US 12,333,863 B1
Liveness detection based on gesture validation, facial expression analysis, and concurrency validation
Zheng Zhang, Bellevue, WA (US); Xiang Xu, New Hyde Park, NY (US); Hao Chen, Seattle, WA (US); Jonathan Wu, Seattle, WA (US); and Joseph P Tighe, Seattle, WA (US)
Assigned to Amazon Technologies, Inc., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on Jun. 27, 2022, as Appl. No. 17/850,421.
Int. Cl. G06V 40/40 (2022.01); G06V 10/56 (2022.01); G06V 40/16 (2022.01); G06V 40/20 (2022.01)
CPC G06V 40/45 (2022.01) [G06V 10/56 (2022.01); G06V 40/172 (2022.01); G06V 40/176 (2022.01); G06V 40/20 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
causing a set of colors to be displayed in a sequence on a display screen of a personal computing device;
receiving a set of target images sent from the personal computing device;
detecting or tracking a face in the set of target images;
spotting a micro-facial expression in the set of target images by identifying a first target image of the set of target images containing a first micro-facial movement, identifying a second target image of the set of target images that follows the first target image in a time domain of the set of target images containing a second micro-facial movement, and identifying a third target image of the set of target images that follows the second target image in the time domain of the set of target images containing a third micro-facial movement;
determining the face is genuine based on spotting the micro-facial expression; and
authenticating, by a face recognition service in a provider network, the face.