IP Library › Granted Patent US 12,494,914
Granted Patent B2
US 12,494,914 · App. 18/126,079 · Granted Dec 9, 2025

System and method for complex confirmation of biometric information without stored biometric data

Inventor: Gilles Mathieu (Peng Chau, HK)
Assignee: Global Bionic Optics Limited
H04L9/3231G06F21/30G06F21/32G06V40/169G06V40/53H04L9/0643H04L9/0866H04L9/3236H04L63/08H04W12/06G06V40/1365G06V40/197G06V40/70H04L2209/04
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,494,914
App. No.
18/126,079
Granted
Dec 9, 2025
Kind
B2
Abstract

A biometric capture is performed to capture multiple regions of a biometric modality of interest, such as regions of a user's face. A complex representation of the user's biometric data is generated, such that each data point within the complex representation is based on biometric information from multiple of the captured regions. Information that later allows reconstruction of the complex representation from another capture of the user's biometric information is stored in a public code that does not include any of the underlying biometric data from the user or information that can be used to derive the underlying biometric data.

Claims (72)

1 . A method for generating a secure biometric code from facial data of a user, comprising:

capturing current samples from a plurality of regions of a face of the user;

combining a first portion of the current samples from a first region of the plurality of regions with a second portion of the current samples from a second region of the plurality of regions;

generating a complex representation of the combined samples, wherein each data point within the complex representation is based on at least the first portion of the current samples and the second portion of the current samples;

acquiring a public code that is based on previously acquired samples of facial data of the user that were acquired prior to the current samples, wherein the public code does not include any of the previously acquired samples of facial data of the user and wherein none of the previously acquired samples of the facial data of the user can be determined based on the public code;

modifying, based on calibration data of the public code, the complex representation of the combined samples to correspond to one or more features of the previously acquired samples of facial data;

binarizing the modified complex representation to generate a binary code; and

generating a witness code based on the binary code;

determining if the witness code matches a previous witness code, wherein the previous witness code is determined from the previously acquired samples of facial data of the user;

recapturing the current samples if the witness code does not match the previous witness code, wherein the combining, generating, modifying, and binarizing steps are repeated for the recaptured current samples; and

determining, based on a bitwise comparison of the binary code with a private code previously determined from the previously acquired samples of facial data of the user, whether the user is authentic.

2 . The method of claim 1 , wherein the samples comprise a plurality of portions; and each portion of the plurality of portions corresponds to a different region of the plurality of regions of the face.

3 . The method of claim 1 , wherein the complex representation is based on all of the first portion of the samples and the second portion of the samples.

4 . The method of claim 3 , wherein a portion of the complex representation corresponding to missing samples is derived from other samples.

5 . The method of claim 1 , wherein modifying the complex representation comprises modifying a phase of the complex representation.

6 . The method of claim 1 , wherein binarizing the modified complex representation comprises assigning binary values based on a complex phase.

7 . The method of claim 6 , wherein binarizing the modified complex representation further comprises hashing the assigned binary values.

8 . The method of claim 1 , wherein binarizing the modified complex representation comprises assigning binary values based on an amplitude of each complex value of the complex representation.

9 . The method of claim 8 , wherein binarizing the modified complex representation further comprises hashing the assigned binary values.

10 . The method of claim 1 , wherein the private code is based on a previously determined complex representation.

11 . The method of claim 1 , wherein:

a timeout occurs if the witness code is not matched with the previous witness code within a period of time; and

the samples are recaptured until the timeout occurs.

12 . The method of claim 1 , wherein the private code is a previous private code, the method further comprising:

receiving a request to revoke the public code;

determining, based on the complex representation, a revised private code; and

generating, based on the revised private code, a new public code.

13 . The method of claim 12 , wherein the new public code identifies portions of the samples that are suitable for bitwise comparison with the revised private code.

14 . The method of claim 1 , further comprising:

acquiring data relating to a non-facial security modality;

generating a binarizing the modified complex representation to generate a binary code; and

determining, based on a bitwise comparison the binary code with a private code previously determined from the previously acquired samples of facial data of the user, whether the user is authentic.

15 . The method of claim 14 , wherein the non-facial security modality comprises a biometric modality.

16 . The method of claim 15 , wherein the non-facial security modality comprises a fingerprint modality.

17 . The method of claim 14 , wherein the non-facial security modality comprises a non-biometric modality.

