US 12,131,583 B2
Identifying objects within images from different sources
Hendrik Dahlkamp, Redwood City, CA (US); Vinay Sharma, Palo Alto, CA (US); Nitin Gupta, Cupertino, CA (US); Floris Chabert, San Francisco, CA (US); Andrew C. Edwards, Altadena, CA (US); Mitchell Williams, San Diego, CA (US); Jonghoon Jin, Cupertino, CA (US); Nicholas M. Fraioli, Mountain View, CA (US); Aravindhan K. Krishnan, San Jose, CA (US); and Patrick L. Coffman, San Francisco, CA (US)
Assigned to Apple Inc., Cupertino, CA (US)
Filed by Apple Inc., Cupertino, CA (US)
Filed on Sep. 21, 2022, as Appl. No. 17/949,880.
Application 17/949,880 is a continuation of application No. 17/033,423, filed on Sep. 25, 2020, granted, now 11,514,717.
Claims priority of provisional application 63/034,114, filed on Jun. 3, 2020.
Prior Publication US 2023/0014837 A1, Jan. 19, 2023
Int. Cl. G06K 9/36 (2006.01); G06F 18/22 (2023.01); G06F 21/60 (2013.01); G06T 7/11 (2017.01); G06V 10/80 (2022.01); G06V 20/52 (2022.01); G06V 40/16 (2022.01); G06V 40/50 (2022.01); H04L 9/08 (2006.01)
CPC G06V 40/173 (2022.01) [G06F 18/22 (2023.01); G06F 21/602 (2013.01); G06T 7/11 (2017.01); G06V 10/803 (2022.01); G06V 20/53 (2022.01); G06V 40/172 (2022.01); G06V 40/50 (2022.01); H04L 9/085 (2013.01); G06T 2207/20132 (2013.01); G06T 2207/30201 (2013.01)] 22 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
receiving, by a resident device and from a first device comprising a first camera, a first plurality of images taken by the first camera of the first device and stored in a photo library of the first device at a first time, the first plurality of images comprising at least first respective croppings of faces of people, and the first device comprising a mobile device associated with a location where the resident device is located;
receiving, by the resident device and from a second device comprising a second camera, a second plurality of images taken by the second camera at a second time, the second plurality of images comprising at least second respective croppings of the faces of the same people collected by the second camera, and the second camera comprising an observational camera located at the location;
generating a set of reference images comprising the first respective croppings and the second respective croppings, the set of reference images being updated to exclude a first subset of croppings below a threshold information gain and add a second subset of croppings above the threshold information gain;
executing, by the resident device, an algorithm utilizing the first respective croppings and the second respective croppings; and
generating, by the resident device, a faceprint for a person based at least in part on an output of the algorithm and the set of reference images.