Apple’s new patent shows plan to unlock iPhones with facial recognition

July 8, 2015 - 

Apple has been granted a US patent that covers a new technology that enables users to unlock future iPhones by taking a selfie, according to a report by the Cult of Mac.

The patent appears to be an entirely different patent than the one it obtained in March, which also covered a new facial recognition mechanism that enables users to unlock mobile phones by taking a selfie.

Entitled “Low threshold face recognition,” the patent describes a process of “reducing the impact of lighting conditions and biometric distortions” that can negatively impact facial recognition for a solution which “can be implemented on camera-equipped consumer portable appliances”.

Although Apple does not specify which one of its devices it intends on integrating this technology into, it is likely for the iPhone and iPad, but it could also apply to the second-generation Apple Watch 2.

Apple has previously flirted with integrating facial recognition technology in the past. In 2010, Apple acquired Swedish face-recognition firm Polar Rose, which developed software applications that could recognize faces in images, similar to Facebook’s tagging feature.

The company has secured multiple patents in face-recognition, as well as incorporating facial recognition and detection aspects into many of its products, including Photo Booth, Photos and the camera software used for iOS devices.

The company could use this latest patent to improve these features, an authentication alternative to Touch ID, or even a two-factor authentication (2FA) system requiring the user’s fingerprints and face image.

“In one aspect, the methods include processing a captured image of a face of a user seeking to access a resource by conforming a subset of the captured face image to a reference model,” according to Apple’s patent application. “The reference model corresponds to a high information portion of human faces.

“The methods further include comparing the processed captured image to at least one target profile corresponding to a user associated with the resource, and selectively recognizing the user seeking access to the resource based on a result of said comparing.”

Leave a Comment

comments

About Justin Lee

Justin Lee has been a contributor with Biometric Update since 2014. Previously, he was a staff writer for web hosting magazine and website, theWHIR. For more than a decade, Justin has written for various publications on issues relating to technology, arts and culture, and entertainment. Follow him on Twitter @BiometricJustin.