Amazon Rekognition
Developer Guide

Managing Face Collections

A collection is a container for persisting faces detected by the IndexFaces API. You might choose to create one container to store all faces or create multiple containers to store faces in groups as you choose. Consider the following examples:

  • You might create a collection to store scanned badge images using the IndexFaces operation, which extracts faces and stores them as searchable image vectors. When an employee enters the building, an image of their face is captured and sent to the SearchFacesByImage operation. If the face match produces a sufficiently high similarity score, the employee is immediately verified. As a developer of identity verification system, you might use a 99% similarity score.


  • You might create multiple collections, one per application user so that their uploaded faces are grouped independently. In this scenario, when a user performs a search, the search is scoped to the user's face collection (the search faces operations require a collection ID as input).

The face collection is the primary Amazon Rekognition resource, each face collection you create has a unique Amazon Resource Name (ARN). You create each face collection in a specific AWS Region in your account.

Amazon Rekognition provides the following operations for you to manage collections:

For information about storing faces, see Storing Faces in a Face Collection: The IndexFaces Operation. For information about searching faces, see Searching Faces in a Face Collection.