US 11,854,188 B2
Machine-implemented acne grading
Christine Elfakhri, Brooklyn, NY (US); Guive Balooch, New York, NY (US); Florent Valceschini, Jersey City, NJ (US); Dominique Moyal, Paris (FR); Hemant Joshi, San Francisco, CA (US); Yuanjie Li, San Francisco, CA (US); and Zhiyuan Song, San Francisco, CA (US)
Assigned to L'OREAL, Paris (FR)
Filed by L'ORÉAL, Paris (FR)
Filed on Oct. 28, 2020, as Appl. No. 17/083,175.
Claims priority of provisional application 62/928,855, filed on Oct. 31, 2019.
Prior Publication US 2021/0133968 A1, May 6, 2021
Int. Cl. G06K 9/00 (2022.01); G06T 7/00 (2017.01); G16H 15/00 (2018.01); G16H 50/50 (2018.01); G16H 50/30 (2018.01); G16H 70/60 (2018.01); G16H 30/40 (2018.01); G16H 30/20 (2018.01); G16H 20/10 (2018.01); G06N 20/00 (2019.01); A61B 5/00 (2006.01); G16H 50/20 (2018.01); G06Q 30/0601 (2023.01)
CPC G06T 7/0012 (2013.01) [A61B 5/445 (2013.01); A61B 5/486 (2013.01); A61B 5/7267 (2013.01); A61B 5/742 (2013.01); G06N 20/00 (2019.01); G16H 15/00 (2018.01); G16H 20/10 (2018.01); G16H 30/20 (2018.01); G16H 30/40 (2018.01); G16H 50/20 (2018.01); G16H 50/30 (2018.01); G16H 50/50 (2018.01); G16H 70/60 (2018.01); A61B 5/0077 (2013.01); A61B 2576/02 (2013.01); G06Q 30/0631 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/30088 (2013.01)] 13 Claims
OG exemplary drawing
 
1. A system comprising:
one or more memory circuits configured to store machine learning models;
one or more processing circuits configured to:
accept at least one image from a user depicting the user's skin;
apply the machine learning models to the image to classify acne characteristics; and
provide an indication of the classified acne characteristics; and
a user interface configured to display the provided indication of the classified acne characteristics,
wherein the one or more processing circuits is further configured to generate a regimen recommendation based on the classified acne characteristics and the user interface is further configured to display the generated regimen recommendation,
wherein the one or more processing circuits is further configured to:
accept another image from the user depicting the user's skin;
apply the machine learning models to the other image to classify the acne characteristics; and
update the regimen recommendation to the user based on the classified acne characteristics of the other image.