Some of us wonder if/when FaceID will come to the Mac. Now Apple has filed for a patent (number US 20230252779 A1) that shows the company is at least considering this.
The patent is dubbed “personal computer device control using face detection and recognition.” It involves systems and methods for control of a personal computing device based on user face detection and recognition techniques.
In the patent filing Apple says that one problem with existing personal computing devices is that such devices often perform certain functions regardless of whether users are passively interfacing with the devices. In other words, personal computer devices are not able to determine whether a non-active or passive user is present and, subsequently, unable to perform certain operations to accommodate the passive user.
For example, a Mac may automatically activate a screen saver every five minutes regardless of whether a user is viewing the computer’s display screen. This means, according to Apple, that a passive user is often inconveniently required to actively perform an interaction with the computer at least every five minutes to prevent the initiation of the screen saver or to deactivate the screen save after it is initiated.
What’s more, another problem with personal computing devices is that such devices often can’t efficiently determine whether certain users have the authority to perform certain functions of the personal computing device, Apple says. For example, to access a restricted computer application, a user may be required to actively enter a password.
Apple says there’s a need for providing a user interface for a personal computing device that’s capable of determine when a passive user is present without the need for active user interaction with the device. Such an interface should also provide a “more efficient and reliable user access interface.”
Apple is considering future Macs that employ face detection, face recognition, object recognition, view-based recognition, computer vision, and machine learning. Face detection may be based on at least one of knowledge-based methods, feature invariant approaches, template matching methods, and appearance-based methods.
If you’d like to help support AWT (and help us reach our goal of eliminating ads), consider becoming a patron. We offer at least three patron-exclusive posts each week. You can start at only $2 per month (though $5/month gets you the exclusives).