IP Library › Granted Patent US 12,340,622
Granted Patent B2
US 12,340,622 · App. 18/514,497 · Granted Jun 24, 2025

Increasing a false positive identification rate of a face recognition algorithm by altering a value of an image classification feature associated with the face recognition algorithm

Inventors: Annika P. Singh (Austin, TX); Arati P. Singh (Austin, TX)
Assignee: Dauntless Labs, LLC
G06V40/172
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 12,340,622
App. No.
18/514,497
Granted
Jun 24, 2025
Kind
B2
Abstract

Systems and methods for increasing a false positive identification rate of a face recognition algorithm are provided. A method includes using a first image sensor, acquiring image data for a first facial image of a person and selecting an application profile for the first facial image. The application profile is selected to modify the image data to alter a value of an image classification feature used by a face recognition algorithm to increase a false positive identification rate of the face recognition algorithm that is configured to match an input facial image with at least one of N stored facial images. The method further includes, modifying an aspect associated with the face of the person, such that a second facial image of the face, when acquired by a second image sensor subsequent to the modification of the aspect, is different from the first facial image.

Claims (28)

1. A method comprising:

using a first image sensor, acquiring image data for a first facial image of a person;

selecting an application profile for the first facial image, wherein the application profile is selected to alter a value of at least one image classification feature used by a face recognition algorithm in order to increase a false positive identification rate of the face recognition algorithm that is configured to match an input facial image with at least one of N stored facial images, wherein N is greater than 1,000; and

based on the selected application profile, modifying an aspect associated with the face of the person, such that a second facial image of the face, when acquired by a second image sensor subsequent to the modification of the aspect, is different from the first facial image acquired by the first image sensor.

2. The method of claim 1 , wherein the application profile comprises a cosmetic application profile.

3. The method of claim 2 , wherein the aspect associated with the face of the person comprises cosmetic applied to the face of the person.

4. The method of claim 3 , further comprising, by processing the selected cosmetic application profile, generating a set of values corresponding to a magnetic field pattern for use with a magnetic field applicator and transmitting the set of values to the magnetic field applicator.

5. The method of claim 4 , further comprising, using the magnetic field applicator, based on the set of values, applying magnetic fields to nanoparticles embedded in the cosmetic applied to the face of the person.

6. The method of claim 5 , wherein the nanoparticles include metallic molecules, and wherein the nanoparticles include melanin molecules attached to the metallic molecules.

7. The method of claim 1 , further automatically selecting the application profile based on a location of the person.

8. A method comprising:

based on a location of a person, automatically selecting an application profile for a first facial image of the person acquired using a first image sensor, wherein the application profile is selected to alter a value of at least one image classification feature used by a face recognition algorithm in order to increase a false positive identification rate of the face recognition algorithm that is configured to match an input facial image with at least one of N stored facial images, wherein N is greater than 1,000;

based on the selected application profile, modifying an aspect associated with the face of the person, such that a second facial image of the face, when acquired by a second image sensor subsequent to the modification of the aspect, is different from the first facial image acquired by the first image sensor.

9. The method of claim 8 , wherein the application profile comprises a cosmetic application profile.

10. The method of claim 9 , wherein the aspect associated with the face of the person comprises cosmetic applied to the face of the person.

11. The method of claim 10 , wherein the cosmetic includes diffractive pigments capable of producing a variation in color based on an angle of observation when hit by visible light.

12. The method of claim 10 , wherein the cosmetic includes reflective particles.

13. The method of claim 10 , wherein the cosmetic includes composite pigments including a magnetic core and a coating of an organic coloring substance.

14. A method comprising:

using a first image sensor, acquiring image data for a first facial image of a person;

selecting an application profile for the first facial image, wherein the application profile is selected to alter a value of at least one image classification feature used by a face recognition algorithm in order to increase a false positive identification rate of the face recognition algorithm that is configured to match an input facial image with at least one of N stored facial images, wherein N is greater than 1,000; and

based on the selected application profile, modifying an appearance of cosmetic applied to the face of the person, such that a second facial image of the face, when acquired by a second image sensor subsequent to the modification of the appearance of the cosmetic, is different from the first facial image acquired by the first image sensor.

