System and method for secure five-dimensional user identification

• US 10,713,344 B2
• Filed: 02/19/2019
• Issued: 07/14/2020
• Est. Priority Date: 09/21/2016
• Status: Active Grant

• Current Assignee: Lextron Systems, Inc.
• Original Assignee: Lextron Systems, Inc.
• Inventors: Kikinis, Dan
• Primary Examiner(s): Couso, Jose L
• Application Number:
  US16/279,692
• Publication Number:
  US 20190294771A1
• Time in Patent Office: 511 Days
• CPC Class Codes: G06F 18/00 Pattern recognition
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints
• CPC Class Codes: G06F 21/34 involving the use of external additional devices, e.g. dongles or smart cards
• CPC Class Codes: G06T 1/0007 Image acquisition
• CPC Class Codes: G06T 2207/30201 Face
• CPC Class Codes: G06V 40/165 using facial parts and geometric relationships
• CPC Class Codes: G06V 40/166 using acquisition arrangements
• CPC Class Codes: G06V 40/169 Holistic features and representations, i.e. based on the facial image taken as a whole
• CPC Class Codes: G06V 40/172 Classification, e.g. identification
• CPC Class Codes: G06V 40/174 Facial expression recognition
• CPC Class Codes: G06V 40/176 Dynamic expression
• CPC Class Codes: G06V 40/40 Spoof detection, e.g. liveness detection

Abstract

A method for secure user identification is disclosed, comprising the steps of: creating a first user identification; uniquely associating the user identification with the user; recording, using the identification device, an unknown user'"'"'s head from a range of positions and using illumination in different wavelengths; retrieving a second user identification; and comparing, using the identification device, the second user identification against the recording of the unknown user'"'"'s head and a plurality of measured movements of the unknown user'"'"'s head and hand to identify the unknown user.

Claims

1. A method for secure user identification, comprising:

creating a first user identification, using an identification device comprising at least a processor, a memory, and a plurality of programming instructions stored in the memory and operating on the processor, the identification comprising;

a video recording of a user'"'"'s head, recorded from a range of positions and using illumination in different wavelengths;

a point cloud model of the user'"'"'s head, based on at least a portion of the video recording;

a three-dimensional mesh model of the user'"'"'s head, based on at least a portion of the video recording;

a first motion signature comprising a plurality of head movements measured during the creation of the video recording, the first motion signature being uniquely identifiable to the user; and

a second motion signature comprising a plurality of hand movements measured during the creation of the video recording, the second motion signature being uniquely identifiable to the user;

uniquely associating the user identification with the user,

recording, using the identification device, an unknown user'"'"'s head from a range of positions and using illumination in different wavelengths;

retrieving a second user identification; and

comparing, using the identification device, the second user identification against the recording of the unknown user'"'"'s head and a plurality of measured movements of the unknown user'"'"'s head and hand to identify the unknown user.

2. The method of claim 1, wherein the first motion signature further comprises a plurality of measured micro-movements.

3. The method of claim 1, wherein the second motion signature further comprises measurements collected using a plurality of non-optical hardware sensors operating on the identification device during the creation of the video recording.

4. The method of claim 1, wherein at least a portion of the video recording is recorded using near-infrared illumination, and wherein the near-infrared portion of the recording is used to construct blood vessel maps in three dimensions, and a graph of each section of the face including the eyes is derived, as well as the heart rate and blood oxygen of each section of the face.

5. The method of claim 1, wherein all derived data, signatures, and other recordings are encrypted and stored securely.

6. The method of claim 5, wherein a current reading is compared to a historical one, and an assessment of a match can be made to confirm or deny authenticity of identification.

7. The method of claim 6, wherein the authentication includes verification that the stored data has not been tampered with.

8. The method of claim 1, wherein a body-worn sensor is used to monitor uninterrupted control of the device by the legitimate user.