    Dear Cognitive Services Team,
    I been trying The Emotions API and I noticed that theres no status for fatigue. I'm working on a Safety project, It could help us a lot to get this.
    could be possible to add that status?,

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

    We’ll send you updates on this idea

    0 comments  ·  Flag idea as inappropriate…  ·  Admin →
  10. Extension support API

    Emotion API does not support images in PNG extensión only JPG

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

    We’ll send you updates on this idea

    0 comments  ·  Flag idea as inappropriate…  ·  Admin →
  11. Photo Requirement API

    For issuing an ID card, we ask patrons to upload a photo that meets requirements similar to the College Board SAT photo standard available at https://collegereadiness.collegeboard.org/sat/register/policies-requirements/photo. It would be nice to have an API that validates the standard.

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

    We’ll send you updates on this idea

    Completed  ·  1 comment  ·  API  ·  Flag idea as inappropriate…  ·  Admin →
  12. Add a few more face landmarks for the top and the bottom of the face, to derive dimensions and locations of landmarks relative to the face

    Add a few more face landmarks that will detail the top and the bottom of the face. In other words, if I want to derive that someone's mouth is 1/3 of the way up from the bottom of their face or that their eyes are 1/3 of the way down, it would be great if the API exposed additional landmarks that would provide me the entire face's relative dimensions to be able to "layout" a person's facial features with relative x/Y coordinates. Or... is the rectangle precise enough for this - my testing doesn't seem to indicate that the rectangle…

    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  ·  API  ·  Flag idea as inappropriate…  ·  Admin →
  13. Identify if person is looking at the camera

    Hi, I'd like to know if it is possible to add a feature that tells is the recognized face is looking into the camera or very near to it. This would improve the stuff we do here greatly.
    thanks!

    14 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  ·  API  ·  Flag idea as inappropriate…  ·  Admin →
  14. Increase number of candidates for Identify method

    Hi,
    Currently in method Identify the paramenter maxNumOfCandidatesReturned can be set between 1 and 5.

    We would like to increase maxNumOfCandidatesReturned to 1000 and get all persons in Identify

    15 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  ·  API  ·  Flag idea as inappropriate…  ·  Admin →
  15. Date-aware grouping/recognition

    I think it might be useful to add a way to train, group or recognize faces based on dates.

    Train based on how a person looked like let's say for every year (or any date/time span).

    Run recognition on a photo based on a Date/Time (probably something from the photo metadata)

    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  ·  API  ·  Flag idea as inappropriate…  ·  Admin →
  16. Quota info through API?

    Is there a way to get quota information through the API?

    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  ·  2 comments  ·  API  ·  Flag idea as inappropriate…  ·  Admin →
  17. Get a Person Face / Get the picture from the persistedFaceId

    It should be great to get the picture that belongs to the persistedFaceId
    That allows to manage, especially for removing a picture from the person with a preview of the picture.

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

    We’ll send you updates on this idea

    1 comment  ·  API  ·  Flag idea as inappropriate…  ·  Admin →
  18. Ability to use face and Emotion API with one single file upload

    To be able to use faceAPI and EmotionAPI with one single file upload.

    I'm using the boxes param quite well at the moment but still I need to send the picture to both endpoints and that's very costly to us just because I want to extract only the face orientation + emotions

    Or the best option should be to enable face orientation of emotions.

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

    We’ll send you updates on this idea

    Completed  ·  1 comment  ·  API  ·  Flag idea as inappropriate…  ·  Admin →
  19. Make confidence level available for age and for gender

    Actually confidence level is only available when identification is performed, it would be cool to also have confidence level for age and gender.

    12 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  ·  API  ·  Flag idea as inappropriate…  ·  Admin →
  20. Hair Analysis

    Hair analysis. hair color(blonde,...), hair type(long, nohair, short hair,..)

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

    We’ll send you updates on this idea

    Completed  ·  2 comments  ·  API  ·  Flag idea as inappropriate…  ·  Admin →
  • Don't see your idea?

Feedback and Knowledge Base