How to automatically identify objects in an image?

Want to try this beta feature? Ask us about enabling it on your account.

Return a JSON object representation of each object recognized in the image. The is ideal for cataloging and tagging images according to their contents.

While this feature is in beta, it is available only through the Uploadcare API. If the feature is enabled on your account, try it for yourself:

curl -H "Accept: application/vnd.uploadcare-v0.6+json"   -H "Authorization: Uploadcare.Simple publickey:secretkey"   "https://api.uploadcare.com/files/:uuid/?add_fields=rekognition_info"

In the response, you will get a JSON file with a special rekognition_info section.

{
  ...
  "rekognition_info":
  {
  "Building": 0.63291,
  "House": 0.63291,
  "Housing": 0.63291,
  "Architecture": 0.63008,
  "Outdoors": 0.55667,
  "Cottage": 0.63291,
  "Pond": 0.55667,
  "Castle": 0.63008,
  "Moat": 0.63008,
  "Fort": 0.63008
  }
  }

You’ll receive a JSON file with a main_colors section: