Biometric aware object detection and tracking

• US 9,679,197 B1
• Filed: 03/13/2015
• Issued: 06/13/2017
• Est. Priority Date: 03/13/2014
• Status: Active Grant

• Current Assignee: Lmi Liquidating Co., LLC
• Original Assignee: Leap Motion Incorporated (Ultraleap Limited)
• Inventors: Sills, Maxwell, Smith, Aaron, He, Hongyuan (Jimmy), Holz, David S.
• Primary Examiner(s): Roz, Mark
• Application Number:
  US14/658,064
• Time in Patent Office: 823 Days
• Field of Search: None
• CPC Class Codes: G06F 3/017 Gesture based interaction, e.g. based on a set of recognized hand gestures interaction based on gestures traced on a digitiser G06F3/04883
• CPC Class Codes: G06V 40/11 Hand-related biometrics; Hand pose recognition
• CPC Class Codes: G06V 40/117 Biometrics derived from hands
• CPC Class Codes: G06V 40/28 Recognition of hand or arm movements, e.g. recognition of deaf sign language static hand signs G06V40/113

Abstract

The technology disclosed can provide methods and systems for identifying users while capturing motion and/or determining the path of a portion of the user with one or more optical, acoustic or vibrational sensors. Implementations can enable use of security aware devices, e.g., automated teller machines (ATMs), cash registers and banking machines, other secure vending or service machines, security screening apparatus, secure terminals, airplanes, automobiles and so forth that comprise sensors and processors employing optical, audio or vibrational detection mechanisms suitable for providing gesture detection, personal identification, user recognition, authorization of control inputs, and other machine control and/or machine communications applications. A virtual experience can be provided to the user in some implementations by the addition of haptic, audio and/or other sensory information projectors.

Claims

1. A method of authorizing commands issued by gestures, the method including:

detecting a set of gestures performed by different users and identifying control gestures in the set of gestures that control responsiveness of one of more virtual objects, including;

capturing a plurality of images of a hand in a three-dimensional (3D) sensory space;

processing one or more of the images to extract biometric features of the hand;

authenticating the hand based on the extracted biometric features;

determining a dominant user from among the users based at least on one or more biometric features extracted of the users;

processing the sequence of the images as a hand gesture;

determining a command indicated by the hand gesture;

determining whether the authenticated hand is authorized to issue the command; and

issuing an authorized command as indicated by the hand gesture triggering a response of the virtual objects to gestures performed by the dominant user without triggering a response to gestures performed by non-dominant users.

2. The method of claim 1, wherein the extracted biometric features include vein patterns of the hand.

3. The method of claim 1, wherein the extracted biometric features include palm prints of the hand.

4. The method of claim 1, wherein the extracted biometric features include fingerprints of the hand.

5. The method of claim 2 further including extracting at least one of:

scars of the hand;

shape of the hand;

size of the hand;

measurements across a palm of the hand;

finger width at a first knuckle of the hand; and

complexion of the hand.

6. The method of claim 1, further including:

using stereo-imaging to capture the plurality of images of the hand.

7. The method of claim 1, further including:

registering multiple images of different poses of the hand during the hand gesture.

8. The method of claim 7, wherein the different poses of the hand include at least one of:

palm view of the hand;

backhand view of the hand; and

closed fist view of the hand.

9. The method of claim 1, further including:

responsive to authenticating the hand based on the extracted biometric features, interpreting subsequent hand gestures based on specific interpretation criteria.

10. The method of claim 1, further including:

issuing the authorized command to a security aware device.

11. The method of claim 1, wherein processing one or more of the images to extract biometric features of the hand further includes:

using at least one image characteristic of the images, determining an image property that specifies changes to the image characteristic across various image points;

determining variations to the image property across the various image points; and

based on the determined variations, identifying points of interest in the images that represent the biometric features.

12. The method of claim 11, further including:

using a Hessian Matrix for determining changes to the image property across the various image points.

13. The method of claim 11, further including:

using eigenvalues and eigenvectors for identifying the points of interest.

14. The method of claim 11, wherein the image characteristic is pixel intensity.

15. The method of claim 11, wherein the image property is gradient of pixel intensity.

16. The method of claim 11, further including:

determining normalized biometric features by at least one of rotating, translating, and scaling the biometric features.

17. The method of claim 11, wherein determining whether the authenticated hand is authorized to issue the command further includes:

comparing the extracted biometric features to a stored biometric profile.

18. The method of claim 17, further including:

constructing a biometric profile based on the extracted biometric features, including;

prompting a user to perform hand gestures in the 3D sensory space and capturing a plurality of images of the hand during the hand gestures;

processing one or more of the images to extract biometric features of the hand;

determining normalized biometric features by at least one of rotating, translating, and scaling the biometric features;

registering multiple images of different poses of the hand during the hand gestures; and

storing the normalized biometric features and corresponding poses for recognizing gestures.

19. The method of claim 1, determining whether the authenticated hand is authorized to issue the command further includes:

determining whether a user who performs the hand gesture has a role authorized to issue the command.

20. The method of claim 1, wherein a biometric profile is constructed at a first device and an authorized command is issued to a second device.