15. The method of claim 14 , wherein the application profile comprises a cosmetic application profile.

16. The method of claim 15 , further comprising, by processing the selected cosmetic application profile, generating a set of values corresponding to a magnetic field pattern for use with a magnetic field applicator and transmitting the set of values to the magnetic field applicator.

17. The method of claim 16 , further comprising, using the magnetic field applicator, based on the set of values, applying magnetic fields to nanoparticles embedded in the cosmetic applied to the face of the person.

18. The method of claim 17 , wherein the nanoparticles include metallic molecules, and wherein the nanoparticles include melanin molecules attached to the metallic molecules.

19. The method of claim 14 , wherein the cosmetic includes at least one of diffractive pigments capable of producing a variation in color based on an angle of observation when hit by visible light or reflective particles.

20. The method of claim 14 , wherein the cosmetic includes composite pigments including a magnetic core and a coating of an organic coloring substance.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 20, 2023
From: SINGH, ANNIKA P.; SINGH, ARATI P.
To: DAUNTLESS LABS, LLC
Reel/Frame 065622/0047 →
Continuity (2)
Continuation 18474750 · Sep 26, 2023
Related Publication 20250104471A1 · Mar 27, 2025
References Cited (36)
US 7724171B2 · Lee · 2010 [cited by examiner]
US 8194938B2 · Wechsler · 2012 [cited by examiner]
US 10755447B2 · Chhaya · 2020 [cited by examiner]
US 10993905B2 · Fisas Verges · 2021 [cited by examiner]
US 11178956B1 · Prout · 2021 [cited by examiner]
US 11837019B1 · Singh · 2023 [cited by examiner]
US 20100243514A1 · Samain · 2010 [cited by examiner]
US 20100252061A1 · Samain · 2010 [cited by examiner]
US 20120017929A1 · Samain · 2012 [cited by examiner]
US 20120044335A1 · Goto · 2012 [cited by examiner]
US 20120223956A1 · Saito · 2012 [cited by examiner]
US 20130160785A1 · Thevenet · 2013 [cited by examiner]
US 20140004275A1 · Yin · 2014 [cited by examiner]
US 20150049924A1 · Tang · 2015 [cited by examiner]
US 20160110587A1 · Han · 2016 [cited by examiner]
US 20170076474A1 · Fu · 2017 [cited by examiner]
US 20170358116A1 · Cheng · 2017 [cited by examiner]
US 20180075524A1 · Sartori Odizzio · 2018 [cited by examiner]
US 20180276453A1 · Takei · 2018 [cited by examiner]
US 20190325616A1 · Chhaya · 2019 [cited by examiner]
US 20190347832A1 · Nishi · 2019 [cited by examiner]
US 20190362134A1 · Kim · 2019 [cited by examiner]
US 20200026906A1 · Ajiki · 2020 [cited by examiner]
US 20200134371A1 · Charraud · 2020 [cited by examiner]
US 20210004569A1 · Zhao · 2021 [cited by examiner]
US 20210397863A1 · Kose Cihangir · 2021 [cited by examiner]
US 20220180485A1 · Chen · 2022 [cited by examiner]
US 20220211163A1 · Yang · 2022 [cited by examiner]
US 20220319064A1 · Yeh · 2022 [cited by examiner]
US 20230180917A1 · Si · 2023 [cited by examiner]
US 20230230325A1 · Lin · 2023 [cited by examiner]
US 20230260167A1 · Mao · 2023 [cited by examiner]
Banerjee et al., “MakeUpMirror: mirroring make-ups and verifying faces post make-up”, IET Biometrics, 2018, vol. 7, Iss. 6, pp. 598-605 (Year: 2018). [cited by examiner]
Chen et al., “Spoofing Faces Using Makeup: An Investigative Study”, IEEE (Year: 2017). [cited by examiner]
Rathgeb et al., “Detection of Makeup Presentation Attacks based on Deep Face Representations”, 2020 25th International Conference on Pattern Recognition (ICPR) Milan, Italy, Jan. 10-15, 2021 (Year: 2021). [cited by examiner]
Chen et al., “Automatic Facial Makeup Detection with Application in Face Recognition”, IEEE (Year: 2013). [cited by examiner]