CPC G06F 21/32 (2013.01) [G06F 3/017 (2013.01); G06N 3/08 (2013.01); G06V 40/107 (2022.01); G06V 40/168 (2022.01); G06V 40/172 (2022.01); G06V 40/28 (2022.01); G06V 40/70 (2022.01); G06F 2221/2141 (2013.01)] | 17 Claims |
1. A method for authenticating a user, comprising:
recording, with a camera, image data of the user, the image data recorded with the camera being three-dimensional image data of the user;
deriving at least one first facial feature of the user's face and at least one first gesture feature of one or more gestures of the user from the image data;
determining a degree of access of the user to data depending on whether the first gesture feature corresponds to at least one predetermined second gesture feature and whether the first facial feature corresponds to at least one predetermined second facial feature; and
permitting the user access the data depending on the degree of access determined, wherein
the degree of access permits the user to retrieve the data if the first gesture feature corresponds to the at least one predetermined second gesture feature,
the degree of access permits the user to retrieve and modify the data if the first gesture feature corresponds to the at least one predetermined gesture feature and the first facial feature corresponds to the at least one predetermined second facial feature, and
the degree of access denies access to the user if the first facial feature corresponds to the at least one predetermined second facial feature but the first gesture feature does not correspond to the at least one predetermined second gesture feature,
wherein the method further comprises recording training image data of at least one test user, determining at least one label indicative of at least one third gesture feature of one or more gestures of the recorded test user, and using machine learning based on the training image data and the labels for training an artificial neural network to detect the first gesture feature from the image data.
|