Facial recognition similarity threshold adjustment
AssigneeGoogle Inc.
InventorMichael Christian Nechyba
Life of this patent
Estimating the term…
Abstract
In general, aspects of the present disclosure are directed to techniques for adjusting the threshold similarity score to match the facial features of an authorized user in a facial recognition system. Instead of a uniform threshold similarity score, representations of authorized faces enrolled in the computing device may be assigned a custom threshold similarity score based at least in part on the distinctiveness of the facial features in the representations of the authorized faces. A computing device can determine a distinctiveness of facial features of an enrolling user, and can determine a threshold similarity score associated with the facial features of the enrolling user based at least in part on the distinctiveness of the facial features of the enrolling user.
Claims27
A method comprising:
- determining a distinctiveness of a first set of facial features of an enrolling user of a facial recognition system based at least in part upon a comparison of the first set of facial features of the enrolling user to facial features of a plurality of other users, the first set of facial features of the enrolling user being extracted from one or more images of the enrolling user, wherein the comparison of the first set of facial features of the enrolling user to the facial features of the plurality of other users further comprises a comparison of at least a first face template that quantifies the first set of facial features of the enrolling user to at least a second template that quantifies the facial features of the plurality of other users;
- and
- determining, by a computing device, a threshold similarity score associated with the first set of facial features of the enrolling user based at least in part on the distinctiveness of the first set of facial features of the enrolling user, wherein a second set of facial features of an accessing user matches the first set of facial features of the enrolling user if a similarity score between the first set of facial features of the enrolling user and the second set of facial features of the accessing user exceeds the threshold similarity score for the first set of facial features.
A device comprising:
- at least one processor, wherein the at least one processor is configured to:
- determine a distinctiveness of a first set of facial features of an enrolling user of a facial recognition system based at least in part upon a comparison of the first set of facial features of the enrolling user to facial features of a plurality of other users, the first set facial features of the enrolling user being extracted from one or more images of the enrolling user, wherein the comparison of the first set of facial features of the enrolling user to the facial features of the plurality of other users further comprises a comparison of at least a first face template that quantifies the first set of facial features of the enrolling user to at least a second face template that quantifies the facial features of the plurality of other users;
- and
- determine a threshold similarity score associated with the first set of facial features of the enrolling user based at least in part on the distinctiveness of the first set of facial features of the enrolling user, wherein a second set of facial features of an accessing user matches the first set of facial features of the enrolling user if a similarity score between the first set of facial features of the enrolling user and the second set of facial features of the accessing user exceeds the threshold similarity score for the first set of facial features.
A computer-readable storage device containing instructions that, when executed on at least one processor, cause the at least one processor to perform operations comprising:
- determining, by a computing device, a distinctiveness of a first set of facial features of an enrolling user of a facial recognition system based at least in part upon a comparison of the first set of facial features of the enrolling user to facial features of a plurality of other users, the first set of facial features of the enrolling user being extracted from one or more images of the enrolling user, wherein the comparison of the first set of facial features of the enrolling user to the facial features of the plurality of other users further comprises a comparison of at least a first face template that quantifies the first set of facial features of the enrolling user to at least a second face template that quantifies the facial features of the plurality of other users;
- and
- determining, by the computing device, a threshold similarity score associated with the first set of facial features of the enrolling user based at least in part on the distinctiveness of the first set of facial features of the enrolling user, wherein a second set of facial features of an accessing user matches the first set of facial features of the enrolling user if a similarity score between the first set of facial features of the enrolling user and the second set of facial features of the accessing user exceeds the threshold similarity score for the first set of facial features.
Dependencies are inferred from the claim text.