Using facial data for device authentication or subject identification

• US 9,082,235 B2
• Filed: 07/12/2011
• Issued: 07/14/2015
• Est. Priority Date: 07/12/2011
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Lau, James Kai Yu, Kaheel, Ayman, El-Saban, Motaz, Shawky, Mohamed, Gonzalez, Monica, Deif, Tamer, Aly, Alaa Abdel-Hakim, El Baz, Ahmed
• Primary Examiner(s): Negron, Daniell L
• Assistant Examiner(s): Haile, Benyam
• Application Number:
  US13/181,377
• Publication Number:
  US 20130015946A1
• Time in Patent Office: 1,463 Days
• Field of Search: 340/5.2, 340/5.3, 340/5.31, 340/5.53, 340/5.8, 340/5.81, 340/5.82, 340/5.83, 382/115, 382/118
• US Class Current: 1/1
• CPC Class Codes: G06F 21/31 User authentication
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints
• CPC Class Codes: G06T 2207/30201 Face
• CPC Class Codes: G06V 10/422 for representing the structure of the pattern or shape of an object therefor
• CPC Class Codes: G06V 40/161 Detection; Localisation; Normalisation
• CPC Class Codes: G06V 40/165 using facial parts and geometric relationships
• CPC Class Codes: G06V 40/166 using acquisition arrangements
• CPC Class Codes: G06V 40/168 Feature extraction; Face representation
• CPC Class Codes: G06V 40/169 Holistic features and representations, i.e. based on the facial image taken as a whole
• CPC Class Codes: G06V 40/171 Local features and components; Facial parts eye characteristics G06V40/18; Occluding parts, e.g. glasses; Geometrical relationships
• CPC Class Codes: G06V 40/172 Classification, e.g. identification
• CPC Class Codes: G06V 40/174 Facial expression recognition
• CPC Class Codes: G06V 40/176 Dynamic expression
• CPC Class Codes: G06V 40/20 Movements or behaviour, e.g. gesture recognition recognition of facial expressions G06V40/16
• CPC Class Codes: G06V 40/40 Spoof detection, e.g. liveness detection
• CPC Class Codes: G07C 9/00 Individual registration on entry or exit
• CPC Class Codes: G09C 5/00 Ciphering apparatus or methods not provided for in the preceding groups, e.g. involving the concealment or deformation of graphic data such as designs, written or printed messages
• CPC Class Codes: H04N 23/74 by influencing the scene brightness using illuminating means

Abstract

Exemplary methods, apparatus, and systems are disclosed for authenticating a user to computing device. In one exemplary embodiment, an indication of a request by a user to unlock a mobile device in a locked state is received. One or more images of the face of the user are captured. Facial components of the user from the one or more captured images are extracted. A determination is made as to whether the user is an authorized user or a non-authorized user based at least in part on a comparison of the facial components of the user extracted from the one or more captured images to facial components of the authorized user from one or more authentication images of the authorized stored on the mobile device. If the user is determined to be the authorized user, the mobile device unlocked; otherwise, the mobile device is maintained in its locked state.

Claims

1. One or more computer-readable storage devices storing computer-executable instructions which when executed by a computer cause the computer to perform a method, the method comprising:

receiving an image of a user of a device;

identifying one or more facial descriptors of the user from the received image; and

evaluating whether the one or more identified facial descriptors of the user match one or more facial descriptors of a previous user extracted from multiple previously captured images of the previous user,

the multiple previously captured images of the previous user being captured under different light sources, at least one image of the previous user being of the previous user illuminated by a low-light source,

the evaluating comprising cross verifying the received images against at least one image of a non-user, the cross verifying comprising computing a distance between the received image and the at least one image of a non-user, and determining if the distance between the received image and the at least one image of a non-user is greater than a non-user image threshold value.

2. The one or more computer-readable storage devices of claim 1, wherein the method further comprises generating an indication that the user in the received image is an authorized user or is not the authorized user based at least in part on the evaluation.

3. The one or more computer-readable storage devices of claim 1, wherein the method further comprises finding that the one or more facial descriptors of the user in the received image match the one or more facial descriptors of the previous user if a smallest difference between the facial descriptors of the user in the received image and the facial descriptors of the previous user from the multiple images of the previous user satisfies a threshold value.

4. The one or more computer-readable storage devices of claim 1, wherein the evaluating further comprises evaluating whether the one or more identified facial descriptors of the user match one or more facial descriptors of multiple other previous users.

5. The one or more computer-readable storage devices of claim 1, wherein a first of the facial descriptors is weighted higher than a second of the facial descriptors.

6. The one or more computer-readable storage devices of claim 1, wherein the method further comprises finding that the one or more facial descriptors of the user in the received image match the one or more facial descriptors of the previous user if a smallest difference between the facial descriptors of the user in the received image and the facial descriptors of the previous user from the multiple images of the previous user satisfies a first threshold value, and if a ratio between the smallest distance and a greatest distance between the facial descriptors of the user in the received image and the facial descriptors of the previous user in the multiple images of the previous user satisfies a second threshold value.

