Facial Recognition with Amazon Rekognition

Here we provide steps to set up a basic Rekognition configuration.

Requirements

  • A headshot photo for each face that will be detected by the Rekognition process.
  • An AWS account. Either of the following are required:
    • The AWS access key ID and secret key.
    • An AWS Role ARN and External ID.
      • The Role will need to be given permissions for the products being used.

  • AWS Bucket used to process the files. The AWS region and the name of the bucket are required.

    The AWS Bucket used to process the files should not be used as a storage location. It's used by Rekognition to process the documents to extract the images.

  • An existing Collection on AWS for validation purposes. To set up a Collection see the AWS CLI documentation.
  • An object text field to store the UUID that is generated for each detected face.

To utilize this feature, ensure that the IAM user has write access for the following actions:

  • ListCollections

  • CreateCollection

  • CreateUser

  • IndexFaces

  • AssociateFaces

  • SearchUsers

  • DeleteFaces

You are billed directly by Amazon for the use of these features.

Rekognition Configuration

Once you have the required information, follow these steps.

  1. Navigate to Capture.
  2. Select Adv Image Processing from the side navigation.
  3. Select the New Configuration Type drop-down.

  4. Select Rekognition.

    New AIP configuration options.

  5. Enter a name for the Rekognition process in the Amazon Rekognition Name field.

  6. Select either Key and Secret or Role Assumption for authentication.

    1. Key and Secret:
      1. AWS Access Key ID — enter the key ID for your AWS account.
      2. AWS Secret Key — enter the secret key for your account.
    2. Role Assumption:
      1. AWS Role ARN — enter the previously configured ARN.
      2. Duration (seconds) — enter a duration for the authentication to be maintained before reauthenticating.
      3. External ID — enter the External ID associated with the AWS Role Arn.
  7. Select Validate.
    AWS Authentication fields.
  8. Once the AWS account is validated complete the following:
    1. AWS Region — use the drop-down to select the AWS region for the account.
    2. AWS Bucket — use the drop-down to select the bucket you created to use with Rekognition.

  9. Select Validate.
    AWS Configuration fields.

  10. Once the AWS Bucket is validated, complete the following:

    1. AWS Collection: use the drop-down to select the Collection that was configured for this process on AWS. For information on how to set up an AWS Collection.

    2. Process Type: use the drop-down to select Headshot Creation or Headshot Matching.

      1. Headshot Creation: select this option to configure the process that will generate User ID values for the detected faces.

      2. Headshot Matching: select this option to configure an ongoing process that will find matches to previously defined headshots.

    3. Object: use the drop-down to select the object where you want to save the detected headshot's associated User ID.

    4. Linking Field for User ID: use the drop-down to select the object field where you want to save the User ID from any detected headshots.

  11. Select Save.

New Rekognition configuration.

For implementation of this configuration, see Scheduled AIP.