The Analyze Image API extracts various visual features from given image content. The visual features might be categories, tags, description, faces, image type, color, and more. When you call this API, you have the option to specify what feature you are interested in getting out of the picture. For example, consider the following photo:

If we want to tag the picture with the various things present in the picture, we can make use of the Analyze Image API. I am going to send a post request to the following URL:

https://northeurope.api.cognitive.microsoft.com/vision/v1.0/analyze?visualFeatures=Tags&language=en 

The content posted is a blob URL: 

{"url":"https://shipanywherestorage1.blob.core.windows.net/visionapisimages/logistics-company.jpg"}

The following are the headers passed to the API call:

The result from the API is as follows. This clearly lists all the items present in the photo:

{ "tags": [{ "name": "sky", "confidence": 0.9999314546585083 }, { "name": "outdoor", "confidence": 0.99404704570770264 }, { "name": "container", "confidence": 0.99404704570770264 }, { "name": "truck", "confidence": 0.14557225261547824 }, { "name": "construction", "confidence": 0.090924330727579022 }, { "name": "crane", "confidence": 0.085285348497175867 }], "requestId": "7a0c9a6f-93d4-447c-9f92-238532084267", "metadata": { "width": 800, "height": 600, "format": "Jpeg" } }