Authentication using facial image comparison

Patent metadata

Field	Value
Publication number	US-10977356-B2
Application number	US-202016795502-A
Country	US
Kind code	B2
Filing date	Feb 19, 2020
Priority date	Aug 9, 2017
Publication date	Apr 13, 2021
Grant date	Apr 13, 2021

Abstract

Computer systems and methods are provided for performing authentication of a user. A computer system receives, from a camera on an electronic device distinct from the computing system: a single captured image that includes a first facial image of a user and an image of a document that includes a second facial image of the user, and a third facial image of the user captured at a different time from the first facial image. The computer system determines whether the first facial image and the second facial image meet matching criteria. The computer system determines, using the third facial image, that the user is moving. And, in accordance with determinations that the first facial image and the second facial image meet the matching criteria and that the user is moving, the computer system transmits authorization information for the user to the electronic device.

First claim

What is claimed is:

1. A computer-implemented method, comprising:
at a computing system including one or more processors and memory storing one or more programs configured for execution by the one or more processors:
receiving, from a camera on an electronic device distinct from the computing system, captured image data including:
a single captured image that includes a first facial image of a user and an image of a document that includes a second facial image of the user, and
a third facial image of the user captured at a different time from the first facial image;

determining whether the first facial image and the second facial image meet matching criteria;
determining that the user is moving based on a comparison of the third facial image and at least the first facial image; and
in accordance with determinations that the first facial image and the second facial image meet the matching criteria and that the user is moving, transmitting authorization information for the user to the electronic device.

2. The method of claim 1 , further comprising, in accordance with a determination that the first facial image and the second facial image do not meet the matching criteria, transmitting, to the electronic device, a facial position adjustment request.

3. The method of claim 1 , including, in accordance with a determination that the first facial image and the second facial image do not meet the matching criteria, transmitting authorization denial information to the electronic device.

4. The method of claim 1 , including:
prior to receiving the single captured image that includes the first facial image and the image of the document that includes the second facial image:
receiving an authorization request from the electronic device via a first network;
determining whether the first network meets image validation criteria;
in accordance with a determination that the first network meets the image validation criteria, transmitting a request for the single captured image that includes the first facial image and the image of the document that includes the second facial image.

5. The method of claim 1 , wherein determining that the user is moving, further comprises:
determining a facial feature movement path by comparing a facial feature of the third facial image with a corresponding facial feature of at least one other facial image; and
determining that a length of the facial feature movement path meets threshold distance criteria.

6. The method of claim 1 , wherein determining that the user is moving, comprises:
transmitting, to the electronic device, information for displaying a target that moves along a target path;
determining a facial feature movement path by comparing a facial feature of the third facial image with a corresponding facial feature of least one other facial image received from the camera; and
comparing the target path with the facial feature movement path.

7. The method of claim 1 , wherein the single captured image and the third facial image are frames in a video stream.

8. The method of claim 7 , further comprising:
analyzing the video stream to determine:
a first portion of the video stream that corresponds to the first facial image, and
a second portion of the video stream that corresponds to the second facial image.

9. The method of claim 8 , further including generating the first portion of the video stream by compositing a plurality of respective portions of respective image frames from the video stream that correspond to the first facial image.

10. The method of claim 8 , wherein analyzing the video stream to determine the first portion of the video stream that corresponds to the first facial image includes selecting, using the second portion of the video stream that corresponds to the second facial image, a respective portion of a respective image frame that corresponds to the first facial image.

11. The method of claim 8 , wherein:
the image of the document that includes the second facial image includes facial image location cue information; and
determining the second portion of the video stream that corresponds to the second facial image includes determining a location of the facial image location cue information.

12. The method of claim 8 , including:
after analyzing the video stream to determine the first portion of the video stream that corresponds to the first facial image and the second portion of the video stream that corresponds to the second facial image:
analyzing the first portion of the video stream to determine a first facial position;
analyzing the second portion of the video stream to determine a second facial position;
determining whether facial position matching criteria are met by comparing the first facial position with the second facial position;
in accordance with a determination that facial position matching criteria are not met, transmitting, to the electronic device, a facial position matching request.

13. The method of claim 8 , including:
after analyzing the video stream to determine the first portion of the video stream that corresponds to the first facial image and the second portion of the video stream that corresponds to the second facial image:
analyzing the second portion of the video stream to determine a second facial position;
determining whether the second facial position meets facial position criteria that correspond to the document;
in accordance with a determination that the facial position criteria that correspond to the document are not met, transmitting, to the electronic device, a facial position adjustment request.

14. The method of claim 8 , wherein determining whether the first facial image and the second facial image meet matching criteria includes at least one of:
comparing the first portion of the video stream with image data that corresponds to a stored facial image; or
comparing the second portion of the video stream with the image data that corresponds to the stored facial image.

15. The method of claim 4 , wherein determining whether the first network meets image validation criteria includes accessing a stored value to determine whether a previous authorization of a received request occurred.

16. The method of claim 4 , including: in accordance with a determination that the first network does not meet the image validation criteria, transmitting a request for alternative authentication data.

17. The method of claim 4 , including,
receiving an authorization request from the electronic device via a second network; and
in response to receiving the authorization request from the electronic device via the second network, forgoing transmitting the request for the single captured image that includes the first facial image and the image of the document that includes the second facial image.

18. A computing system, comprising:
one or more processors;
memory; and
one or more programs, wherein the one or more programs are stored in the memory and are configured for execution by the one or more processors, the one or more programs including instructions for:
receiving, from a camera on an electronic device distinct from the computing system, captured image data including:
a single captured image that includes a first facial image of a user and an image of a document that includes a second facial image of the user, and
a third facial image of the user captured at a different time from the first facial image;

determining whether the first facial image and the second facial image meet matching criteria;
determining that the user is mo

Assignees

• Jumio Corp

Inventors

• Hochrieser Reinhard
• Danzer Lukas
• Bayer Lukas

Classifications

• G06V40/70

  Multimodal biometrics, e.g. combining information from different biometric modalities · CPC title

• G06V40/67

  by interactive indications to the user · CPC title

• G06V40/45

  Detection of the body part being alive · CPC title

• G06V40/172

  Classification, e.g. identification · CPC title

• G06V40/16

  Human faces, e.g. facial parts, sketches or expressions · CPC title