IP Library Granted Patent US 12,322,201
Granted Patent B2
US 12,322,201 · App. 17/553,666 · Granted Jun 3, 2025

Digital imaging systems and methods of analyzing pixel data of an image of a skin area of a user for determining skin hyperpigmentation

Inventors: Leigh Knight (Reading, GB); Robyn Dolbear (Reading, GB); Rachel Russell (Reading, GB); Kate Budds (Reading, GB); Katie Wilson (Reading, GB)
Assignee: The Gillette Company LLC
G06V40/10G06Q30/0631G06T7/70G06T11/00G06Q10/083G06T2207/20081
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 12,322,201
App. No.
17/553,666
Granted
Jun 3, 2025
Kind
B2
Abstract

Digital imaging systems and methods are described for analyzing pixel data of an image of a skin area of a user for determining skin hyperpigmentation. A plurality of training images of a plurality of individuals are aggregated, each of the training images comprising pixel data of a respective skin area of an individual. A skin hyperpigmentation model, trained with the pixel data, is operable to output, across a range of a skin hyperpigmentation scale, skin hyperpigmentation values associated with a degree of skin hyperpigmentation. An image of a user comprising pixel data of at least a portion of a user skin area is received and analyzed, by the skin hyperpigmentation model, to determine a user-specific skin hyperpigmentation value of the user skin area. A user-specific electronic recommendation addressing at least one feature identifiable within the pixel data is generated and rendered, on a display screen of a user computing device.

Claims (31)

1. A digital imaging method of analyzing pixel data of an image of a skin area of a user for determining skin hyperpigmentation, the digital imaging method comprising the steps of:

a. aggregating, at one or more processors communicatively coupled to one or more memories, a plurality of training images of a plurality of individuals, each of the training images comprising pixel data of a skin area of a respective individual;

b. training, by the one or more processors with the pixel data of the plurality of training images, a skin hyperpigmentation model comprising a skin hyperpigmentation scale and operable to output, across a range of the skin hyperpigmentation scale, skin hyperpigmentation values associated with a degree of skin hyperpigmentation ranging from least hyperpigmentation to most hyperpigmentation;

c. receiving, at the one or more processors, at least one image of a user, the at least one image captured by a digital camera, and the at least one image comprising pixel data of at least a portion of a user skin area of the user;

d. analyzing, by the skin hyperpigmentation model executing on the one or more processors, the at least one image captured by the digital camera to determine a user-specific skin hyperpigmentation value of the user skin area;

e. generating, by the one or more processors based on the user-specific skin hyperpigmentation value, at least one user-specific electronic recommendation designed to address at least one feature identifiable within the pixel data comprising the at least the portion of the user skin area;

f. receiving, at the one or more processors, a new image of the user, the new image captured by the digital camera, and the new image comprising pixel data of at least a portion of a user skin area of the user;

g. analyzing, by the skin hyperpigmentation model executing on the one or more processors, the new image captured by the digital camera to determine a new user-specific skin hyperpigmentation value of the user skin area;

h. generating, based on the new user-specific skin hyperpigmentation value, a new user-specific electronic recommendation or comment regarding at least one feature identifiable within the pixel data of the new image; and

rendering, on a display screen of a user computing device, the at least one user-specific recommendation;

wherein a delta user-specific skin hyperpigmentation value is generated based on a comparison between the new user-specific skin hyperpigmentation value and the user-specific skin hyperpigmentation value, wherein the new user-specific recommendation or comment is further based on the delta user-specific skin hyperpigmentation value, and wherein the delta user-specific skin hyperpigmentation value, a representation of the delta user-specific skin hyperpigmentation value, or a comment based on the delta user-specific skin hyperpigmentation value, is rendered on the display screen of the user computing device.

2. The digital imaging method of claim 1 , wherein the at least one user-specific electronic recommendation is displayed on the display screen of the user computing device with a graphical representation of the user's skin as annotated with one or more graphics or textual renderings corresponding to the user-specific skin hyperpigmentation value.

