Novetta analyses Amazon face recognition solution
21 August 2017 14:28 GMT

Biometrics testing firm Novetta has released a whitepaper analysing the performance of Amazon Rekognition, Amazon's machine learning-based face recognition service. 

In a statement, the firm noted that cloud-based face recognition services from Amazon Web Service (AWS), Face++, and Microsoft – as well as dozens of smaller start-ups – are significantly expanding the range of applications in which face recognition can be deployed.

Amazon Rekognition has gained significant traction in government and commercial applications due to its relatively low cost, ease of implementation, and use of deep learning, adds Novetta.

The firm found that against relatively small databases, Rekognition correctly identified over 90% of subjects. Rekognition enrollment error rates were approximately 10x lower than those of other cloud-based face recognition tools.

It has found that Rekognition is calibrated to reduce false positive errors, even if this leads to relatively high false negative errors

To read the full report, click here

"Amazon Rekognition - along with other machine learning-based approaches - is emerging as a disruptive capability in US Government applications," said Michael Thieme, Novetta's vice president of Special Projects. "Understanding its real-world performance is a precondition of effective use in surveillance, large-scale identification, and social media applications."