US 12,353,511 B2
Information processing device, personal identification device, information processing method, and storage medium
Akinori Ebihara, Tokyo (JP)
Assigned to NEC CORPORATION, Tokyo (JP)
Appl. No. 17/439,009
Filed by NEC Corporation, Tokyo (JP)
PCT Filed Mar. 26, 2019, PCT No. PCT/JP2019/012793
§ 371(c)(1), (2) Date Sep. 14, 2021,
PCT Pub. No. WO2020/194497, PCT Pub. Date Oct. 1, 2020.
Prior Publication US 2022/0147778 A1, May 12, 2022
Int. Cl. G06F 18/00 (2023.01); G06F 18/21 (2023.01); G06F 18/2415 (2023.01); G06F 18/2431 (2023.01)
CPC G06F 18/2415 (2023.01) [G06F 18/217 (2023.01); G06F 18/2431 (2023.01)] 8 Claims
OG exemplary drawing
 
1. An information processing device comprising:
at least one memory storing instructions; and
at least one processor configured to execute the instructions to:
acquire a first face image from sequential data acquired by a camera;
acquire at least one second face image acquired earlier than the first face image;
calculate a likelihood ratio indicating a ratio between a probability that the first face image and the second face image belong to a first class and a probability that the first face image and the second face image belong to a second class;
read out an integrated likelihood ratio calculated in a past from the memory;
calculate a logarithm of the likelihood using the integrated likelihood ratio calculated in the past, and calculate the integrated likelihood ratio indicating that the entire sequential data belongs to one of a plurality of classes;
when the integrated likelihood ratio does not exceed a threshold, repeat a process of acquiring a new face image and calculating the likelihood ratio and the integrated likelihood ratio to compare the integrated likelihood ratio with the threshold;
for use in authentication of an authentication gate, compare the integrated likelihood ratio with the threshold, and classify the entire sequential data to a corresponding class when the integrated likelihood ratio exceeds the threshold.