7. The one or more computer-readable storage devices of claim 1, wherein two or more images of the user of the device are received, and wherein the method further comprises:

computing an average of the one or more facial descriptors from the two or more images of the user; and

finding that the one or more facial descriptors of the user match the one or more facial descriptors of the previous user if a difference between the average of the one or more facial descriptors and the facial descriptors of the previous user in at least one of the multiple images of the previous user satisfies a threshold value.

8. One or more computer-readable storage devices storing computer-executable instructions which when executed by a computer cause the computer to perform a method, the method comprising:

receiving an image of a user of a device;

identifying one or more facial descriptors of the user from the received image; and

evaluating whether the one or more identified facial descriptors of the user match one or more facial descriptors of an authorized user extracted from a plurality of images of the authorized user, the plurality of images of the authorized user being captured under different light sources, at least one image of the authorized user being of the previous user illuminated by a low-light source,

wherein the evaluating comprises cross verifying the received images against at least one image of a non-user, and

wherein the method further comprises finding that the one or more facial descriptors of the user in the received image match the one or more facial descriptors of the authorized user if (a) a difference between the facial descriptors of the user in the received image and the facial descriptors of the authorized user from the plurality of images of the authorized user satisfies a first threshold value, and (b) the number of images in the plurality of images satisfies a second threshold.

9. The one or more computer-readable storage devices of claim 8, wherein the method further comprises generating an indication that the user in the received image is an authorized user or is not the authorized user based at least in part on the evaluation.

10. The one or more computer-readable storage devices of claim 8, wherein a first of the facial descriptors is weighted higher than a second of the facial descriptors.

11. A computing device having a processor and memory, the computing device being configured to perform operations comprising:

receiving an image of a user of the device;

identifying one or more facial descriptors of the user from the received image; and

evaluating whether the one or more identified facial descriptors of the user match one or more facial descriptors of a previous user extracted from multiple previously captured images of the previous user,

the multiple previously captured images of the previous user being captured under different light sources, at least one image of the previous user being of the previous user illuminated by a low-light source,

the evaluating comprising cross verifying the received images against at least one image of a non-user, the cross verifying comprising computing a distance between the received image and the at least one image of a non-user, and determining if the distance between the received image and the at least one image of a non-user is greater than a non-user image threshold value.

12. The computing device of claim 11 further configured to perform the operation of generating an indication that the user in the received image is an authorized user or is not the authorized user based at least in part on the evaluation.

13. The computing device of claim 11 further configured to perform the operation of finding that the one or more facial descriptors of the user in the received image match the one or more facial descriptors of the previous user if a smallest difference between the facial descriptors of the user in the received image and the facial descriptors of the previous user from the multiple images of the previous user satisfies a threshold value.

14. The computing device of claim 11, wherein the evaluating further comprises evaluating whether the one or more identified facial descriptors of the user match one or more facial descriptors of multiple other previous users.

15. The computing device of claim 11, wherein a first of the facial descriptors is weighted higher than a second of the facial descriptors.

16. The computing device of claim 11 further configured to perform the operation of finding that the one or more facial descriptors of the user in the received image match the one or more facial descriptors of the previous user if a smallest difference between the facial descriptors of the user in the received image and the facial descriptors of the previous user from the multiple images of the previous user satisfies a first threshold value, and if a ratio between the smallest distance and a greatest distance between the facial descriptors of the user in the received image and the facial descriptors of the previous user in the multiple images of the previous user satisfies a second threshold value.

17. The computing device of claim 11, wherein two or more images of the user of the device are received, and wherein the device is configured to perform the further operations of:

computing an average of the one or more facial descriptors from the two or more images of the user; and

finding that the one or more facial descriptors of the user match the one or more facial descriptors of the previous user if a difference between the average of the one or more facial descriptors and the facial descriptors of the previous user in at least one of the multiple images of the previous user satisfies a threshold value.

18. A computing device having a processor and memory, the computing device being configured to perform operations comprising:

receiving an image of a user of the device;

identifying one or more facial descriptors of the user from the received image;

evaluating whether the one or more identified facial descriptors of the user match one or more facial descriptors of an authorized user extracted from a plurality of images of the authorized user, the plurality of images of the authorized user being captured under different light sources, at least one image of the authorized user being of the previous user illuminated by a low-light source, wherein the evaluating comprises cross verifying the received images against at least one image of a non-user; and

finding that the one or more facial descriptors of the user in the received image match the one or more facial descriptors of the authorized user if (a) a difference between the facial descriptors of the user in the received image and the facial descriptors of the authorized user from the plurality of images of the authorized user satisfies a first threshold value, and (b) the number of images in the plurality of images satisfies a second threshold.

19. The computing device of claim 18 further configured to perform the operation of generating an indication that the user in the received image is an authorized user or is not the authorized user based at least in part on the evaluation.

20. The computing device of claim 18, wherein a first of the facial descriptors is weighted higher than a second of the facial descriptors.