US 12,307,815 B2
Face recognition method and face recognition apparatus
Honglei Zhang, Beijing (CN); and Zhigang Li, Beijing (CN)
Assigned to HUAWEI TECHNOLOGIES CO., LTD., Shenzhen (CN)
Appl. No. 17/758,946
Filed by Huawei Technologies Co., Ltd., Shenzhen (CN)
PCT Filed Jul. 30, 2020, PCT No. PCT/CN2020/105772
§ 371(c)(1), (2) Date Jul. 15, 2022,
PCT Pub. No. WO2021/143101, PCT Pub. Date Jul. 22, 2021.
Claims priority of application No. 202010051193.9 (CN), filed on Jan. 16, 2020.
Prior Publication US 2023/0080031 A1, Mar. 16, 2023
Int. Cl. G06V 40/16 (2022.01); G06N 3/045 (2023.01); G06N 3/084 (2023.01); G06V 10/82 (2022.01)
CPC G06V 40/172 (2022.01) [G06N 3/045 (2023.01); G06N 3/084 (2013.01); G06V 10/82 (2022.01); G06V 40/165 (2022.01); G06V 40/171 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method, applied to an apparatus, the method comprising:
obtaining a face image to be recognized;
extracting a face image feature based on the face image using a pre-trained feature extraction network;
extracting a plurality of facial geometric feature points from the face image to determine a plurality of feature point sets, wherein each feature point set of the plurality of feature point sets corresponds to one face part, and each feature point set comprises at least one facial geometric feature point;
obtaining a face topology structure feature based on the plurality of feature point sets, wherein the face topology structure feature is used to determine a relative location relationship between the feature point sets of the plurality of feature point sets; and
performing matching in a preset face database based on the face topology structure feature and the face image feature, to obtain a face recognition result,
wherein obtaining the face topology structure feature based on the plurality of feature point sets comprises:
constructing a mapping relationship between the plurality of feature point sets and a plurality of feature point sets of a standard face, wherein the mapping relationship is used to determine the relative location relationship between the feature point sets of the plurality of feature point sets; and
inputting the mapping relationship into a pre-trained face topology structure feature extraction network to obtain the face topology structure feature.