This section covers the types of analysis that Amazon Rekognition Image can perform on images.
These are performed by non-storage API operations where Amazon Rekognition Image doesn't persist any information discovered by the operation. No input image bytes are persisted by non-storage API operations. For more information, see Understanding non-storage and storage API operations.
Amazon Rekognition Image can also store facial metadata in collections for later retrieval. For more information, see Searching faces in a collection.
In this section, you use the Amazon Rekognition Image API operations to analyze images stored in an Amazon S3 bucket and image bytes loaded from the local file system. This section also covers getting image orientation information from a .jpg image.
Rekognition only uses RGB channels to perform inference. AWS recommends users remove the Alpha Channel before using a Display to visually (manually by a human) inspect the comparison.
Topics
