Face-based authentication with situational adaptivity

A non-transitory computer readable medium having stored thereon program code executable by a processor, the program code comprising:

• code that causes the processor to create an enrollment template for a user, the enrollment template being derived from one or more enrollment images of the user's face and being usable by a face-based authentication system to authenticate the user's identity;
• code that causes the processor to determine a first set of metadata associated with the one or more enrollment images, the first set of metadata pertaining to environmental or situational conditions at the time of creating the enrollment template;
• code that causes the processor to store the first set of metadata with the enrollment template;
• code that causes the processor to capture, at a time of user authentication, an input image of the user's face;
• code that causes the processor to determine a second set of metadata associated with the input image, the second set of metadata pertaining to environmental or situational conditions at the time of capturing the input image;
• code that causes the processor to calculate a computational distance between features extracted from the input image and the facial template, wherein the computational distance is increased if a degree of difference between the first set of metadata and the second set of metadata is relatively large, and wherein the computational distance is decreased if the degree of difference between the first set of metadata and the second set of metadata is relatively small;
• and
• code that causes the processor to determine whether to authenticate the user based on the computational distance.

A computing device comprising:

• a face-based authentication subsystem;
• and
• a processor configured to:
• create an enrollment template for a user, the enrollment template being derived from one or more enrollment images of the user's face and being usable by the face-based authentication subsystem to authenticate the user's identity;
• determine a first set of metadata associated with the one or more enrollment images, the first set of metadata pertaining to environmental or situational conditions at the time of creating the enrollment template;
• store the first set of metadata with the enrollment template;
• capture, at a time of user authentication, an input image of the user's face;
• determine a second set of metadata associated with the input image, the second set of metadata pertaining to environmental or situational conditions at the time of capturing the input image;
• calculate a computational distance between features extracted from the input image and the enrollment template, wherein the computational distance is increased if a degree of difference between the first set of metadata and the second set of metadata is relatively large, and wherein the computational distance is decreased if the degree of difference between the first set of metadata and the second set of metadata is relatively small;
• and
• determine whether to authenticate the user based on the computational distance.