USER IDENTIFICATION BY GESTURE RECOGNITION

• US 20140219515A1
• Filed: 04/07/2014
• Published: 08/07/2014
• Est. Priority Date: 06/29/2011
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Karakotsios, Kenneth Mark, Ivanchenko, Volodymyr V.
• Granted Patent: US 9,465,982 B2
• Time in Patent Office: Days
• US Class Current: 382/115
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints
• CPC Class Codes: G06V 40/172 Classification, e.g. identification
• CPC Class Codes: G06V 40/28 Recognition of hand or arm movements, e.g. recognition of deaf sign language static hand signs G06V40/113
• CPC Class Codes: G06V 40/37 based only on signature signals such as velocity or pressure, e.g. dynamic signature recognition

Abstract

A user can be identified and/or authenticated to an electronic device by analyzing aspects of a motion or gesture made by that user. At least one imaging element of the device can capture image information including the motion or gesture, and can determine time-dependent information about that motion or gesture in two or three dimensions of space. The time-dependent information can be used to identify varying speeds, motions, and other such aspects that are indicative of a particular user. The way in which a gesture or motion is made, in addition to the motion or gesture itself, can be used to authenticate an individual user. While other persons can learn the basic gesture or motion, the way in which each person makes that gesture or motion will generally be at least slightly different, which can be used to prevent unauthorized access to sensitive information, protected functionality, or other such content.

Claims

1. A computing device, comprising:

a processor;

a camera; and

memory including instructions that, upon being executed by the processor, cause the computing device to;

capture, using the camera, a plurality of images each including a respective representation of at least one object corresponding to a user;

identify a respective position of the respective representation of the at least one object in each image of the plurality of images

compare the respective position of the respective representation of the at least one object in each image and a respective time for each respective position to one or more user-specific measurements corresponding to a manner of the user performing a gesture, the one or more user-specific measurements including at least one of;

(a) a path of movement of the gesture, (b) one or more of relative timing, acceleration, or velocity information corresponding to the gesture, or (c) measurements of at least one feature of the user that is used to perform the gesture; and

identify the user in response to determining that the respective position of the respective representation of the at least one object identified in each image and the respective time for each respective position matches the one or more user-specific measurements with at least a minimum level of confidence.

2. The computing device of claim 1, wherein the instructions, upon being executed, further cause the computing device to:

restrict access to at least some content or functionality of the computing device in response to determining that the respective position of the respective representation of the at least one object in each image and the respective time for each respective position do not match the one or more user-specific measurements with the at least the minimum level of confidence.

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

an infrared emitter; and

an infrared detector,

wherein the instructions, upon being executed, further cause the computing device to;

activate the infrared emitter during a period of time corresponding to when the plurality of images are captured;

capture a second plurality of images using the infrared detector during the period of time; and

subtract a weighted amount of respective ambient light image information in each image of the plurality of images and respective reflected infrared image information in each corresponding image of the second plurality of images to substantially remove background information in each corresponding image of the second plurality of images.

4. A computer-implemented method of identifying a user, comprising:

under control of one or more computing devices including executable instructions,

obtaining a plurality of images each including a respective representation of at least one object corresponding to the user;

identifying a respective set of one or more points corresponding to the respective representation of the at least one object in each image of the plurality of images

comparing the respective set of points identified in each image and a respective time for each respective set of points to one or more measurements corresponding to a manner of the user performing a gesture; and

identifying the user in response to determining that the respective set of points identified in each image and the respective time for each respective set of points matches the one or more measurements with at least a minimum level of confidence.

5. The computer-implemented method of claim 4, wherein the one or more measurements include at least one of:

(a) a path of movement of the gesture, (b) one or more of relative timing, acceleration, or velocity information corresponding to the gesture, or (c) measurements of at least one feature of the user that is used to perform the gesture.

6. The computer-implemented method of claim 4, wherein identifying the respective set of points in each image is based at least in part upon one of image recognition, proximity detection, or intensity analysis.

