Posted On: Aug 23, 2018

Amazon Rekognition is a deep learning-based image and video analysis service that can identify objects, people, text, scenes, and activities, as well as detect any inappropriate content. Amazon Rekognition now includes a DescribeCollection API that allows you to discover information about your face collections, such as the number of faces stored or the face model version you are currently using, to make it easier to manage collections. Given a face collection identifier known as a CollectionId, the DescribeCollection API returns the following information:

  • The number of faces indexed into the collection. Using this, you can verify whether the expected number of faces were indexed successfully or estimate your face metadata storage bill. For example, if you indexed 10,000 photos, each with a single face in it, this API helps you quickly find out the success percentage of the indexing workflow.
  • The version of the face model used by the collection for face detection and face recognition. For more information, see Model Versioning. If you are on an older version of the face model, you can create a new collection to get the latest updates.
  • The Amazon Resource Name (ARN) of the collection. ARNs help you to specify a resource unambiguously across all of AWS, such as in IAM policies. For more information on ARNs, please see this.
  • The creation date and time of the collection.

To try out these updates, simply download the latest version of the AWS SDK. For more information on DescribeCollection, please refer to the documentation.