US 12,288,416 B2
Secure biometric metadata generation
Jonathan Mumm, Marina del Rey, CA (US); Donald Holly, Venice, CA (US); Faisal Alqadi, Santa Monica, CA (US); and Jonathan Brody, Marina Del Rey, CA (US)
Assigned to Snap Inc., Santa Monica, CA (US)
Filed by Snap Inc., Santa Monica, CA (US)
Filed on Oct. 18, 2023, as Appl. No. 18/489,651.
Application 18/489,651 is a continuation of application No. 17/662,524, filed on May 9, 2022, granted, now 11,804,073.
Application 17/662,524 is a continuation of application No. 16/394,792, filed on Apr. 25, 2019, granted, now 11,328,153.
Claims priority of provisional application 62/662,562, filed on Apr. 25, 2018.
Prior Publication US 2024/0046697 A1, Feb. 8, 2024
Int. Cl. G06V 40/16 (2022.01); G06F 21/60 (2013.01); G06N 20/00 (2019.01)
CPC G06V 40/172 (2022.01) [G06F 21/602 (2013.01); G06N 20/00 (2019.01); G06V 40/161 (2022.01); G06V 40/179 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
accessing a first image stored on a device;
determining a set of positions for a set of facial features depicted within the first image;
generating a set of biometric reference maps by inputting the set of positions for the set of facial features into a machine learning model to receive the set of biometric reference maps from the machine learning model based on the inputted set of positions, wherein the machine learning model is trained to generate biometric reference maps based on face images and positions; and
applying the set of biometric reference maps on a second image.