3. The digital imaging method of claim 1 , wherein the at least one user-specific electronic recommendation is rendered in real-time or near-real time, during, or after receiving the at least one image having the user skin area.

4. The digital imaging method of claim 1 , wherein the at least one user-specific electronic recommendation comprises a product recommendation for a manufactured product.

5. The digital imaging method of claim 4 , wherein the at least one user-specific electronic recommendation is displayed on the display screen of the user computing device with instructions for treating, with the manufactured product, the at least one feature identifiable in the pixel data comprising the at least the portion of the user skin area.

6. The digital imaging method of claim 4 , further comprising the steps of:

initiating, based on the product recommendation, the manufactured product for shipment to the user.

7. The digital imaging method of claim 4 , further comprising the steps of:

generating, by the one or more processors, a modified image based on the at least one image, the modified image depicting how the user's skin is predicted to appear after treating the at least one feature with the manufactured product; and

rendering, on the display screen of the user computing device, the modified image.

8. The digital imaging method of claim 1 , wherein the at least one user-specific electronic recommendation is displayed on the display screen of the user computing device with instructions for treating the at least one feature identifiable in the pixel data comprising the at least the portion of the user skin area.

9. The digital imaging method of claim 1 , wherein the skin hyperpigmentation model is an artificial intelligence (AI) based model trained with at least one AI algorithm.

10. The digital imaging method of claim 1 ,

wherein the skin hyperpigmentation model is further trained, by the one or more processors with the pixel data of the plurality of training images, to output one or more location identifiers indicating one or more corresponding body area locations of respective individuals, and

wherein the skin hyperpigmentation model, executing on the one or more processors and analyzing the at least one image of the user, determines a location identifier indicating a body area location of the user skin area.

11. The digital method of claim 10 , wherein the body area location comprises the user's cheek, the user's neck, the user's head, the user's groin, the user's underarm, the user's chest, the user's back, the user's leg, the user's arm, or the user's bikini area.

12. The digital method of claim 1 , wherein training, by the one or more processors with the pixel data of the plurality of training images, the skin hyperpigmentation model comprises training the skin hyperpigmentation model to detect a darker amount of skin from a body area location of the user to determine the user-specific skin hyperpigmentation value of the user skin area.

13. The digital method of claim 1 , wherein training, by the one or more processors with the pixel data of the plurality of training images, the skin hyperpigmentation model comprises training the skin hyperpigmentation model to detect a darker amount of skin within the skin area to determine the user-specific skin hyperpigmentation value of the user skin area.

14. The digital method of claim 1 , wherein training, wherein training, by the one or more processors with the pixel data of the plurality of training images, the skin hyperpigmentation model comprises training the skin hyperpigmentation model to detect a dark amount of skin from a body area location of the user within the skin area to determine the user-specific skin hyperpigmentation value of the user skin area.

15. The digital imaging method of claim 1 , wherein a delta user-specific skin hyperpigmentation value is generated based on a comparison between the new user-specific skin hyperpigmentation value and the user-specific skin hyperpigmentation value, wherein the new user-specific recommendation comprises a recommendation of a hair removal product or hair removal technique for the user corresponding to the delta user-specific skin hyperpigmentation value.

