Machine-implemented facial health and beauty assistant

Patent metadata

Field	Value
Publication number	US-10990858-B2
Application number	US-201916241425-A
Country	US
Kind code	B2
Filing date	Jan 7, 2019
Priority date	Jan 5, 2018
Publication date	Apr 27, 2021
Grant date	Apr 27, 2021

Abstract

An image is accepted by one or more processing circuits from a user depicting the user's facial skin. Machine learning models stored in one or more memory circuits are applied to the image to classify facial skin characteristics. A regimen recommendation is provided to the user based on the classified facial skin characteristics.

First claim

The invention claimed is:

1. An apparatus comprising:
a processing circuit to accept at least one image depicting facial skin of a user;
a communication circuit to convey the accepted image to machine learning models and to receive a regimen recommendation from the machine learning models; and
a user interface circuit to present the regimen recommendation to the user,
wherein the processing circuit is further configured to:
alert the user that another image depicting the user's facial skin is required according to a predefined schedule;
accept the other image from a user depicting the user's facial skin;
the communication circuit being further configured to convey the other image to the machine learning models and to receive an updated regimen recommendation from the machine learning models; and
the user interface circuit being further configured to present the updated regimen recommendation to the user.

2. The apparatus of claim 1 , wherein the user interface circuit is further configured to present images of human faces to the user;
the processing circuit being further configured to accept input from the user that classifies facial skin characteristics from the images provided thereto through the user interface circuit; and
the communication interface circuit being further configured to convey the user input to the machine learning models as training data.

3. The apparatus of claim 2 , wherein the user interface circuit is further configured to present a user control by which the facial skin characteristics are rated on a predetermined scale.

4. The apparatus of claim 1 , further comprising a camera communicatively coupled to the processing circuit to provide the image from the user thereto.

5. The apparatus of claim 1 , wherein the camera, the processing circuit, the user interface circuit and the communication circuit are components of a smartphone.

6. A method comprising:
accepting at least one image depicting facial skin of a user;
conveying the accepted image to machine learning models;
receiving a regimen recommendation from the machine learning models; and
presenting the regimen recommendation to the user,
wherein the method further comprises:
alerting the user that another image depicting the user's facial skin is required according to a predefined schedule;
accepting the other image from a user depicting the user's facial skin;
conveying the other image to the machine learning models;
receiving an updated regimen recommendation from the machine learning models; and
presenting the updated regimen recommendation to the user.

7. The method of claim 6 further comprising:
presenting images of human faces to the user;
accepting input from the user that classifies facial skin characteristics from the images provided thereto; and
conveying the user input to the machine learning models as training data.

8. The method of claim 7 further comprising:
presenting a user control by which the facial skin characteristics are rated on a predetermined scale.

Assignees

• Oreal

Inventors

• Ludwinski Celia
• VALCESCHINI Florent
• Li Yuanjie
• Song Zhiyuan
• El-Fakhri Christine
• Joshi Hemant

Classifications

• G06V10/764

  using classification, e.g. of video objects · CPC title

• G09B19/0076 Primary

  Body hygiene; Dressing; Knot tying · CPC title

• G06F18/41

  Interactive pattern learning with a human teacher · CPC title

• G06F18/2413

  based on distances to training or reference patterns · CPC title

• G06V40/172

  Classification, e.g. identification · CPC title