Granted Patent B2

US 12,482,287 · App. 17/579,445 · Granted Nov 25, 2025

Inventor: Adrian Kaehler (Los Angeles, CA)

Assignee: MAGIC LEAP, INC.

G06V30/413G06F18/2148G06F18/22G06T19/006G06V20/20G06V40/171G06V40/172

Abstract

Claims (84)

1 . A method for verifying an identity of a person using an augmented reality (AR) system, the method comprising:

under control of the AR system comprising computer hardware, the AR system comprising:

an outward-facing camera configured to image an environment, and

an optical sensor configured to emit light outside of a human visible spectrum:

obtaining, with the outward-facing camera, an image of the environment;

identifying a first biometric information associated with a person based at least partly on an analysis of the image of the environment;

identifying a second biometric information in a first document presented by the person to the outward facing camera;

identifying a third biometric information in a second document presented by the person to the outward facing camera; and

determining a first match between the first biometric information with the second biometric information;

determining, upon the determination of the first match, a second match between at least one of the first biometric information or the second biometric information with the third biometric information.

2 . The method of claim 1 , wherein the light emitted by the optical sensor comprises ultraviolet light.

3 . The method of claim 1 , wherein the first biometric information or the second biometric information comprises one or more of the following: a fingerprint, a height, a gender, a hair color, or a weight.

4 . The method of claim 1 , wherein identifying the first biometric information and identifying the second biometric information comprise:

detecting a first face in the image, wherein the first face comprises first facial features and is associated with the person; and

detecting a second face in the image, wherein the second face comprises second facial features and is included in the document presented by the person,

wherein determining the match comprises:

calculating a first feature vector for the first face the based at least partly on the first facial features or calculating a second feature vector for the second face based at least partly on the second facial features, respectively;

calculating a distance between the first feature vector and the second feature vector;

comparing the distance to a threshold value; and

confirming the match when the distance passes the threshold value, wherein calculating the first feature vector or calculating the second feature vector is implemented using one or more of the following: a facial landmark detection algorithm, a deep neural network algorithm, or a template matching algorithm.

5 . The method of claim 1 , wherein identifying the first biometric information and identifying the second biometric information comprise:

detecting a first face in the image, wherein the first face comprises first facial features and is associated with the person; and

detecting a second face in the image, wherein the second face comprises second facial features and is included in the document presented by the person,

wherein determining the match comprises:

calculating a first feature vector for the first face based at least partly on the first facial features or calculating a second feature vector for the second face based at least partly on the second facial features, respectively;

calculating a distance between the first feature vector and the second feature vector;

comparing the distance to a threshold value; and

confirming the match when the distance passes the threshold value.

6 . The method of claim 1 , wherein identifying the first biometric information and identifying the second biometric information comprise:

detecting a first face in the image, wherein the first face comprises first facial features and is associated with the person; and

detecting a second face in the image, wherein the second face comprises second facial features and is included in the document presented by the person,

wherein detecting the first face or detecting the second face comprises locating the first face or the second face in the image using at least one of the following: a wavelet-based boosted cascade algorithm or a deep neural network algorithm.

7 . The method of claim 1 , wherein identifying the first biometric information and identifying the second biometric information comprise:

detecting a first face in the image, wherein the first face comprises first facial features and is associated with the person;

detecting a second face in the image, wherein the second face comprises second facial features and is included in the document presented by the person; and

assigning first weights to the first facial features based at least partly on locations of the respective first facial features, or assigning second weights to second facial features based at least partly on locations of the respective second facial features.

8 . The method of claim 1 , wherein identifying the first biometric information and identifying the second biometric information comprise:

detecting a first face in the image, wherein the first face comprises first facial features and is associated with the person; and

detecting a second face in the image, wherein the second face comprises second facial features detected in a photograph within the document presented by the person to the outward facing camera of the AR system from the image captured by the outward facing camera in which the first biometric information is identified.

9 . The method of claim 1 , wherein identifying the second information comprises:

emitting a light, by the optical sensor, onto the document presented by the person to the outward facing camera of the AR system,

wherein the light is outside the human visible spectrum; and

identifying the information under the light emitted by the optical sensor, wherein the second information is not directly visible when illuminated with light within the human visible spectrum.

