Custom Face detection and celebrity recognition

Prev Next

Applications this article relates to:

Clip Link_001 Logger_001

Curator version supported from this article: 3.7.2 (Azure) 3.3 (AWS)

Curator supports AWS Rekognition Services and Azure AI Video Indexer Services to scan and analyse your media assets for faces and automatically tag the media asset's metadata with the person (personality) that is contained in the media asset (images and videos). This article will explain how to task an asset(s) to be scanned for automated metadata tagging.

In order for Curator to recognise and detect faces in media assets ingested, a System Administrator must have installed AWS rekognition or Azure AI Video Indexer. Learn more here: (Azure) (AWS). In addition to this, an admin must have created an image library of a personality (person) and configured the images to be scannable by the cloud service for automated metadata tagging (Building an image library for face detection and celebrity recognition)

How to scan assets and automatically tag with metadata

  1. Right click an asset(s) and select relevant plugin from the menu.
  2. Select ‘Scan file for custom faces’

image.png

  1. You will receive a notification to advise you the process has been requested.
  • The asset will take no longer than 1 hour
  • Once complete the metadata name of your asset will be populated with a list of metadata in ‘FaceSearchResults’ (AWS) or 'Faces' (Azure) for the asset.
  • If the metadata is not populated after 1 hour, please consult your system administrator who can advise the progress of the scan and/if the process failed/if still in progress.