Eventually, facial recognition technology will evolve to the point where it makes few mistakes. That's where the real concerns are.

High accuracy scores come from conditions that don't reflect real-world usage Facial recognition technology has been deployed ...

With these safeguards, facial recognition can be part of building smarter, safer and more equitable communities, without ...

The accuracy of facial recognition systems has improved dramatically in recent years, though limitations remain. This post explores how accuracy improvements are changing the risks associated with ...

Everything we know about the face recognition systems the FBI and police use suggests the software has a built-in racial bias. That isn’t on purpose—it’s an artifact of how the systems are ...

Clearview performed less well in another version of the test, which simulates using facial recognition for providing access to buildings, such as verifying that someone is an employee.

In practice, they found that software that generated an average face for recognition worked far better than software that matched faces based on the features of individual images.

But using a newly developed program at the university, computers were found to be 100 percent accurate when using what they call an "averaged" face image, made up of 20 photos, Jenkins and co ...

The key to moving the accuracy needle for facial recognition was to use a new method that looks at a person's attributes and poses.