CPC G06V 40/50 (2022.01) [G06F 18/23 (2023.01); G06V 40/1347 (2022.01); G06V 40/1365 (2022.01)] | 20 Claims |
1. A method comprising:
storing multiple feature data, each respective feature data being generated using a trained machine-learning model configured to receive respective image data of a palm of a respective user and output the respective feature data, the respective feature data representing one or more biometric characteristics of the palm of the respective user;
applying a clustering algorithm to the multiple feature data to generate cluster data, wherein the cluster data indicates a connection between an individual feature data and each other feature data having a computed similarity to the individual feature data that is greater than a threshold similarity;
determining a dominating set for a first cluster represented by the cluster data, wherein the first cluster is associated with a first user profile;
generating identification data using feature data of the dominating set; and
storing the identification data in association with the first user profile.
|