This API provides tags for images based on various recognizable objects, living beings, actions, and scenery. After uploading an image or specifying an image's URL, the algorithm of the Computer Vision API comes up with tags that it identified in the image. This might include the main subject, the setting (indoor or outdoor), furniture, tools, plants, animals, accessories, and gadgets.
Let's take a look at an example image:
We send this to the API and get the output in JSON format. This will show us the tags and the confidence that is associated with each tag:
|
Tags |
[ { "name": "bench", "confidence": 0.999963641 }, { "name": "outdoor", "confidence": 0.9997799 }, { "name": "grass", "confidence": 0.99955374 }, { "name": "tree", "... |
