US 11,861,938 B2
Device and method for classifying biometric authentication data
Hyogi Lee, Seongnam-si (KR); Kideok Lee, Seongnam-si (KR); and Bong Seop Song, Seongnam-si (KR)
Assigned to Suprema Inc., Seongnam-si (KR)
Filed by Suprema Inc., Seongnam-si (KR)
Filed on Mar. 18, 2022, as Appl. No. 17/698,311.
Application 17/698,311 is a continuation of application No. 17/537,988, filed on Nov. 30, 2021, granted, now 11,386,706.
Claims priority of application No. 10-2021-0158733 (KR), filed on Nov. 17, 2021.
Prior Publication US 2023/0154234 A1, May 18, 2023
Int. Cl. G06V 40/16 (2022.01); G06N 20/00 (2019.01)
CPC G06V 40/172 (2022.01) [G06N 20/00 (2019.01)] 2 Claims
OG exemplary drawing
 
1. A method for adding biometric authentication training data into a database performed by a biometric authentication data classification device, comprising:
extracting first biometric characteristic information from at least one candidate biometric training data for biometric authentication using an artificial neural network model;
calculating an overall similarity between the first biometric characteristic information and second biometric characteristic information extracted from a performance test database of which a biometric authentication performance is lower than a threshold level, the performance test database being selected among performance test databases for the biometric authentication; and
adding the at least one candidate biometric training data into one of the biometric authentication training database and the performance test database based on the calculated overall similarity,
wherein the calculating of the overall similarity includes:
calculating a characteristic similarity of the age characteristic, a characteristic similarity of a race characteristic, and a characteristic similarity of a gender characteristic; and
multiplying the calculated characteristic similarities of the age characteristic, the race characteristic, and the gender characteristic to determine a result of the multiplying as the overall similarity,
wherein the overall similarity is calculated by an equation as follows:
V=WaSa(A,B)×WeSe(A,B)×WsSs(A,B)
where Wa is an age characteristic weight, We is a race characteristic weight, Ws is a gender characteristic weight, Sa is an age characteristic similarity, Se is a race characteristic similarity, Ss is a gender characteristic similarity, A is first face characteristic information, and B is second face characteristic information.