What is Amazon’s facial recognition tool – Rekognition?

Amazon Rekognition is a machine-learning and AI service that makes it easy for organizations to add image and video analysis to applications. Used mainly by IT teams, users can provide an image or video to the Rekognition API and in return the service will identify objects, people, text, scenes and activities. It can also detect any inappropriate content.

Rekognition is designed to provide highly accurate facial analysis and recognition services too. Using the clever APIs, businesses can detect, analyze and compare faces for a wide variety of use cases, including user verification, cataloguing, people counting and public safety.

How does it do it?

The software applies thousands of labels to images and videos to detect objects and scenes. These labels span countless categories, such as People and Events, Animals and Pets, Nature and Outdoors, and Transportation and Vehicles. All help businesses analyze their data with greater accuracy. Users can detect labels through an API called DetectLabel but can request a new label to be made through AWS’ Customer Support.

The most common uses cases for Rekognition include:

  • Searchable image and video libraries – It can make images and stored videos searchable so you can discover objects and scenes that appear within them
  • Verification through Facial Recognition – It enables your applications to confirm user identities by comparing their live image with a reference image
  • Sentiment and demographic analysis – Amazon Rekognition detects emotions such as happy, sad, or surprised, and demographic information such as gender from facial images
  • Unsafe Content Detection – It can detect explicit and suggestive adult content in images and in videos. Developers can use this data to filter inappropriate content based on their business needs
  • Celebrity recognition – It can recognize celebrities within supplied images and in videos
  • Text detection – It can recognize and extract textual content from images, helping with everything from improving public safety (identify license plate numbers from street cameras) through to assisting with archival work by cataloguing videos based on relevant on-screen text

It’s currently available across the Americas and throughout Europe. However, it’s not free so businesses looking to use the service will be asked to pay a small monthly fee.

Do you have a question you’d like answered? Leave a comment below.