Skin color assessment and color pigment mixing recommendation for cosmetic applications

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media for determining a color pigment mixing recommendation based on a sensor reading of a person's skin. One or more color value sets of a person's skin are determined. The one or more color value sets are evaluated. A color pigment mixing recommendation is generated. The color pigment mixing recommendation including one or more color pigments and an amount of the color pigments to be mixed. The color pigment mixing recommendation is displayed, via a user interface of a client device, the color pigment mixing recommendation.

What is claimed is: 
     
         1 . A system comprising one or more processors configured to perform the operations of:
 determining one or more color value sets of a person's skin;   evaluating the one or more color value sets; and   generating one or more color pigment mixing recommendations, the color pigment mixing recommendations including one or more color pigments and an amount of the color pigments to be mixed; and   displaying, via a user interface of a client device, the color pigment mixing recommendations.   
     
     
         2 . The system of  claim 1 , wherein the determining the one or more color value sets comprises:
 obtaining by a color sensor device, the one or more color value sets, wherein an individual color value set includes an L* value, an a* value, and a b* value in the L*a*b* color space; and   receiving from the color sensor device the one or more color value sets.   
     
     
         3 . The system of  claim 1 , further comprises the operations of:
 obtaining one or more images, via the client device, of the person's skin;   inputting the one or more images into a trained machine learning network configured to determine a color pigment mixing recommendation; and   determining by the trained machine learning network the one or more color pigment mixing recommendations.   
     
     
         4 . The system of  claim 1 , further comprises the operations of:
 inputting the one or more color value sets into a trained machine learning network configured to determine one or more color pigment mixing recommendations; and   determining by the trained machine learning network the one or more color pigment mixing recommendations.   
     
     
         5 . The system of  claim 4 , further comprising the operations of:
 performing a lookup operation to identify a closet match of color values in a lookup table to individual values in the color value set; and   selecting one or more predetermined color pigment mixing recommendations from the lookup table to be the generated one or more color pigment mixing recommendations.   
     
     
         6 . The system of  claim 1 , further comprising the operations of:
 obtaining multiple color value sets for a person's skin, wherein the set includes a first value, second value and third value; and   averaging each of the first values, the second values and the third values and generating an averaged color value set, wherein the generated color pigment mixing recommendation is based on the averaged color value set.   
     
     
         7 . The system of  claim 1 , further comprising the operations:
 obtaining one or more images, via the client device, of a person's skin; and   determining the one or more color value sets of a person's skin based on processing of the one or more images to determine the one or more color value sets.   
     
     
         8 . A computer-implemented method for comprising:
 determining one or more color value sets of a person's skin;   evaluating the one or more color value sets; and   generating one or more color pigment mixing recommendations, the one or more color pigment mixing recommendation including one or more colors and ratios of the colors to be mixed; and   displaying, via a user interface of a client device, the generated one or more color pigment mixing recommendation.   
     
     
         9 . The computer-implemented method of  claim 9 , wherein the determining the one or more color value sets comprises:
 obtaining by a color sensor device, the one or more color value sets, wherein an individual color value set includes an L* value, an a* value, and a b* value in the L*a*b* color space; and   receiving from the color sensor device the one or more color value sets.   
     
     
         10 . The computer-implemented method of  claim 8 , further comprising the operations of:
 obtaining one or more images, via the client device, of the person's skin;   inputting the one or more images into a trained machine learning network configured to determine a color pigment mixing recommendation; and   determining by the trained machine learning network the color pigment mixing recommendation.   
     
     
         11 . The computer-implemented method of  claim 8 , further comprising the operations of:
 inputting the one or more color value sets into a trained machine learning network configured to determine color pigment mixing recommendation; and   determining by the trained machine learning network the color pigment mixing recommendation.   
     
     
         12 . The computer-implemented method of  claim 11 , further comprising the operations of:
 performing a lookup operation to identify a closet match of color values in a lookup table to individual values in the color value set; and   selecting a predetermined color pigment mixing recommendation from the lookup table to be the generated color pigment mixing recommendation.   
     
     
         13 . The computer-implemented method of  claim 8 , further comprising the operations of:
 obtaining multiple color value sets for a person's skin, wherein the set includes a first value, second value and third value; and   averaging each of the first values, the second values and the third values and generating an averaged color value set, wherein the generated color pigment mixing recommendation is based on the averaged color value set.   
     
     
         14 . The computer-implemented method of  claim 8 , further comprising the operations:
 obtaining one or more images, via the client device, of a person's skin; and   determining the one or more color value sets of a person's skin based on processing of the one or more images to determine the one or more color value sets.   
     
     
         15 . A non-transitory computer readable medium that stores executable program instructions that when executed by one or more computing devices configure the one or more computing devices to perform operations comprising:
 determining one or more color value sets of a person's skin;   evaluating the one or more color value sets; and   generating one or more color pigment mixing recommendations, the color pigment mixing recommendation including one or more color pigments and an amount of the color pigments to be mixed; and   displaying, via a user interface of a client device, the color pigment mixing recommendation.   
     
     
         16 . The non-transitory computer readable medium of  claim 15 , wherein the determining the one or more color value sets comprises:
 obtaining by a color sensor device, the one or more color value sets, wherein an individual color value set includes an L* value, an a* value, and a b* value in the L*a*b* color space; and   receiving from the color sensor device the one or more color value sets.   
     
     
         17 . The non-transitory computer readable medium of  claim 15 , further comprising the operations of:
 obtaining one or more images, via the client device, of the person's skin;   inputting the one or more images into a trained machine learning network configured to determine a color pigment mixing recommendation; and   determining by the trained machine learning network the color pigment mixing recommendation.   
     
     
         18 . The non-transitory computer readable medium of  claim 15 , further comprising the operations of:
 inputting the one or more color value sets into a trained machine learning network configured to determine color pigment mixing recommendation; and   determining by the trained machine learning network the color pigment mixing recommendation.   
     
     
         19 . The non-transitory computer readable medium of  claim 18 , further comprising the operations of:
 performing a lookup operation to identify a closet match of color values in a lookup table to individual values in the color value set; and   selecting a predetermined color pigment mixing recommendation from the lookup table to be the generated color pigment mixing recommendation.   
     
     
         20 . The non-transitory computer readable medium of  claim 15 , further comprising the operations of:
 obtaining multiple color value sets for a person's skin, wherein the set includes a first value, second value and third value; and   averaging each of the first values, the second values and the third values and generating an averaged color value set, wherein the generated color pigment mixing recommendation is based on the averaged color value set.   
     
     
         21 . The non-transitory computer readable medium of  claim 15 , further comprising the operations:
 obtaining one or more images, via the client device, of a person's skin; and   determining the one or more color value sets of a person's skin based on processing of the one or more images to determine the one or more color value sets.