US 12,437,574 B2
Threshold calculation system, threshold calculation method, and computer program
Masakazu Shimizu, Tokyo (JP)
Assigned to NEC CORPORATION, Tokyo (JP)
Appl. No. 18/023,932
Filed by NEC Corporation, Tokyo (JP)
PCT Filed Sep. 30, 2020, PCT No. PCT/JP2020/037286
§ 371(c)(1), (2) Date Feb. 28, 2023,
PCT Pub. No. WO2022/070349, PCT Pub. Date Apr. 7, 2022.
Prior Publication US 2024/0029466 A1, Jan. 25, 2024
Int. Cl. G06V 40/10 (2022.01); G06F 21/32 (2013.01); G06V 10/74 (2022.01); G06V 10/75 (2022.01); G06V 30/19 (2022.01); G06V 40/50 (2022.01)
CPC G06V 40/10 (2022.01) [G06F 21/32 (2013.01); G06V 10/751 (2022.01); G06V 10/761 (2022.01); G06V 30/1912 (2022.01); G06V 40/50 (2022.01)] 16 Claims
OG exemplary drawing
 
1. A threshold calculation system, comprising:
at least one memory that is configured to store instructions; and
at least one first processor that is configured to execute the instructions to obtain a matching information that is used for matching of a biological body;
obtain an attribute information indicating an attribute of the biological body or an attribute of the matching information;
store the matching information and the attribute information for each biological body;
extract, as sample data, a plurality of matching information, based on a predetermined condition about the attribute information;
estimate a population from the sample data;
calculate a threshold related to the matching information, based on a distribution of the estimated population;
perform an authentication process based on a comparison between the matching information and the threshold; and
control a gate based on a result of the authentication process,
wherein the attribute information includes an environment attribute information indicating an environment in which the matching information is obtained,
wherein the environment attribute information indicates pixel brightness, and
wherein the at least one first processor is further configured to execute the instructions to extract the plurality of matching information as the sample data based on the pixel brightness.