16. The digital method of claim 1 , wherein the user computing device receives the at least one image the user-specific recommendation on the display screen of the user computing device.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 16, 2022
From: KNIGHT, LEIGH; DOLBEAR, ROBYN; RUSSELL, RACHEL; BUDDS, KATE; WILSON, KATIE
To: THE GILLETTE COMPANY LLC
Reel/Frame 059025/0621 →
Continuity (1)
Related Publication 20230196816A1 · Jun 22, 2023
References Cited (79)
US 10818007B2 · Purwar et al. · 2020 [cited by applicant]
US 11901080B1 · Matt · 2024 [cited by applicant]
US 11908128B2 · Jiang · 2024 [cited by applicant]
US 11998334B2 · Berthier · 2024 [cited by applicant]
US 20030065578A1 · Peyrelevade et al. · 2003 [cited by applicant]
US 20040264750A1 · Znaiden et al. · 2004 [cited by applicant]
US 20080194928A1 · Bandic · 2008 [cited by applicant]
US 20100185064A1 · Bandic et al. · 2010 [cited by applicant]
US 20120314920A1 · Prigent · 2012 [cited by examiner]
US 20140323873A1 · Cummins · 2014 [cited by applicant]
US 20170270593A1 · Sherman et al. · 2017 [cited by applicant]
US 20180033205A1 · Kong et al. · 2018 [cited by applicant]
US 20180350071A1 · Purwar · 2018 [cited by applicant]
US 20190213453A1 · Ludwinski · 2019 [cited by examiner]
US 20190237194A1 · Salvi et al. · 2019 [cited by applicant]
US 20200042769A1 · Yan et al. · 2020 [cited by applicant]
US 20200170564A1 · Jiang et al. · 2020 [cited by applicant]
US 20200250404A1 · Shinoda · 2020 [cited by applicant]
US 20200342594A1 · Dissanayake · 2020 [cited by applicant]
US 20210012493A1 · Jiang et al. · 2021 [cited by applicant]
US 20210142111A1 · Yao · 2021 [cited by applicant]
US 20210142890A1 · Adiri et al. · 2021 [cited by applicant]
US 20210174965A1 · Thubagere Jagadeesh · 2021 [cited by examiner]
US 20210182705A1 · Bates · 2021 [cited by applicant]
US 20210286975A1 · Sun · 2021 [cited by examiner]
US 20220019765A1 · Yao · 2022 [cited by applicant]
US 20220051409A1 · Maclellan · 2022 [cited by examiner]
US 20220224876A1 · Matts et al. · 2022 [cited by applicant]
US 20220237751A1 · Bradley · 2022 [cited by examiner]
US 20220237811A1 · Cai · 2022 [cited by examiner]
US 20220309668A1 · Swart · 2022 [cited by examiner]
US 20220344044A1 · Yoo · 2022 [cited by applicant]
US 20220359062A1 · Dunn · 2022 [cited by applicant]
US 20230001593A1 · Palero · 2023 [cited by applicant]
US 20230029766A1 · Jay · 2023 [cited by examiner]
US 20230074782A1 · Tendulkar · 2023 [cited by applicant]
US 20230077452A1 · Cardelino · 2023 [cited by applicant]
US 20230116487A1 · Tendulkar · 2023 [cited by applicant]
US 20230255544A1 · Goyal · 2023 [cited by examiner]
US 20240148999A1 · Hartono · 2024 [cited by applicant]
CN 110298815A · 2019 [cited by applicant]
CN 111428552A · 2020 [cited by applicant]
CN 111985458A · 2020 [cited by applicant]
CN 112084965A · 2020 [cited by applicant]
CN 112541394A · 2021 [cited by applicant]
CN 113298841A · 2021 [cited by applicant]
CN 113610844A · 2021 [cited by applicant]
EP 3816932A1 · 2021 [cited by applicant]
EP 3933774A1 · 2022 [cited by applicant]
EP 3933851A1 · 2022 [cited by applicant]
KR 102135874B1 · 2020 [cited by applicant]
WO 0233628A2 · 2002 [cited by applicant]
PCT Search Report and Written Opinion for PCT/US2022/079873 dated Mar. 22, 2023, 12 pages. [cited by applicant]
Hsia Chih-Hsien et al: “System for Recommending Facial Skincare Products”, Sensors and Materials, vol. 32, No. 10, Oct. 9, 2020, pp. 3235-3242. [cited by applicant]