7. The computer-implemented method of claim 4, wherein the respective set of points corresponding to the respective representation of the at least one object in each image are three-dimensional points.

8. The computer-implemented method of claim 4, wherein each image of the plurality of images includes respective ambient light image information, and the method further comprises:

obtaining a second plurality of images during a period of time corresponding to when the plurality of images are obtained, each image of the second plurality of images including respective reflected infrared image information.

9. The computer-implemented method of claim 8, further comprising:

subtracting a weighted amount of the respective ambient light image information in each image of the plurality of images and the respective reflected infrared image information in each corresponding image of the second plurality of images to substantially remove background information in each corresponding image of the second plurality of images.

10. The computer-implemented method of claim 4, wherein obtaining the plurality of images includes capturing the plurality of images using a camera of a computing device in response to detecting motion within a field of view of the camera.

11. The computer-implemented method of claim 4, further comprising:

prompting the user to perform a second gesture;

capturing a second plurality of images and a respective second time corresponding to each image of the second plurality of images, the second plurality of images each including a respective representation of at least one second object corresponding to the user; and

providing to the user an indication of a degree of difficulty of replicating the second gesture.

12. The computer-implemented method of claim 4, further comprising:

causing at least one source of illumination to be activated at least during a period of time corresponding to when a first image of the plurality of images is obtained and a second image of the plurality of images is obtained.

13. The computer-implemented method of claim 12, wherein the at least one source of illumination includes at least one of a white light or an infrared source of illumination, the at least one of the white light or the infrared source of illumination being activated continuously or periodically during the period of time.

14. The computer-implemented method of claim 4, further comprising:

storing at least one portion of the plurality of images in a rolling buffer,

wherein identifying the respective set of points corresponding to the respective representation of the at least one object in each image occurs after a fixed period of time of storing the at least one portion of the plurality of images in the rolling buffer.

15. The computer-implemented method of claim 4, further comprising:

fitting a curve or a function to the respective set of points corresponding to the respective representation of the at least one object in each image.

16. The computer-implemented method of claim 4, further comprising:

restricting access to at least some content or functionality of the computing device in response to determining that the respective set of points identified in each image and the respective time for each respective set of points do not match the one or more measurements with the at least the minimum level of confidence.

17. The computer-implemented method of claim 4, further comprising:

deactivating a gesture input mode if no gesture is detected within a specified period of inactivity.

18. A non-transitory computer-readable storage medium storing instructions for identifying a user that, upon being executed by a processor, cause the processor to:

obtain a plurality of images each including a respective representation of at least one object corresponding to the user;

identify a respective set of one or more points corresponding to the respective representation of the at least one object in each image of the plurality of images

compare the respective set of points identified in each image and a respective time for each respective set of points to one or more measurements corresponding to a manner of the user performing a gesture, the one or more measurements including at least one of;

(a) a path of movement of the gesture, (b) one or more of relative timing, acceleration, or velocity information corresponding to the gesture, or (c) measurements of at least one feature of the user that is used to perform the gesture; and

identify the user in response to determining that the respective set of points identified in each image and the respective time for each respective set of points matches the one or more measurements with at least a minimum level of confidence.

19. The non-transitory computer-readable storage medium of claim 18, wherein the instructions, upon being executed, further cause the processor to:

prompt the user to perform a second gesture;

capture a second plurality of images and a respective second time corresponding to each image of the second plurality of images, the second plurality of images each including a respective representation of at least one second object corresponding to the user; and

provide to the user an indication of a degree of difficulty of replicating the second gesture.

20. The non-transitory computer-readable storage medium of claim 18, wherein the instructions, upon being executed, further cause the processor to:

store at least one portion of the plurality of images in a rolling buffer,

wherein the instructions, upon being executed to cause the processor to identify the respective set of points corresponding to the respective representation of the at least one object in each image, are executed after a fixed period of time of storing the at least one portion of the plurality of images in the rolling buffer.