Disclosed in embodiments of the present application is a face recognition method that can be used in the field of artificial intelligence. The method of the embodiments of the present application comprises: obtaining a face image to be recognized; extracting face image features according to the face image by means of a pre-trained feature extraction network; extracting a plurality of facial geometric feature points in the face image so as to determine a plurality of feature point sets, each feature point set in the plurality of feature point sets corresponding to one face region, and the feature point set comprising at least one facial geometric feature point; obtaining face topological structure features according to the plurality of feature point sets, the face topological structure features being used to determine a relative positional relationship between the plurality of feature point sets; and performing matching in a preset face database according to the face topological structure features and the face image features so as to obtain a face recognition result.