Computerized system and method for determining authenticity of users via facial recognition

• US 10,049,287 B2
• Filed: 05/22/2015
• Issued: 08/14/2018
• Est. Priority Date: 05/22/2015
• Status: Active Grant

• Current Assignee: Verizon Patent and Licensing Incorporated (Verizon Communications Inc.)
• Original Assignee: Oath Inc. (Verizon Communications Inc.)
• Inventors: Holz, Christian, Patel, Miteshkumar, Buthpitiya, Senaka Wimal
• Primary Examiner(s): STREGE, JOHN B
• Application Number:
  US14/719,654
• Publication Number:
  US 20160342851A1
• Time in Patent Office: 1,180 Days
• Field of Search: 382118
• CPC Class Codes: G06V 40/172 Classification, e.g. identification
• CPC Class Codes: G06V 40/45 Detection of the body part being alive
• CPC Class Codes: G06V 40/70 Multimodal biometrics, e.g. combining information from different biometric modalities

Abstract

Disclosed are systems and methods for improving interactions with and between computers in an authentication system supported by or configured with authentication servers or platforms. The systems interact to identify access and retrieve data across platforms, which data can be used to improve the quality of results data used in processing interactions between or among processors in such systems. The disclosed anti-spoofing systems and methods provide improved functionality to facial recognition systems by enabling enhanced “spoof” (or attempts to impersonate a user) detection while authenticating a user. The disclosed systems and method provide additional functionality to existing facial recognition systems that enables such systems to actually determine whether the image being captured and/or recorded is that of an actual person, as opposed to a non-human representation.

Claims

1. A method comprising:

capturing, via a user-facing camera of a computing device, a representation of a user, said representation comprising a rendering of a face of the user;

capturing, via a back-facing camera of the computing device, biometric input of the user;

parsing, via the computing device, said captured representation to identify facial features of the user;

determining, via the computing device and based on said parsing, first information associated with a human being based on the identified facial features;

parsing, via the computing device, said biometric input of the user;

determining, via the computing device, second information associated with a human being based on the parsed biometric input;

normalizing, via the computing device, the first information and the second information;

analyzing, via the computing device, the normalized first and second information, and based on said analysis, determining whether biometric values of the second information correspond to biometric values of the first information;

determining, via the computing device, a live-ness of the user based on said biometric value determination, said live-ness indicating whether the representation is of a human being and not a non-human representation of a human-being; and

enabling, via the computing device, facial recognition authentication of the user based on said live-ness determination, said enabling comprising executing said facial recognition authentication when said live-ness indicates the captured representation is of a human being, said enabling further comprising denying execution of said facial recognition authentication when said live-ness indicates the captured representation is a non-human representation.

2. The method of claim 1, further comprising:

analyzing said captured representation to identify an activity associated with at least one of said facial features; and

identifying variations in at least one of said facial features as performing an autonomous activity.

3. The method of claim 2, further comprising:

determining a pulse from the captured image by amplifying said identified variations, wherein said pulse determination triggers said live-ness determination.

4. The method of claim 2, further comprising:

detecting temporal color changes in the user'"'"'s face based on said identified variations; and

determining blood circulation from said captured image based on said detected color changes, wherein said blood circulation determination triggers said live-ness determination.

5. The method of claim 2, wherein said activity is identified and analyzed via a magnification algorithm being applied to the captured image.

6. The method of claim 1, further comprising:

analyzing said facial features to identify movements of at least one of said facial features; and

detecting non-linear movements of said at least one of said facial features, wherein said non-linear movement detection triggers said live-ness determination.

7. The method of claim 1, further comprising:

generating an output to be rendered to the user, said output comprising information indicating a predetermined user response to the output;

tracking a response by the user to said output; and

determining said live-ness of the user based on said user response, said determination comprising comparing said predetermined user response to said user response, wherein said comparison satisfying a threshold triggers said live-ness determination.

8. The method of claim 7, wherein said output comprises content that triggers said user response to be involuntary.

9. The method of claim 7, wherein said generating the output comprises prompting the user with said output, said prompt comprising requesting said user to respond to said output.

10. The method of claim 7, wherein said output comprises content selected from a group consisting of:

audio, video, an image, text, and some combination thereof.

11. The method of claim 3, further comprising:

receiving an input from the user, said input comprising a second pulse reading derived from a finger of the user being placed a camera of the computing device;

comparing a pulse pattern of the pulse determined from the captured image and a pulse pattern of the second pulse; and

determining said live-ness of the user based on said comparison, wherein said comparison satisfying a threshold triggers said live-ness determination.

