US 12,147,516 B2
Anti-spoofing method and apparatus
Sungun Park, Suwon-si (KR); Kyuhong Kim, Seoul (KR); and Jaejoon Han, Seoul (KR)
Assigned to Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed by Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed on Feb. 10, 2022, as Appl. No. 17/668,618.
Claims priority of application No. 10-2021-0042081 (KR), filed on Mar. 31, 2021; and application No. 10-2021-0077373 (KR), filed on Jun. 15, 2021.
Prior Publication US 2022/0318354 A1, Oct. 6, 2022
Int. Cl. G06F 21/32 (2013.01); G06V 10/74 (2022.01); G06V 10/82 (2022.01); G06V 40/12 (2022.01); G06V 40/40 (2022.01); G06V 40/50 (2022.01)
CPC G06F 21/32 (2013.01) [G06V 10/761 (2022.01); G06V 10/82 (2022.01); G06V 40/1365 (2022.01); G06V 40/1388 (2022.01); G06V 40/45 (2022.01); G06V 40/50 (2022.01)] 26 Claims
OG exemplary drawing
 
1. An anti-spoofing method comprising:
detecting first information related to whether biometric information of a user is forged, based on a first output vector of a first neural network configured to detect whether the biometric information is forged from input data comprising the biometric information;
extracting an input embedding vector comprising a feature of the biometric information from the input data;
calculating a similarity value of the input embedding vector based on a result of comparing the input embedding vector with a fake embedding vector and a result of comparing the input embedding vector with one or both of a real embedding vector and an enrollment embedding vector, the real embedding vector and the enrollment embedding vector being provided in advance;
calculating a total forgery score based on the similarity value and a second output vector of the first neural network according to whether the first information is detected; and
detecting second information related to whether the biometric information is forged, based on the total forgery score,
wherein the detecting the first information comprises:
extracting the first output vector from an intermediate layer of the first neural network; and
calculating an intermediate forgery score based on the first output vector.