US 11,935,321 B2
Method and apparatus with anti-spoofing
Sungun Park, Suwon-si (KR); and Kyuhong Kim, Seoul (KR)
Assigned to Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed by SAMSUNG ELECTRONICS CO., LTD., Suwon-si (KR)
Filed on Feb. 10, 2021, as Appl. No. 17/172,429.
Claims priority of application No. 10-2020-0027792 (KR), filed on Mar. 5, 2020; and application No. 10-2020-0187857 (KR), filed on Dec. 30, 2020.
Prior Publication US 2021/0279441 A1, Sep. 9, 2021
Int. Cl. G06V 40/12 (2022.01); G06F 18/214 (2023.01); G06F 18/22 (2023.01); G06F 21/32 (2013.01); G06N 3/04 (2023.01); G06N 7/01 (2023.01); G06V 10/762 (2022.01); G06V 10/764 (2022.01)
CPC G06V 40/1388 (2022.01) [G06F 18/214 (2023.01); G06F 18/22 (2023.01); G06F 21/32 (2013.01); G06N 3/04 (2013.01); G06N 7/01 (2023.01); G06V 10/763 (2022.01); G06V 10/764 (2022.01); G06V 40/1347 (2022.01); G06V 40/1365 (2022.01); G06V 40/1382 (2022.01)] 25 Claims
OG exemplary drawing
 
1. A processor-implemented anti-spoofing method comprising:
extracting an input embedding vector from input biometric information;
selecting, based on the input embedding vector, a fake embedding vector from among a plurality of fake embedding vectors of a predetermined fake model based on fake biometric information;
obtaining either one or both of a real embedding vector of a predetermined real model and an enrolled embedding vector of an enrollment model the enrollment model being generated based on biometric information of an enrolled user;
determining a confidence value of the input embedding vector based on a comparison between the input embedding vector and the selected fake embedding vector and one or more other comparisons between the input embedding vector and either one or both of the real embedding vector and the enrolled embedding vector; and
determining whether the input biometric information is forged, based on the confidence value.