18 . A biometric processing system, comprising:

a sensor configured to capture facial data from a user;

a memory comprising instructions stored thereon; and

a processor coupled to the sensor and the memory, wherein the processor is configured to execute the instructions to:

capture current samples from a plurality of regions of a face of the user;

combine a first portion of the current samples from a first region of the plurality of regions with a second portion of the current samples from a second region of the plurality of regions;

generate a complex representation of the combined samples, wherein each data point within the complex representation is based on at least the first portion of the current samples and the second portion of the current samples;

acquire a public code that is based on previously acquired samples of facial data of the user that were acquired prior to the current samples, wherein the public code does not include any of the previously acquired samples of facial data of the user and wherein none of the previously acquired samples of the facial data of the user can be determined based on the public code;

modify, based on calibration data of the public code, the complex representation of the combined samples to correspond to one or more features of the previously acquired samples of facial data;

binarize the modified complex representation to generate a binary code;

determine, based on a bitwise comparison of the binary code with a private code previously determined from the previously acquired samples of facial data of the user, whether the user is authentic;

receive a request to revoke the public code;

determine, based on the complex representation, a revised private code; and

generate, based on the revised private code, a new public code.

19 . A non-transitory computer-readable medium having instructions stored thereon, that when executed by a processor of a biometric processing system cause the processor to perform operations comprising:

capturing current samples from a plurality of regions of a face of the user;

combining a first portion of the current samples from a first region of the plurality of regions with a second portion of the current samples from a second region of the plurality of regions;

generating a complex representation of the combined samples, wherein each data point within the complex representation is based on at least the first portion of the current samples and the second portion of the current samples;

acquiring a public code that is based on previously acquired samples of facial data of the user that were acquired prior to the current samples, wherein the public code does not include any of the previously acquired samples of facial data of the user and wherein none of the previously acquired samples of the facial data of the user can be determined based on the public code;

modifying, based on calibration data of the public code, the complex representation of the combined samples to correspond to one or more features of the previously acquired samples of facial data;

binarizing the modified complex representation to generate a binary code; and

generating a witness code based on the binary code;

determining if the witness code matches a previous witness code, wherein the previous witness code is determined from the previously acquired samples of facial data of the user;

recapturing the current samples if the witness code does not match the previous witness code, wherein the combining, generating, modifying, and binarizing steps are repeated for the recaptured current samples; and

determining, based on a bitwise comparison of the binary code with a private code previously determined from the previously acquired samples of facial data of the user, whether the user is authentic.

20 . A method for generating a secure biometric code from facial data of a user, comprising:

capturing current samples from a plurality of regions of a face of the user;

combining a first portion of the current samples from a first region of the plurality of regions with a second portion of the current samples from a second region of the plurality of regions;

generating a complex representation of the combined samples, wherein each data point within the complex representation is based on at least the first portion of the current samples and the second portion of the current samples;

acquiring a public code that is based on previously acquired samples of facial data of the user that were acquired prior to the current samples, wherein the public code does not include any of the previously acquired samples of facial data of the user and wherein none of the previously acquired samples of the facial data of the user can be determined based on the public code;

modifying, based on calibration data of the public code, the complex representation of the combined samples to correspond to one or more features of the previously acquired samples of facial data;

binarizing the modified complex representation to generate a binary code;

determining, based on a bitwise comparison of the binary code with a private code previously determined from the previously acquired samples of facial data of the user, whether the user is authentic;

receiving a request to revoke the public code;

determining, based on the complex representation, a revised private code; and

generating, based on the revised private code, a new public code.

