Multi-frame depth image information identification

• US 8,966,613 B2
• Filed: 09/30/2011
• Issued: 02/24/2015
• Est. Priority Date: 09/30/2011
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Horvitz, Eric, Tan, Desney S., Liu, James Chia-Ming
• Primary Examiner(s): Lemma, Samson
• Assistant Examiner(s): Cribbs, Malcolm
• Application Number:
  US13/250,542
• Publication Number:
  US 20130086674A1
• Time in Patent Office: 1,243 Days
• Field of Search: None
• US Class Current: 726/17
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints
• CPC Class Codes: G06V 40/20 Movements or behaviour, e.g. gesture recognition recognition of facial expressions G06V40/16
• 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: H04L 9/3231 Biological data, e.g. fingerprint, voice or retina network architectures or network communication protocols for supporting authentication of entities using biometrical features in a packet data network H04L63/0861

Abstract

Embodiments of the present invention relate to systems, methods, and computer storage media for identifying, authenticating, and authorizing a user to a device. A dynamic image, such as a video captured by a depth camera, is received. The dynamic image provides data from which geometric information of a portion of a user may be identified as well as motion information of a portion of the user may be identified. Consequently, a geometric attribute is identified from the geometric information. A motion attribute may also be identified from the motion information. The geometric attribute is compared to one or more geometric attributes associated with authorized users. Additionally, the motion attribute may be compared to one or more motion attributes associated with the authorized users. A determination may be made that the user is an authorized user. As such the user is authorized to utilize functions of the device.

Claims

1. A method in a computing environment utilizing a processor and memory for authenticating a user to a device, the method comprising:

capturing with a depth camera on the device, a first dynamic depth image comprised of geometric information and motion information of a portion of the user from a plurality of angles, the geometric information useable to generate at least a partial three-dimensional representation of the portion of the user;

storing the captured first dynamic depth image in an authorized user attribute repository as an authorized entity;

identifying, with the processor, a first attribute from the geometric information and a second attribute from the motion information;

subsequently, detecting an acceleration of the device from a first position to a second position, by an accelerometer on the device;

upon detection of the acceleration of the device, the accelerometer triggering the depth camera to capture a second dynamic depth image;

receiving at the device, the second dynamic depth image of the portion of the user captured at an angle within the plurality of angles, the second dynamic depth image also comprised of geometric information of the portion of the user and motion information of the portion of the user;

identifying, with the processor, the first attribute from the geometric information and the second attribute from the motion information of the second dynamic depth image;

comparing, with the processor, the first attribute from the geometric information and the second attribute from the motion information of the second dynamic depth image to one or more attributes associated with the authorized entity; and

when the first attribute and the second attribute of the second dynamic depth image are matched to the authorized entity, authorizing the user to utilize one or more functions of the device.

2. The method of claim 1 further comprising instructing a camera to capture the first and second dynamic depth images.

3. The method of claim 1, wherein the camera is functional to capture the first and second dynamic depth images utilizing a human visible light spectrum, a human non-visible light spectrum, or a combination of a human visible light spectrum and a human non-visible light spectrum.

4. The method of claim 1, wherein the first and second dynamic depth images are videos comprised of two or more frames.

5. The method of claim 1, wherein the first and second dynamic depth images are comprised of depth information captured by a depth camera.

6. The method of claim 1, wherein the portion of the user comprises at least one selected from the following:

a hand of the user;

a head of the user;

a torso of the user;

an eye of the user;

a mouth of the user; and

an ear of the user.

7. The method of claim 1, wherein the first attribute represents a size of one or more features captured in the first and second dynamic depth images.

8. The method of claim 1, wherein the motion information is inferred from a change in position of a point on the user from a first frame to a second frame of the first and second dynamic depth images.

9. The method of claim 1, wherein the comparing of the first attribute and the second attribute is further comprised of determining the first attribute and the second attribute are individually comparable to attributes associated with an authorized entity within a predefined confidence level.

10. A handheld device for authenticating a user to the handheld device, the system comprising:

a processor;

an accelerometer;

a depth camera; and

computer storage media having computer-executable instructions embodied thereon, that when executed by the processor, cause the handheld device to perform a method, the method comprising;

(1) capturing, with the depth camera, a series of images for a multi-frame depth image of at least a portion of a head of the user;

(2) identifying a first attribute to be identified from a variety of angles within the series of images;

(3) detecting an acceleration of the device from a first position to a second position;

(4) upon detection of the acceleration of the device, triggering the depth camera to capture an authentication dynamic depth image;

(5) comparing, with the processor, the first attribute identified from the variety of angles within the series of images with the authentication dynamic depth image; and

(6) determining the user is an authorized user of the device based, at least in part, on the first attribute; and

(7) providing a first functionality of the device to the user in response to determining the user is an authorized user.

11. The handheld device of claim 10 further comprising a microphone.

12. The handheld device of claim 10, wherein the method further comprising:

capturing, with the microphone, a verbal input;

identifying a second attribute within the verbal input; and

determining the user is an authorized user of the device based, at least in part on the second input.

13. The handheld device of claim 10, wherein the series of image is comprised of a representation of a mouth of the user as the user mimics speaking one or more words.

14. The handheld device of claim 10, wherein the series of images is comprised of an ear of the user as the handheld device approaches the ear.

15. The handheld device of claim 10, wherein the series of images is comprised of a predefined sequence of facial expressions performed by the user.

16. The handheld device of claim 10, wherein the first attribute is a motion path of a point on the user as captured in the series of images.

17. The handheld device of claim 10, wherein the first attribute is a depth differential between a first point and a second point on the user as captured in the series of images.

18. The handheld device of claim 10, wherein the first attribute is a change in a depth of a point on the user as captured in the series of images.

19. One or more computer storage media devices having computer-executable instructions embodied thereon, that when executed by a computing system having a processor and memory, cause the computing system to perform a method of authenticating a user of a device, the method comprising:

detecting an acceleration of a first device from a first position to a second position, by an accelerometer on the device;

in response to the acceleration of the first device, capturing an image sequence, from a plurality of angles, of a user with a camera coupled with the first device, wherein each image of the image sequence is comprised of depth information;

identifying, with the processor, a first facial gesture in three dimensional space captured in the image sequence;

identifying, with the processor, a second facial gesture captured in three dimensional space in the image sequence;

determining the first facial gesture corresponds with a first authorizing gesture; and

determining, with the processor, the user is an authorized user of a second device.