Computer vision technology enables digital media professionals to generate valuable insights at a quick pace and at a lower cost by automatically identifying the contents of images and video. With a few clicks, you can integrate artificial intelligence into your media workflows with Amazon Rekognition, a deep learning-based image and video analysis service.
Amazon Rekognition can identify objects, people, text, scenes, and activities, as well as detect inappropriate content from media files you provide. These features make it possible for media and entertainment professionals to easily extract metadata from their content and then use the metadata to create innovative solutions.
For instance, customers can use the extracted metadata generated from Amazon Rekognition to create a searchable asset library, moderate image and video content, perform audience sentiment analysis, and more.
Batch & Real-Time Analysis
Analyze images and video as soon as they are uploaded to the cloud or analyze thousands of images and hours of video all at once.
Automatic Metadata Extraction
Automatically extract rich metadata from your media with celebrity recognition, object and scene detection, sentiment analysis, and more.
Easy to Get Started
Use pre-built AWS solutions that enable you to get started with all the necessary components with just one click.
Featured Customer Quotes
C-SPAN is a public service that provides gavel-to-gavel proceedings of the U.S. House of Representatives and the U.S. Senate, and to other forums where public policy is discussed, debated and decided––all without editing.
Sky News is a 24-hour international multimedia news organisation based in the UK.
"By using Amazon Rekognition, we are able to tag who is speaking / on camera at what time down to the second, if needed. Rekognition allows us to index twice as much content as we do currently - from 3500 hours a year to 7500 hours a year which would allow us to index 100% of our first run content and it was shockingly easy to set up, even with 97,000 entities from our database.”
- Alan Cloutier, Technical Manager, C-SPAN Archives
“Amazon Rekognition was critical in powering our “Who’s Who Live” feature for the Royal Wedding broadcast. Utilizing the latest machine learning technologies to create insightful metadata of identified guests as they arrive at the event, the GrayMeta Platform used Amazon Rekognition for real-time identification of Royal Wedding guests and tagged them with related biographical information. In combination with human interaction, this allowed us to easily identify celebrities that attended the royal wedding and to provide a better experience for hundreds of thousands of viewers. Implementing this type of software in media is exciting given its potential to give audiences new ways to consume and enjoy content. It was also simple to integrate it into our workflows since Rekognition is a pre-trained API service.”
- Hugh Westbrook, Senior Product Owner, Sky News
Amazon Rekognition automatically extracts metadata such as names of celebrities, scenes, and activities, which enable you to create a searchable image library. You can keep the library current by using AWS Lambda functions to automatically add new image labels to the library when new images are uploaded to Amazon S3.
Create a Searchable Image Library
Amazon Rekognition Video allows organizations managing user-generated content, such as social media or dating apps, to automatically detect explicit or suggestive content in videos and create their own rules around what is appropriate for the culture and demographics of their users.