Amazon Rekognition
Developer Guide

Detecting Objects and Scenes

This section provides information for detecting labels in images and videos with Amazon Rekognition Image and Amazon Rekognition Video.

A label or a tag is an object, scene, or concept found in an image or video based on its contents. For example, a photo of people on a tropical beach may contain labels such as Person, Water, Sand, Palm Tree, and Swimwear (objects), Beach (scene), and Outdoors (concept). Amazon Rekognition Video can also detect activities such as a person skiing or riding a bike. Amazon Rekognition Image does not detect activities in images.

For example, in the following image, Amazon Rekognition Image is able to detect the presence of a person, a skateboard, parked cars and other information. Amazon Rekognition Video and Amazon Rekognition Image also provide a percentage score for how much confidence Amazon Rekognition has in the accuracy of each detected label.