21 . The method of claim 20 , wherein the new public code identifies portions of the samples that are suitable for bitwise comparison with the revised private code.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 21, 2023
From: MATHIEU, GILLES
To: GLOBAL BIONIC OPTICS LIMITED
Reel/Frame 064005/0596 →
Continuity (5)
Continuation In Part 18108328 · Feb 10, 2023
Continuation 16775144 · Jan 28, 2020
Provisional Application 62848463 · May 15, 2019
Provisional Application 62799537 · Jan 31, 2019
Related Publication 20230246839A1 · Aug 3, 2023
References Cited (59)
US 5561718A · Trew et al. · 1996 [cited by applicant]
US 6038315A · Strait et al. · 2000 [cited by applicant]
US 6310966B1 · Dulude et al. · 2001 [cited by applicant]
US 7233686B2 · Hamid · 2007 [cited by applicant]
US 9524420B2 · Suh et al. · 2016 [cited by applicant]
US 9691132B2 · Kim et al. · 2017 [cited by applicant]
US 9935948B2 · Schultz et al. · 2018 [cited by applicant]
US 10826686B1 · Cho et al. · 2020 [cited by applicant]
US 11336857B2 · Okura et al. · 2022 [cited by applicant]
US 11424929B2 · Taylor · 2022 [cited by applicant]
US 11488022B2 · Mallya et al. · 2022 [cited by applicant]
US 11562548B2 · Assouline et al. · 2023 [cited by applicant]
US 11837239B2 · Mallya et al. · 2023 [cited by applicant]
US 11960585B2 · Grover et al. · 2024 [cited by applicant]
US 20030169910A1 · Reisman · 2003 [cited by examiner]
US 20030217294A1 · Kyle · 2003 [cited by applicant]
US 20070226515A1 · Maletsky · 2007 [cited by examiner]
US 20070266427A1 · Kevenaar · 2007 [cited by examiner]
US 20080209227A1 · Venkatesan · 2008 [cited by examiner]
US 20080222496A1 · Tuyls · 2008 [cited by examiner]
US 20090138725A1 · Madhvanath et al. · 2009 [cited by applicant]
US 20090310830A1 · Bolle et al. · 2009 [cited by applicant]
US 20100027784A1 · Tuyls · 2010 [cited by examiner]
US 20150095654A1 · Li et al. · 2015 [cited by applicant]
US 20170085562A1 · Schultz et al. · 2017 [cited by applicant]
US 20170141920A1 · Herder, III · 2017 [cited by examiner]
US 20180365479A1 · Lee · 2018 [cited by examiner]
US 20190215164A1 · Hamann · 2019 [cited by examiner]
US 20210279515A1 · Zhang et al. · 2021 [cited by applicant]
US 20210357761A1 · Mallya et al. · 2021 [cited by applicant]
US 20220029799A1 · Subudhi et al. · 2022 [cited by applicant]
US 20220172416A1 · Kuta et al. · 2022 [cited by applicant]
US 20230009298A1 · Mallya et al. · 2023 [cited by applicant]
US 20230169157A1 · Grover et al. · 2023 [cited by applicant]
US 20230246839A1 · Mathieu · 2023 [cited by applicant]
US 20240045996A1 · O'Bryan et al. · 2024 [cited by applicant]
CN 101340283A · 2009 [cited by applicant]
CN 112699386A · 2021 [cited by applicant]
CN 113298534A · 2021 [cited by applicant]
CN 114144110A · 2022 [cited by applicant]
EP 1385117A2 · 2004 [cited by applicant]
EP 1524620A1 · 2005 [cited by applicant]
KR 20110095638A · 2011 [cited by applicant]
KR 1020190029706A · 2019 [cited by applicant]
KR 1020190041084A · 2019 [cited by applicant]
WO 1998050875A2 · 1998 [cited by applicant]
WO 1999034554A2 · 1999 [cited by applicant]
WO 2006008485A1 · 2006 [cited by applicant]
WO 2019018049A1 · 2019 [cited by applicant]
Dodis, Yevgeniy et al., Fuzzy Extractors, Boston University, Apr. 9, 2008 (Year: 2008). [cited by examiner]
International Search Report and Written Opinion of the International Searching Authority in relation to International Application No. PCT/IB2020/000070, dated Jun. 24, 2020, 8 pages. [cited by applicant]
International Search Report and Written Opinion of the International Searching Authority in relation to International No. PCT/IB2024/052739, dated Jul. 11, 2024, 7 pages. [cited by applicant]
Arakala et al., “Fuzzy Extractors for Minutiae-Based Fingerprint Authentication,” SAT 18th International Conference, 760-769 (2007). [cited by applicant]
International Search Report and Written Opinion from PCT/IB2020/000079 dated Jun. 24, 2020. [cited by applicant]
Ratha et al., “Generating Cancelable Fingerprint Templates,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 29(4):561-572 (2007). [cited by applicant]
Uludag et al., “Securing Fingerprint Template: Fuzzy Vault with Helper Data,” IEEE Computer Vision and Pattern Recognition Workshop, pp. 163-170 (2006). [cited by applicant]
Office action of CN Application CN202080005739.5 dated Nov. 13, 2023 (9 Pages). [cited by applicant]
International search report from European Patent Application No. EP20748661.4 dated Sep. 21, 2022 (9 Pages). [cited by applicant]
International search report from European Patent Application No. EP23214425.3 dated May 27, 2024 (6 pages). [cited by applicant]