10 . The method of claim 1 , wherein identifying the second information comprises:

identifying a label in the document presented by the person to the outward facing camera of the AR system, wherein the label contains encoded biometric information; and

retrieving decoded biometric information based at least partly on the analysis of the label,

wherein retrieving decoded biometric information comprises retrieving biometric information from a data source other than the image of the environment.

11 . The method of claim 1 , wherein identifying the second information comprises: identifying a label in the document presented by the person to the outward facing camera of the AR system, wherein the label contains encoded biometric information; and retrieving decoded biometric information based at least partly on the analysis of the label.

12 . The method of claim 1 , further comprising a virtual annotation indicating a result of the determination of the match between the first biometric with the second biometric information.

13 . An augmented reality (AR) system comprising:

an outward-facing camera, configured to image an environment;

an optical sensor configured to emit light outside of a human visible spectrum; computer hardware configured to perform operations comprising:

under control of the AR system comprising computer hardware, the AR system comprising an outward-facing camera configured to image an environment and an optical sensor:

obtaining, with the outward-facing camera, an image of the environment;

identifying a first face as first biometric information associated with a person based at least partly on an analysis of the image of the environment;

identifying a second face as second biometric information in a photograph on a document presented by the person to the outward facing camera of the AR system and extracted based at least partly on an analysis of the image of the environment from which the first biometric information is identified, wherein the photograph is only visible under the light outside of the human visible spectrum; and

determining a match between the first biometric information with the second biometric information.

14 . The AR system of claim 13 , wherein the first biometric information or the second biometric information further comprises an iris code.

15 . The AR system of claim 13 ,

wherein determining the match comprises:

calculating a first feature vector for the first face the based at least partly on first facial features of the first face or calculating a second feature vector for the second face based at least partly on second facial features of the second face, respectively;

calculating a distance between the first feature vector and the second feature vector;

comparing the distance to a threshold value; and

confirming the match when the distance passes the threshold value, wherein calculating the first feature vector or calculating the second

feature vector is implemented using one or more of the following: a facial landmark detection algorithm, a deep neural network algorithm, or a template matching algorithm.

16 . The AR system of claim 13 ,

wherein determining the match comprises:

calculating a first feature vector for the first face based at least partly on first facial features of the first face or calculating a second feature vector for the second face based at least partly on second facial features of the second face, respectively;

calculating a distance between the first feature vector and the second feature vector;

comparing the distance to a threshold value; and

confirming the match when the distance passes the threshold value.

17 . The AR system of claim 13 , wherein identifying the first biometric information and identifying the second biometric information comprise:

wherein the identifying the first face or the identifying the second face comprises locating the first face or the second face in the image using at least one of the following: a wavelet-based boosted cascade algorithm or a deep neural network algorithm.

18 . The AR system of claim 13 , wherein identifying the first biometric information and identifying the second biometric information comprise:

wherein the first face comprises first facial features;

wherein the second face comprises second facial features; and

assigning first weights to the first facial features based at least partly on locations of the respective first facial features, or assigning second weights to second facial features based at least partly on locations of the respective second facial features.

19 . The AR system of claim 13 , wherein identifying the second information comprises:

emitting a light onto the document presented by the person to the outward facing camera of the AR system,

wherein the light is outside the human visible spectrum; and

identifying the information under the light outside the human visible spectrum, wherein the second information is not directly visible in the absence of light outside of the human visible spectrum.

20 . The AR system of claim 13 , wherein the photograph is a first photograph only visible under the light outside of the visible spectrum, and

wherein computer hardware is further configured to perform operations comprising, under control of the AR system: identifying a second face as third biometric information associated with a person based on a second photograph associated with the person based at least partly on the analysis of the image of the environment, wherein the second photograph is visible under light within the human visible spectrum; and

wherein the determining the match further includes determining a further match between the first biometric information or the second biometric information with the third biometric information.

Assignments (2)

Continuity (4)

References Cited (137)