Computing device, method and apparatus for recommending at least one of a makeup palette or a hair coloration scheme

Patent metadata

Field	Value
Publication number	US-12254664-B2
Application number	US-201917632453-A
Country	US
Kind code	B2
Filing date	Aug 21, 2019
Priority date	Aug 21, 2019
Publication date	Mar 18, 2025
Grant date	Mar 18, 2025

Abstract

Method and apparatus for recommending at least one of a makeup palette or a hair coloration scheme are provided. The method comprises extracting a color set of at least one region of a digital image associated with a user ( 201 ); generating color recommendation information for at least one of a makeup palette or a hair coloration scheme for at least two other regions of the digital image associated with the user based on one or more inputs indicative of the extracted color set ( 202 ); and generating one or more instances of a virtual representation of a makeup palette recommendation or a hair coloration scheme recommendation based on the color recommendation information ( 203 ).

First claim

The invention claimed is:

1. A computing device, comprising:
an optimal color unit including computational circuitry configured to extract a color set of at least one region of a digital image associated with a user, and to generate color recommendation information for at least one of a makeup palette or a hair coloration scheme for at least two other regions of the digital image associated with the user based on one or more inputs indicative of the extracted color set; and
a makeup and hair color unit including computational circuitry configured to generate one or more instances of a virtual representation of a makeup palette recommendation or a hair coloration scheme recommendation based on the color recommendation information,
wherein the color recommendation information is a recommendation for a combination of colors of at least one region and at least two other regions,
wherein the optimal color unit includes computational circuitry which is further configured to:
store the extracted color set in a memory;
locate said extracted color set into a sample training set, wherein said sample training set comprises information for colors of different regions of a plurality of sampled images, information for color combinations for different regions of said plurality of sampled images and information for total scores for each of color combinations;
search color combinations which contain said extracted color set in said sample training set;
rank total scores corresponding to said searched color combinations;
generate recommended color combinations based on said ranked total scores.

2. The computing device according to claim 1 , wherein the optimal color unit includes computational circuitry which is further configured to generate color recommendation information for at least one of a makeup palette or a hair coloration scheme for at least two other regions of the digital image associated with the user based on one or more inputs indicative of the extracted color set by a prediction model.

3. The computing device according to claim 2 , wherein said prediction model comprises one of Chi-squared Automatic Interaction Detector (CHAID) Decision tree model and Multi-variate Gaussian map classifier.

4. The computing device according to claim 3 , wherein when said prediction model comprises Chi-squared Automatic Interaction Detector (CHAID) Decision tree model, the optimal color unit includes computational circuitry which is further configured to:
input said extracted color set to said CHAID Decision tree model, wherein said extracted color set is category type, said CHAID Decision tree model is trained from a sample training set, said sample training set comprises information for colors of different regions of a plurality of sampled images, information for color combinations for different regions of said plurality of sampled images and information for total scores for each of color combinations;
generate color recommendation information for at least one of a makeup palette or a hair coloration scheme for at least two other regions of the digital image associated with the user.

5. The computing device according to claim 3 , wherein when said prediction model comprises Chi-squared Automatic Interaction Detector (CHAID) Decision tree model, the optimal color unit includes computational circuitry which is further configured to:
translate said extracted color set to corresponding numerical values of colors in a color space;
input said corresponding numerical values of colors to said CHAID Decision tree model, said CHAID Decision tree model is trained from a sample training set, said sample training set comprises information for numerical values of colors in a color space for different regions of a plurality of sampled images and information for total scores for each of color combinations;
generate color recommendation information for at least one of a makeup palette or a hair coloration scheme for at least two other regions of the digital image associated with the user.

6. The computing device according to claim 3 , wherein when said prediction model comprises Multi-variate Gaussian map classifier, the optimal color unit includes computational circuitry which is further configured to:
translate said extracted color set to corresponding numerical values of colors in a color space;
input said corresponding numerical values of colors to said Multi-variate Gaussian map classifier, said Multi-variate Gaussian map classifier is trained from a sample training set, said sample training set comprises information for numerical values of colors in a color space for different regions of a plurality of sampled images and information for total scores for each of color combinations;
generate color recommendation information for at least one of a makeup palette or a hair coloration scheme for at least two other regions of the digital image associated with the user.

7. The computing device according to claim 1 , wherein said at least one region, said at least two other regions and different regions can be regions where a feature of a body of said user is located.

8. A method for recommending at least one of a makeup palette or a hair coloration scheme, the method comprising:
extracting a color set of at least one region of a digital image associated with a user;
generating color recommendation information for at least one of a makeup palette or a hair coloration scheme for at least two other regions of the digital image associated with the user based on one or more inputs indicative of the extracted color set; and
generating one or more instances of a virtual representation of a makeup palette recommendation or a hair coloration scheme recommendation based on the color recommendation information,
wherein the color recommendation information is a recommendation for a combination of colors of at least one region and at least two other regions,
wherein said generating color recommendation information for at least one of a makeup palette or a hair coloration scheme for at least two other regions of the digital image associated with the user based on one or more inputs indicative of the extracted color set comprising:
storing said extracted color set in a memory;
locating said extracted color set into a sample training set, wherein said sample training set comprises information for colors of different regions of a plurality of sampled images, information for color combinations for different regions of said plurality of sampled images and information for total scores for each of color combinations;
searching color combinations which contain said extracted color set in said sample training set;
ranking total scores corresponding to said searched color combinations;
generating recommended color combinations based on said ranked total scores.

9. The method according to claim 8 , wherein said generating color recommendation information for at least one of a makeup palette or a hair coloration scheme for at least two other regions of the digital image associated with the user based on one or more inputs indicative of the extracted color set is achieved by a prediction model,
wherein said prediction model comprises one of Chi-squared Automatic Interaction Detector (CHAID) Decision tree model and Multi-variate Gaussian map classifier.

10. The method according to claim 9 , wherein when said prediction model comprises Chi-squared Automatic Interaction Detector (CHAID) Decision tree model, said generating color recommendation information for at least one of a makeup palette or a hair coloration scheme for at least two other regions of the digital image associated with the user based on one or more inputs indicative of the extracted color

Assignees

• Oreal

Inventors

• Li Shuting
• Zhu Tingting
• Jiang Qing
• Wu Jun
• Liu Honghui

Classifications

• G06T2207/30196

  Human being; Person · CPC title

• G06T2207/20092

  Interactive image processing based on input by user · CPC title

• G06T2207/20081

  Training; Learning · CPC title

• G06T2207/10024

  Color image · CPC title

• G06T11/00

  Two-dimensional [2D] image generation · CPC title