Process for updating templates used in facial recognition

A method, comprising:

• obtaining a first image of a face of a user using a camera located on a device, the device comprising a computer processor and a memory;
• encoding the first image to generate at least one first feature vector, wherein the first feature vector represents one or more facial features of the user in the first image;
• comparing the first feature vector to one or more reference templates stored in a first space in the memory of the device to obtain a first matching score;
• comparing the first matching score to an unlock threshold for the device;
• in response to the first matching score being below the unlock threshold:
• prompting the user to complete at least one additional authentication protocol;
• in response to the user being successfully authenticated using the at least one additional authentication protocol:
• storing the first feature vector as a temporary template in a second space in the memory of the device in response to the first matching score being above a first threshold;
• obtaining a second image of the face of the user using the camera;
• encoding the second image to generate at least one second feature vector, wherein the second feature vector represents one or more facial features of the user in the second image;
• comparing the second feature vector to the temporary template stored in the second space to obtain a second matching score;
• assessing a confidence score for the temporary template by comparing the second matching score to a second threshold, the second threshold being above the first threshold;
• and
• adding the temporary template to the reference templates in response to the assessed confidence score being above a selected confidence score.

A device, comprising:

• a camera;
• at least one illuminator providing infrared illumination;
• circuitry coupled to the camera and the illuminator, wherein the circuitry is configured to:
• obtain a first image of the face of the user using the camera;
• encode the first image to generate at least one first feature vector, wherein the first feature vector represents one or more facial features of the user in the first image;
• compare the first feature vector to one or more reference templates stored in a first space in the memory of the device to obtain a first matching score;
• authorize the user to perform at least one operation on the device that requires authentication in response to the first matching score being above an unlock threshold for the device;
• store the first feature vector as a temporary template in a second space in the memory of the device in response to the first matching score being above a first threshold;
• obtain a plurality of additional images of the face of the user using the camera, wherein the additional images are obtained in response to additional authentication attempts initiated by the user;
• subsequent to each additional authentication attempt initiated by the user:
• encode at least one additional image for the additional authentication attempt to generate at least one additional feature vector, wherein the additional feature vector represents one or more facial features of the user in the at least one additional image;
• compare the additional feature vector to the temporary template stored in the second space to obtain an additional matching score;
• and
• assess the additional authentication attempt as being successful
• in response to the additional matching score for the additional
• authentication attempt being above a second threshold;
• after a selected number of additional authentication attempts, assess a confidence score for the temporary template, the confidence score being based on a number of the additional authentication attempts assessed as being successful for the selected number of additional authentication attempts;
• and
• add the temporary template to the reference templates in response to the assessed confidence score being above a selected confidence score.