Japan's Fair Trade Commission is Investigating Serious Allegations that Apple has Abused its Power in violation of Anti-monopoly Rules
Apple Wins Autonomous Vehicle Patent that provides an iPhone user with an Advanced 'Guidance System' to Fine Tune Destinations

Apple Wins Patent for Presence Sensing and Facial Recognition for Macs

1 cover presense sensing


The U.S. Patent and Trademark Office officially published a series of 54 newly granted patents for Apple Inc. today. In this particular report we cover an advanced facial recognition system for the iMac. The patent in-part derived from the acquisition of Sweden's Polar Rose back in 2010. Other patents from the former CEO Jan Erik Solem may relate to a street-level mapping system and automotive AI Systems powered by computer vision. Whether the latter patents were a part of the original acquisition is unknown at this time.


Apple's newly granted patent covers their invention relating to devices having computing capabilities and, more particularly, devices and systems for sensing the presence of a user in local proximity to the device.


The computing device may be configured to determine when a user arrives or enters into proximity with the computing device and/or a probability that the user is present based on sensor input. In response to a positive determination that the user is present or upon achieving a threshold probability that the user is present, the device may power up, exit a sleep mode, and/or provide some feedback to the user.


Generally, one goal of the presence sensing system may be to more intelligently use technology. For example, in some embodiments, a system awake may be initiated when it is determined that a user is approaching. The system awake may include a reduced set of routines so that the system is in an operational mode faster than with a conventional power up sequence.


Apple's patent FIG. 1 is an iMac with a camera that could sense motion; FIG. 10 illustrates frames being divided into window for single frame motion detection; and FIG. 12 is a flowchart illustrating an example method for multiple concurrent asynchronous sensors being used to determine a probability of a user being proximately located to a device.


2 motion sensing patent win for Apple figs1  10 & 12 - Patently Apple IP report aug 6  2019


Apple further notes that although cameras and light sensors will be generally used with respect to the presence sensing, it should be appreciated that other sensor types may be implemented as well, such as ultrasonic sensors, microwave RADAR, and so forth. Some of these technologies may be utilized to determine physiological parameters when a human is in proximity to the device.


For example, RADAR may be used to detect and/or locate a heartbeat in the room. Moreover, various techniques and wavelengths of light may be implemented.


For example, proximity may be determined using depth sensors. Some example depth sensor techniques may include: focusing and defocusing, active IR reflected power, active IR structured light; active IR time of flight (2D+depth), active IR time of flight (single pixel sensor), passive IR (motion detector), passive IR thermal imaging (2D), stereo vision, polarization techniques, and so forth. In some embodiments, active IR may user multiple specific IR wavelengths to detect certain unique material properties, such as reflectivity of human skin or carbon dioxide emissions in breath.


Although the patent description doesn't mention it, Apple's patent claims clarifies that the camera will be one that could capture 3D images.


Another aspect of the patent not present in the patent's description is that of facial recognition that is present in the all-important patent claims.


A part of patent claim 1 it is noted that "when the determined probability that the user is facing the computing device exceeds a first threshold, updating a state representation maintained by the computing device; capturing one or more subsequent images with a camera having a second resolution higher than the first resolution of the image sensor; using the captured one or more subsequent images to determine a facial feature detection parameter and a movement detection parameter; and using the facial feature detection parameter and the movement detection parameter to update the probability that the user is facing the computing device; determining that the updated probability that the user is facing the computing device exceeds a second threshold; and further updating the state representation.


Apple's granted patent 10,372,191 was originally filed in Q2 2011 and published today by the US Patent and Trademark Office. Patently Apple first covered this invention back in 2012 titled "Apple Advances their Multi-Level Presence Sensing System." See our detailed report here.


While a partial list of inventors from Apple are listed below, it should be noted that one of the inventors is Jan Erik Solem who owned "Polar Rose" a face recognition company that was sold to Apple in 2010. Other patents from Polar Rose and Jan Erik Solem could be found in our reports as noted below:


2011: Apple Wins Secret Patent for High-End 3D Object Recognition

2012: Future iDevice Cameras will Recognize Famous Faces & Objects


Some of the other Apple Inventors


Matt Waldon: Director, Depth Hardware

Rudolph van der Merwe: Advanced R&D Manager – Advanced Computation Group.

Myra Haggerty: VP, Sensor Software and UX Prototyping (26 years with Apple).

Alex Nelson: Algorithm Research Engineer

Karen Jenkins: Senior algorithms Engineer


10.52FX - Granted Patent BarAbout Making Comments on our Site: Patently Apple reserves the right to post, dismiss or edit any comments. Those using abusive language or negative behavior will result in being blacklisted on Disqus.


The comments to this entry are closed.