Amazon’s Facial Recognition System Can Now Detect Fear

Posted: Aug 14 2019, 5:03am CDT | by , in Technology News

 

This story may contain affiliate links.

Amazon’s facial recognition system can now detect fear

The technology is now also able to more accurately estimate a person's age.

Amazon Rekognition, Amazon’s cloud-based software that offers tools for facial recognition, among many others, has added a new feature that detects “Fear”.

The fear detection is an addition to Rekognition’s already existing suite of emotion detection for face analysis that includes “Happy,” “Sad”, “Angry”, “Surprised”, “Disgusted”, “Calm” and “Confused”.

Amazon’s face analysis technology is used to generate metadata about detected faces in the form of gender, age range, emotions, attributes such as “Smile”, face pose, face image quality and face landmarks.

Additionally, Amazon Rekognition is now more accurate than ever before in estimating people’s age range.

The announcement comes just three days after Amazon announced that Rekognition can now detect violence and visually disturbing themes such as blood, wounds, weapons, self-injury, corpses and more in images and videos.

Earlier, the company also improved Rekognition’s ability to identify explicit nudity and suggestive content through a 68% lower false positive rate and a 36% lower false negative rate on average. The technology is now also able to detect new categories of adult content, such as unsafe anime or illustrated content, adult toys, and sheer clothing.

With Amazon Rekognition, developers can easily add image and video analysis to their applications. It works by providing an image or video to the Rekognition API, and the service will automatically identify objects, people, text, scenes, and activities.

The latest updates are available to all regions where Amazon Web Services supported by Amazon Rekognition is available.

To learn more about Amazon Rekognition, the Amazon Rekognition Developer Guide book is available on Amazon.com for $59.99.

This story may contain affiliate links.

Loading...

Find rare products online! Get the free Tracker App now.


Download the free Tracker app now to get in-stock alerts on Pomsies, Oculus Go, SNES Classic and more.

Latest News

Comments

The Author

<a href="/latest_stories/all/all/81" rel="author">Mandy Jean</a>
Mandy covers the latest news in Tech and Business.

 

 

Advertisement

comments powered by Disqus