21. The method of claim 1, further including:

detecting another hand gesture in the 3D sensory space;

verifying hand continuity by comparing biometric features of a hand captured during the another hand gesture with biometric features of the hand captured previously; and

repudiating authentication of the hand responsive to a lack of verification of the hand continuity.

22. The method of claim 1, wherein the hand gesture is at least one of:

an upward swiping gesture;

a downward swiping gesture;

a rotating gesture; and

a grasping gesture.

23. The method of claim 1, further including:

distinguishing control gestures from proximate non-control gestures in a virtually augmented real environment, by;

detecting the set of gestures performed by different users in a virtually augmented real environment; and

identifying control gestures in the set of gestures that control responsiveness of the one of more virtual objects superimposed over a real environment.

26. A system implementing the method of claim 1, the system including:

a processor and a computer readable storage medium storing computer instructions configured to cause the processor to detect a set of gestures performed by different users and identifying control gestures in the set of gestures that control responsiveness of one of more virtual objects, including;

capture a plurality of images of a hand in a three-dimensional (3D) sensory space;

process one or more of the images to extract biometric features of the hand;

authenticate the hand based on the extracted biometric features;

determine a dominant user from among the users based at least on one or more biometric features extracted of the users;

process a sequence of the images as a hand gesture;

determine a command indicated by the hand gesture;

determine whether the authenticated hand is authorized to issue the command; and

issue an authorized command as indicated by the hand gesture triggering a response of the virtual objects to gestures performed by the dominant user without triggering a response to gestures performed by non-dominant users.

27. One or more non-transitory computer readable media having instructions stored thereon to detect a set of gestures performed by different users and identifying control gestures in the set of gestures that control responsiveness of one of more virtual objects, which when executed by one or more processors performs the method of claim 1, the method including:

capture a plurality of images of a hand in a three-dimensional (3D) sensory space;

process one or more of the images to extract biometric features of the hand;

authenticate the hand based on the extracted biometric features;

determine a dominant user from among the users based at least on one or more biometric features extracted of the users;

process a sequence of the images as a hand gesture;

determine a command indicated by the hand gesture;

determine whether the authenticated hand is authorized to issue the command; and

issue an authorized command as indicated by the hand gesture triggering a response of the virtual objects to gestures performed by the dominant user without triggering a response to gestures performed by non-dominant users.

24. An automated teller machine (ATM) system, including:

a motion-capture program executing on a processor of an automated teller machine (ATM) for detecting a set of gestures performed by different users and identifying control gestures in the set of gestures that control responsiveness of one of more virtual objects, including capturing a plurality of images of a hand in a three-dimensional (3D) sensory space;

a biometric processing module for processing one or more of the images to extract biometric features of the hand; and

a command authorization module for authenticating the hand based on the extracted biometric features to determine a dominant user from among the users based at least on one or more biometric features extracted of the users, including;

processing a sequence of the images as a hand gesture;

determining a command indicated by the hand gesture;

determining whether the authenticated hand is authorized to issue the command; and

issuing an authorized command to the ATM as indicated by the hand gesture triggering a response of the virtual objects to gestures performed by the dominant user without triggering a response to gestures performed by non-dominant users.

25. The automated teller machine system of claim 24, wherein the authorized command controls a session manager of the ATM using a virtual object that effects transactions.

28. A system implementing distinguishing control gestures made by an authorized user from motions or gestures made by non-dominant hands, the system including:

a processor and a computer readable storage medium storing computer instructions configured to cause the processor to;

detect a set of gestures performed by different users in a virtually augmented real environment and identify control gestures in the set of gestures that control responsiveness of one of more virtual objects superimposed over a real environment by;

capturing a plurality of images of at least one hand of a plurality of hands moving in a three-dimensional (3D) sensory space;

processing one or more of the images to extract biometric features of the hand;

authenticating the hand based on the extracted biometric features;

determining a dominant user from among the users based at least on one or more biometric features of the users;

processing the sequence of the images as a hand gesture;

determining a command indicated by the hand gesture;

determining whether the authenticated hand is authorized to issue the command; and

issuing an authorized command as indicated by the hand gesture triggering a response of the virtual objects to gestures performed by the dominant user without triggering a response to gestures performed by non-dominant users.

29. One or more non-transitory computer readable media having instructions stored thereon to distinguishing control gestures made by an authorized user from motions or gestures made by non-dominant hands, which instructions when executed by one or more processors, implement, a method including:

detecting a set of gestures performed by different users in a virtually augmented real environment and identifying control gestures in the set of gestures that control responsiveness of one of more virtual objects superimposed over the real environment by;

capturing a plurality of images of at least one hand of a plurality of hands moving in a three-dimensional (3D) sensory space;

processing one or more of the images to extract biometric features of the hand; and

authenticating the hand based on the extracted biometric features;

determining a dominant user from among the users based at least on one or more biometric features of the users;

processing the sequence of the images as a hand gesture;

determining a command indicated by the hand gesture;

determining whether the authenticated hand is authorized to issue the command; and

issuing an authorized command as indicated by the hand gesture triggering a response of the virtual objects to gestures performed by the dominant user without triggering a response to gestures performed by non-dominant users.