Biometric authentication techniques

Patent metadata

Field	Value
Publication number	US-12554817-B2
Application number	US-202318521808-A
Country	US
Kind code	B2
Filing date	Nov 28, 2023
Priority date	Aug 1, 2017
Publication date	Feb 17, 2026
Grant date	Feb 17, 2026

Abstract

Techniques are disclosed relating to biometric authentication, e.g., facial recognition. In some embodiments, a device is configured to verify that image data from a camera unit exhibits a pseudo-random sequence of image capture modes and/or a probing pattern of illumination points (e.g., from lasers in a depth capture mode) before authenticating a user based on recognizing a face in the image data. In some embodiments, a secure circuit may control verification of the sequence and/or the probing pattern. In some embodiments, the secure circuit may verify frame numbers, signatures, and/or nonce values for captured image information. In some embodiments, a device may implement one or more lockout procedures in response to biometric authentication failures. The disclosed techniques may reduce or eliminate the effectiveness of spoofing and/or replay attacks, in some embodiments.

First claim

What is claimed is:

1 . A device, comprising:
one or more camera sensors; one or more infrared light emitters configured to emit multiple points of illumination; and one or more processors configured to:
perform a biometric authentication of a user that includes:
determining an illumination pattern for the one or more infrared light emitters to illuminate a biometric of the user;
capturing, via the one or more camera sensors, one or more image frames of the user; and
determining whether to indicate an authentication recognition failure based on determining whether the determined illumination pattern is present in a reflection from the biometric of the user in the one or more image frames.

2 . The device of claim 1 , wherein performing the biometric authentication further includes:
determining a sequence of illumination patterns for the one or more infrared light emitters to illuminate the user; capturing, via the one or more camera sensors, a plurality of image frames of the user; and determining whether to indicate the authentication recognition failure based on determining whether the determined sequence is present in the one or more image frames.

3 . The device of claim 2 , wherein the determined sequence of illumination patterns uses different wavelengths of light.

4 . The device of claim 2 , wherein the determined sequence of illumination patterns uses different intensities of light.

5 . The device of claim 2 , wherein the determined sequence of illumination patterns is a pseudo random sequence.

6 . The device of claim 2 , wherein capturing the plurality of image frames uses differing ones of the camera sensors.

7 . The device of claim 1 , wherein performing the biometric authentication further includes:
assessing depth to the biometric of the user by using the multiple points of illumination projected by the one or more infrared light emitters onto the biometric.

8 . The device of claim 1 , wherein performing the biometric authentication further includes:
determining whether the user is looking at the device during the biometric authentication.

9 . The device of claim 1 , wherein performing the biometric authentication further includes:
using one or more neural networks to compare biometric data captured in the one or more image frames with biometric data of an authorized user.

10 . The device of claim 1 , wherein the one or more camera sensors are configured to send the one or more image frames to the one or more processors via a secure channel.

11 . A method, comprising:
performing, by a device, a biometric authentication of a user that includes:
determining, by the device, an illumination pattern for one or more infrared light emitters of the device to illuminate a biometric of the user, wherein the one or more infrared light emitters are configured to emit multiple points of illumination;
capturing, via one or more camera sensors of the device, one or more image frames of the user; and
determining, by the device, whether to indicate an authentication recognition failure based on determining whether the determined illumination pattern is present in a reflection from the biometric of the user in the one or more image frames.

12 . The method of claim 11 , wherein performing the biometric authentication further includes:
determining a sequence of illumination patterns for the one or more infrared light emitters to illuminate the user, wherein the sequence uses different wavelengths of light or different intensities of light.

13 . The method of claim 11 , wherein the illumination pattern differs from one biometric authentication to another biometric authentication.

14 . The method of claim 11 , wherein performing the biometric authentication further includes:
tracking eye movement of the user in the one or more image frames.

15 . The method of claim 11 , wherein performing the biometric authentication further includes:
projecting, by the one or more infrared light emitters, the multiple points of illumination projected onto the biometric of the user; and assessing depth to the biometric of the user based on the multiple points of illumination captured in the one or more image frames.

16 . A non-transitory computer readable medium having program instructions stored therein that are executable by a device to perform operations comprising:
performing a biometric authentication of a user that includes:
determining an illumination pattern for one or more infrared light emitters of the device to cause the one or more infrared light emitters to emit multiple points of illumination to illuminate a biometric of the user;
capturing, via one or more camera sensors of the device, one or more image frames of the user; and
determining whether to indicate an authentication recognition failure based on determining whether the determined illumination pattern is present in a reflection from the biometric of the user in the one or more image frames.

17 . The computer readable medium of claim 16 , wherein performing the biometric authentication further includes:
determining a sequence of illumination patterns that includes varying wavelengths of light or intensities of light.

18 . The computer readable medium of claim 16 , wherein performing the biometric authentication further includes:
tracking eye movement of the user in the one or more image frames.

19 . The computer readable medium of claim 16 , wherein performing the biometric authentication further includes:
projecting, by the one or more infrared light emitters, the multiple points of illumination projected onto the biometric of the user; and determining multiple depths to the biometric of the user based on the multiple points of illumination captured in the one or more image frames.

20 . The computer readable medium of claim 16 , wherein performing the biometric authentication further includes:
applying one or more neural networks to generate feature vectors of a biometric of an authorized user; and comparing the generated feature vectors with features vectors generated from the one or more image frames.

Assignees

• Apple Inc

Inventors

• Prakash Deepti S
• Ballard Lucia E
• Hauck Jerrold V
• Tang Feng
• Littwin Etai
• Vasu Pavan Kumar Anasosalu
• Littwin Gideon
• Gernoth Thorsten
• Kucerova Lucie
• Kostka Petr
• Hotelling Steven P
• Hirsh Eitan
• Kaitz Tal
• Pokrass Jonathan
• Kolin Andrei
• Laifenfeld Moshe
• Waldon Matthew C
• Mensch Thomas P
• Youngs Lynn R
• Zeleznik Christopher G
• Malone Michael R
• Hendel Ziv
• Krstic Ivan
• Sharma Anup K

Classifications

• H04L9/3231

  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) · CPC title

• H04L9/085

  Secret sharing or secret splitting, e.g. threshold schemes · CPC title

• H04L9/0844

  with user authentication or key authentication, e.g. ElGamal, MTI, MQV-Menezes-Qu-Vanstone protocol or Diffie-Hellman protocols using implicitly-certified keys · CPC title

• G06V40/172

  Classification, e.g. identification · CPC title

• G06V40/166

  using acquisition arrangements · CPC title