12. The method of claim 1, wherein said captured representation of the user is an image.

13. The method of claim 1, wherein said captured representation of the user is a video.

14. The method of claim 1, wherein said information comprises biometric information related to at least one of the user'"'"'s retina and the user'"'"'s face.

15. A non-transitory computer-readable storage medium tangibly encoded with computer-executable instructions, that when executed by a processor associated with a computing device, performs a method comprising:

capturing, via a user-facing camera of the computing device, a representation of a user, said representation comprising a rendering of a face of the user;

capturing, via a back-facing camera of the computing device, biometric input of the user;

parsing, via the computing device, said captured representation to identify facial features of the user;

determining, via the computing device and based on said parsing, first information associated with a human being based on the identified facial features;

parsing, via the computing device, said biometric input of the user;

determining, via the computing device, second information associated with a human being based on the parsed biometric input;

normalizing, via the computing device, the first information and the second information;

analyzing, via the computing device, the normalized first and second information, and based on said analysis, determining whether biometric values of the second information correspond to biometric values of the first information;

determining, via the computing device, a live-ness of the user based on said biometric value determination, said live-ness indicating whether the representation is of a human being and not a non-human representation of a human-being; and

enabling, via the computing device, facial recognition authentication of the user based on said live-ness determination, said enabling comprising executing said facial recognition authentication when said live-ness indicated the captured representation is of a human being, said enabling further comprising denying execution of said facial recognition authentication when said live-ness indicates the captured representation is a non-human representation.

16. The non-transitory computer-readable storage medium of claim 15, further comprising:

analyzing said captured representation to identify an activity associated with at least one of said facial features; and

identifying variations in at least one of said facial features as performing an autonomous activity, wherein said identified autonomous activity triggers said live-ness determination.

17. The non-transitory computer-readable storage medium of claim 15, further comprising:

generating an output to be rendered to the user, said output comprising information indicating a predetermined user response to the output;

tracking a response by the user to said output; and

determining said live-ness of the user based on said user response, said determination comprising comparing said predetermined user response to said user response, wherein said comparison satisfying a threshold triggers said live-ness determination.

18. A computing device comprising:

a processor;

a non-transitory computer-readable storage medium for tangibly storing thereon program logic for execution by the processor, the program logic comprising;

logic executed by the processor for capturing, via a user-facing camera of the computing device, a representation of a user, said representation comprising a rendering of a face of the user;

logic executed by the processor for capturing, via a back-facing camera of the computing device, biometric input of the user;

logic executed by the processor for parsing, via the computing device, said captured representation to identify facial features of the user;

logic executed by the processor for determining, via the computing device and based on said parsing, first information associated with a human being based on the identified facial features;

logic executed by the processor for parsing, via the computing device, said biometric input of the user;

logic executed by the processor for determining, via the computing device, second information associated with a human being based on the parsed biometric input;

logic executed by the processor for normalizing, via the computing device, the first information and the second information;

logic executed by the processor for analyzing, via the computing device, the normalized first and second information, and based on said analysis, determining whether biometric values of the second information correspond to biometric values of the first information;

logic executed by the processor for determining, via the computing device, a live-ness of the user based on said biometric value determination, said live-ness indicating whether the representation is of a human being and not a non-human representation of a human-being; and

logic executed by the processor for enabling, via the computing device, facial recognition authentication of the user based on said live-ness determination, said enabling comprising executing said facial recognition authentication when said live-ness indicates the captured representation is of a human being, said enabling further comprising denying execution of said facial recognition authentication when said live-ness indicates the captured representation is a non-human representation.

19. The computing device of claim 18, further comprising:

logic executed by the processor for analyzing said captured representation to identify an activity associated with at least one of said facial features; and

logic executed by the processor for identifying variations in at least one of said facial features as performing an autonomous activity, wherein said identified autonomous activity triggers said live-ness determination.

20. The computing device of claim 18, further comprising:

logic executed by the processor for generating an output to be rendered to the user, said output comprising information indicating a predetermined user response to the output;

logic executed by the processor for tracking a response by the user to said output; and

logic executed by the processor for determining said live-ness of the user based on said user response, said determination comprising comparing said predetermined user response to said user response, wherein said comparison satisfying a threshold triggers said live-ness determination.