Amazon Facial Recognition System Will Be Able To Detect Fear

Amazon, in its latest announcement claimed that its facial recognition system is capable of detecting fear on a user's face by looking at an image. According to the company, the Rekognition software is capable of detecting face, analysis, and recognition in images. Here are the details of the software:

The company has improved the accuracy and functionality with an update. The update also improves the accuracy of gender identification, emotion detection, and age. Last week, Amazon updated the software to detect violent content such as blood, weapons, wounds, sexually explicit content, and more. This will add a filter to the platform.

"We have improved accuracy for emotion detection - for all seven emotions: 'Happy,' 'Sad,' 'Angry,' 'Surprised,' 'Disgusted,' 'Calm,' and 'Confused' - and added a new emotion: 'Fear,'" The Next Web quoted company as saying.

According to the report, researches have invested plenty of resources to learn about human emotions, with the help of facial features, movements, voice and more.

However, some experts claimed that it's impossible to deliver an accurate result. The logical reason behind this debate is that facial expression and emotions vary from person to person depending on the way they communicate on different occasion and circumstance.

There is a huge possibility that a similar type of facial movement can express more than one category of emotion. In this case, Rekognition might get confused and give some different output.
"It is not possible to confidently infer happiness from a smile, anger from a scowl, or sadness from a frown, as much of current technology tries to do when applying what are mistakenly believed to be scientific facts," reads expets report.

We will have to wait and see how accurate Amazon's facial recognition system is going to be in terms of detecting the emotions of a person.

Source