Image analysis for user authentication

• US 9,934,504 B2
• Filed: 10/19/2015
• Issued: 04/03/2018
• Est. Priority Date: 01/13/2012
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Wang, Yicong, Xu, Haizhi
• Primary Examiner(s): Sherali, Ishrat I
• Application Number:
  US14/887,274
• Publication Number:
  US 20160071111A1
• Time in Patent Office: 897 Days
• Field of Search: 382100, 382115
• CPC Class Codes: A61K 48/00 Medicinal preparations containing genetic material which is inserted into cells of the living body to treat genetic diseases; Gene therapy
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints
• CPC Class Codes: G06Q 20/12 specially adapted for electronic shopping systems
• CPC Class Codes: G06Q 20/3674 involving authentication
• CPC Class Codes: G06Q 20/40 Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
• CPC Class Codes: G06Q 20/4014 Identity check for transactions
• CPC Class Codes: G06Q 20/40145 Biometric identity checks
• CPC Class Codes: G06Q 30/0643 Graphical representation of items or shoppers
• CPC Class Codes: G06V 40/16 Human faces, e.g. facial parts, sketches or expressions
• 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: G06V 40/45 Detection of the body part being alive
• CPC Class Codes: H04L 63/0861 using biometrical features, e.g. fingerprint, retina-scan cryptographic mechanisms or cryptographic arrangements for entity authentication using biological data H04L9/3231
• CPC Class Codes: H04N 21/44008 involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream arrangements characterised by components specially adapted for monitoring, identification or recognition of video in broadcast systems H04H60/59

Abstract

A transaction is authorized using an authentication process that prompts the user to perform an action in view of a camera or sensor. The process identifies the user and verifies that the user requesting the transaction is a living human being. The user is identified using image information which is processed utilizing facial recognition. The device verifies that the image information corresponds to a living human using one or more human-verification processes. The device prompts the user to perform an action to confirm the transaction, and causes the transaction to be performed after verifying performance of the action by the identified user.

Claims

1. A computing device, comprising:

a processor; and

memory storing instructions that, when executed by the processor, cause the computing device to;

receive identifying information for a user in association with accessing information for products offered through an electronic marketplace;

receive a request to complete a transaction with the electronic marketplace on behalf of the user;

capture a first image using a camera of the computing device, the camera configured to capture at least a portion of a person interacting with a display screen of the computing device;

cause the first image to be analyzed to attempt to recognize an identity of the person contained in the first image;

cause additional captured image information to be analyzed to verify whether the person contained in the first image corresponds to a physical being in proximity of the computing device;

authenticate the user as a result of the identity of the person being recognized as the user associated with the identifying information and as a result of the person being verified to correspond to a physical being; and

cause the transaction to be completed once the user is authenticated.

2. The computing device of claim 1, wherein the additional captured image information includes still image or video information captured using the camera or another sensor on the computing device.

3. The computing device of claim 1, further comprising:

obtaining model information for the user, the model information being associated with a user profile for the electronic marketplace.

4. The computing device of claim 1, wherein receiving identifying information includes receiving information used to log the user into the electronic marketplace.

5. The computing device of claim 1, further comprising:

denying the transaction as a result of determining that the person is not recognized as the user or the person in the first image is not verified to correspond to a physical being.

6. A computer-implemented method comprising:

under control of one or more computing systems configured with executable instructions,

receiving a request to perform a transaction;

obtaining image information captured by a camera in communication with the one or more computing systems;

identifying a source of the request by at least analyzing at least a first portion of the image information;

verifying that the source of the request corresponds to a physical being within proximity of the camera by at least analyzing at least a second portion of the image information;

presenting a prompt to perform an action to authorize the transaction;

verifying that the action has been performed by at least analyzing a third portion of the image information; and

as a result of verifying that the action has been performed, causing the transaction to be completed.

7. The computer-implemented method of claim 6, wherein the second portion of the image information is captured while the source of the request is illuminated by an illumination source that is under the control of the one or more computing systems.

8. The computer-implemented method of claim 6, wherein the second portion of the image information is captured using a different camera or sensor than for the first portion of the image information.

9. The computer-implemented method of claim 6, wherein the second portion of the image information includes image information or video information.

10. The computer-implemented method of claim 6, wherein the action is selected at random from a collection of verifiable actions.

11. The computer-implemented method of claim 6, wherein the second portion of the image information is analyzed using at least two human verification processes.

12. The computer-implemented method of claim 11, further comprising:

performing a weighted combination of results from the at least two human verification processes.

13. The computer-implemented method of claim 11, wherein at least a second verification process is utilized when a first verification process is unable to verify that the source of the request contained in the image information corresponds to a physical being with at least a minimum level of confidence.

14. The computer-implemented method of claim 6, wherein the action is selected from a collection of actions that cannot be replicated with a two-dimensional image.

15. The computer-implemented method of claim 6, wherein analyzing at least a second portion of the image information includes detecting an eye blink in an amount of time.

16. The computer-implemented method of claim 6, further comprising:

receiving a request to utilize an authentication process;

obtaining image information including a requester;

generating a model corresponding to a face of the requester; and

providing the model to the computing device for use in authenticating the requester.

17. A non-transitory computer-readable storage medium storing instructions that, as a result of being executed by a processor of a computing system causing the computing system to:

capture, with a camera, image information that describes at least a first portion of a requester;

capture sensor data describing at least a second portion of the requester;

determine an identity of the requester using the image information;

verify that the requester included in the image information corresponds to a physical being in a particular location with respect to the camera;

display a prompt to perform an action to confirm performance of a request;

determine that the requester has performed the action; and

provide the identity of the requester and the request to a computing device as a result of having determined that the requester has performed the action.

18. The non-transitory computer-readable storage medium of claim 17, wherein verifying that the requester included in the image information corresponds to a physical being is accomplished at least in part by detecting an eye blink.

19. The non-transitory computer-readable storage medium of claim 17, wherein the sensor data is analyzed using at least two human verification processes, and further comprising:

performing a weighted combination of results from the at least two human verification processes.

20. The non-transitory computer-readable storage medium of claim 17, wherein analyzing at least a second portion of the image information includes at least one of analyzing infrared reflection data, thermographic information, motion information, or gesture information in the image information.