Kohli Indermeet et al: “Quantitative measurement of skin surface oiliness and shine using differential polarized images”, Archives of Dermatological Research, vol. 313, No. 2, Apr. 8, 2020, pp. 71-77. [cited by applicant]
Kothari Arya et al: “Cosmetic Skin Type Classification Using CNN With Product Recommendation”, 2021 12th International Conference on Computing Communication and Networking Technologies (ICCCNT), Jul. 6-8, 2021, 6 pages. [cited by applicant]
Li Hsiao-Hui et al: “Based on machine learning for personalized skin care products recommendation engine”, 2020 International Symposium on Computer, Consumer and Control (IS3C), Nov. 13, 2020, 3 pages. [cited by applicant]
Mueller Willem: “DeepSkin: Mobile-Based Skin Quality Assessment with Deep Learning”, Aug. 31, 2020, 180 pages. [cited by applicant]
Nissa Farhan Novia et al: “Application of Deep Learning Using Convolutional Neural Network (CNN) Method for Women's Skin Classification”, Scientific Journal of Informatics, vol. 8, No. 1, May 2021, pp. 144-153. [cited by applicant]
Pierrard Jean-Sebastien et al: “Skin Detail Analysis for Face Recognition”, 2007 IEEE Conference on Computer Vision and Pattern Recognition, Jun. 1, 2007, 8 pages. [cited by applicant]
Tianxing Li et al: “Lightweight Real-time Makeup Try-on in Mobile Browsers with Tiny CNN Models for Facial Tracking”, Arxiv.Org, Cornell University Library, Jun. 5, 2019, 4 pages. [cited by applicant]
Min Chen et al. “AI-Skin: Skin disease recognition based on self-learning and wide data collection through a closed-loop framework”, Information Fusion 54, Jun. 2, 2019, pp. 1-9. [cited by applicant]
All Office Actions; U.S. Appl. No. 17/553,596, filed Dec. 16, 2021. [cited by applicant]
All Office Actions; U.S. Appl. No. 17/553,611, filed Dec. 16, 2021. [cited by applicant]
All Office Actions; U.S. Appl. No. 17/553,619, filed Dec. 16, 2021. [cited by applicant]
All Office Actions; U.S. Appl. No. 17/553,632, filed Dec. 16, 2021. [cited by applicant]
All Office Actions; U.S. Appl. No. 17/553,655, filed Dec. 16, 2021. [cited by applicant]
All Office Actions; U.S. Appl. No. 17/553,659, filed Dec. 16, 2021. [cited by applicant]
All Office Actions; U.S. Appl. No. 17/553,647, filed Dec. 16, 2021. [cited by applicant]
Unpublished U.S. Appl. No. 17/553,596, filed Dec. 16, 2021, to Leigh Knight et. al. [cited by applicant]
Unpublished U.S. Appl. No. 17/553,611, filed Dec. 16, 2021, to Leigh Knight et. al. [cited by applicant]
Unpublished U.S. Appl. No. 17/553,619, filed Dec. 16, 2021, to Leigh Knight et. al. [cited by applicant]
Unpublished U.S. Appl. No. 17/553,632, filed Dec. 16, 2021, to Leigh Knight et. al. [cited by applicant]
Unpublished U.S. Appl. No. 17/553,647, filed Dec. 16, 2021, to Leigh Knightr et. al. [cited by applicant]
Unpublished U.S. Appl. No. 17/553,655, filed Dec. 16, 2021, to Leigh Knight et. al. [cited by applicant]
Unpublished U.S. Appl. No. 17/553,659, filed Dec. 16, 2021, to Leigh Knightr et. al. [cited by applicant]
A. Kothari, “Cosmetic Skin Type Classification Using CNN With Product Recommendation”, 2021 12th International Conference on Computing Communication and Networking Technologies (I000NT), Kharagpur, India, 2021, pp. 1-6,… [cited by applicant]
P. R. H. Perera, “Virtual Makeover and Makeup Recommendation Based on Personal Trait Analysis”, 2021 3rd International Conference on Advancements in Computing (ICAC), Colombo, Sri Lanka, 2021, pp. 288-293, (Year:2021). [cited by applicant]
Cula, et al., “Skin Texture Modeling”, International Journal of Computer Vision, vol. 62, Issue 1/2, Nov. 2004, pp. 97-119. [cited by applicant]