FB pixel

Apple files new facial recognition patent

 

Apple has filed a patent with the U.S. Patent and Trademark Office, outlining a new facial recognition system that analyzes the characteristics of an image’s subject and uses this data to create a “faceprint,” to match with other photos to establish a person’s identity, Apple Insider reports. 

According to a TechCrunch article on the recent filing, this new image recognition patent appears similar to Apple’s existing facial recognition systems included in iPhoto, which allows automatic tagging and identifying of friends and family in pictures after first determining the unique characteristics of their face.

This new patent, dubbed the “Auto-recognition for noteworthy objects” appears to be intended to tag celebrities, landmarks and famous objects. TechCrunch reports that though most the patent describes these faceprints as representing actual people, it also allows for the recognition of “iconic images.” Though the exact intent behind this recently-filed patent is unknown, it does describe a system returning information including Facebook pages, Twitter profiles and iTunes Store links.

As the patent filing explains:

“In order to automatically recognise a person’s face that is detected in a digital image, facial detection/recognition software generates a set of features or a feature vector (referred to as a “faceprint”) that indicate characteristics of the person’s face. The generate faceprint is then compared to other faceprints to determine whether the generated faceprint matches (or is similar enough to) one or more of the other faceprints. If so, then the facial detection/recognition software determines that the person corresponsing to the generated faceprint is likely to be the same person that corresponds to the “matched” faceprints(s).”

This patent also includes the ability to group together multiple faceprints using metadata along with a reliability score. This can supposedly help to identify faces as they age, as well as in the case of famous people, provide a visual retrospective.

Many await advanced biometric integration in Apple devices. Earlier this year, Apple agreed to purchase AuthenTec for a cool US$356 million and since then, there has been mass speculation as to how the company would make use of this acquisition. Though this most recent patent filing isn’t it, it’s clear Apple is making moves towards deeper biometric integrations.

Article Topics

 |   |   |   |   |   |   | 

Latest Biometrics News

 

‘Interoperable but not identical’: applying ID standards across diverse communities

Exchanging knowledge and experiences with identity systems to improve future ID projects is central to the concept of ID4Africa’s mission….

 

Biometrics providers and credentials level up with new capabilities

Biometrics is a fast-evolving field about persistence, so new versions of major digital identity providers and biometric technology companies naturally…

 

Alan Goode offers insights on booming transitional IDV market on BU Podcast

Technology is transforming identity verification. According to Alan Goode of Goode Intelligence, by 2030, digital identity verification will pass traditional…

 

Share less data in more places: inching towards decentralized digital ID for travel

The travel industry is slowly shifting to a more decentralized model of digital identity. This was one of the key…

 

Clearview takes fresh legal hits over Canada class action, UK fine

Few biometrics companies have taken a bigger regulatory and legal beating than Clearview AI. It has already been a rough…

 

Mexico makes biometric identifier mandatory for all citizens

Mexico has officially introduced a digital identification system by signing a law that turned the previously optional biometric-based citizen code…

Comments

4 Replies to “Apple files new facial recognition patent”

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Biometric Market Analysis

Most Viewed This Week

Featured Company

Biometrics Insight, Opinion

Digital ID In-Depth

Biometrics White Papers

Biometrics Events