US 12,266,215 B2
Face liveness detection using background/foreground motion analysis
Fang Hua, Bedford, MA (US); and Taras Riopka, Concord, MA (US)
Assigned to AWARE, INC., Bedford, MA (US)
Appl. No. 17/777,841
Filed by AWARE, INC., Bedford, MA (US)
PCT Filed Dec. 5, 2019, PCT No. PCT/US2019/064635
§ 371(c)(1), (2) Date May 18, 2022,
PCT Pub. No. WO2021/112849, PCT Pub. Date Jun. 10, 2021.
Prior Publication US 2023/0222842 A1, Jul. 13, 2023
Int. Cl. G06V 10/82 (2022.01); G06T 7/20 (2017.01); G06V 40/16 (2022.01); G06V 40/40 (2022.01)
CPC G06V 40/171 (2022.01) [G06T 7/20 (2013.01); G06V 10/82 (2022.01); G06V 40/161 (2022.01); G06V 40/172 (2022.01); G06V 40/45 (2022.01)] 19 Claims
OG exemplary drawing
 
1. A method of determining face liveness, comprising:
receiving, at a processor of a face recognition system and from an image capture device of the face recognition system, a time-stamped frame sequence;
generating time-constrained sequential pair-frames by constraining time lapse between frames in the time-stamped frame sequence;
identifying corresponding pixels for each pair of time-constrained sequential frames in the time-stamped frame sequence;
segmenting one of each pair of time constrained sequential frames in the time-stamped frame sequence into regions of interest;
calculating a motion feature for each region of interest of each pair of time constrained sequential frames in the time-stamped frame sequence;
generating a pair-decision for each pair-frames from the time constrained sequential frames in the time-stamped frame sequence, based on a comparison of the calculated motion features for each region of interest of the pair of time constrained sequential frames;
applying a dynamic decision fusion scheme to make the final liveness determination on all pair-decisions from qualified frames in the time-stamped frame sequence, wherein the dynamic decision fusion scheme is conducted on all pair-decisions to identify changes and patterns to generate a final determination and all pair-decision results are treated together as a time series of decisions; and
matching face region with pre-enrolled face region images for a genuine check if the user is pre-enrolled.