Methods for classifying makeup product colors and tools to support the development of makeup product colors.

Abstract

A computer-implemented tool, intended to be controlled by a user to assist in the development of the color of a makeup product, includes a mapping mode adapted such that the user selects a group of colors of a makeup product from a makeup product color bank, and the mapping mode is configured to classify each color of the selected group of colors according to a method for classifying the color of a makeup product according to labels designed according to the subjective perception of makeup colors. The mapping mode is configured to display a map of the selected colors, arranged in a table according to their respective assigned labels, the table being organized by major rows for each color system group label and major columns for each hue sub-system group label, each major row including sub-rows for each lightness sub-system group label, and each major column including sub-columns for each saturation sub-system group label.

Description

Technical Field

[0001] Embodiments of the present invention relate to a method for classifying the colors of cosmetic makeup products, automatically implemented by a computer, and a tool for assisting in the development of the colors of cosmetic makeup products, implemented by a computer and controlled by a user.

Background Art

[0002] "Cosmetics" means any product as defined in Regulation (EC) No. 1223 / 2009 of the European Parliament and of the Council of 30 November 2009 on cosmetics. Cosmetic makeup products or "makeup products" more specifically are intended to cover the body surface in order to modify the perceived color and / or texture.

[0003] The development of the colors of makeup products may involve the visualization and comparison of the colors of makeup products present in a given market for different skin tones, for example, to identify the preferences of customers in terms of color shades or to identify color shades that are missing and may be needed in a given market.

[0004] For example, the markets surveyed can vary from low-cost products to high-end products, and the products can vary depending on the location of the market, such as different Asian or Chinese markets in the European market.

[0005] The comparison between makeup products can be carried out between products of different brands and franchises of the same company or between legacy products owned and competing products.

[0006] Visualization is typically performed by color experts using physical samples of colors, such as thumbnail color samples of makeup products, under the perception of the human eye, due to the large response in subjective perception of makeup colors that can be produced by slight variations in absolute color. For example, in the case of lipstick red, the first red may appear subjectively cold and lifeless, while the second red, which is absolutely very close to the first red, may appear subjectively warm and rich.

[0007] The absolute difference between two colors may be the distance at which they separate in a "standard observer" model, such as the "CIEXYZ" color space or the "CIELAB" color space. These standard observer models are defined by the International Commission on Illumination (CIE), and the colors they define are not related to any particular device, such as a computer monitor or printer, but to the CIE standard observer, which is the average of the results of color matching experiments under laboratory conditions.

[0008] The RGB (Red-Green-Blue) color space is defined by the coordinates of the additive primary colors red, green, and blue, and is typically used in electronic devices for detecting and displaying color.

[0009] The "CIELAB" color space, also known as L*a*b*, represents color using three coordinates: L* for lightness, a* for chromaticity from greenish to reddish, and b* for chromaticity from bluish to yellowish (chromaticity represents both hue and saturation). In the a*b* plane, specific hues can be identified by specific angles within the triangular circle. The CIELAB color space is designed to be more perceptually uniform than, for example, the RGB color space. However, the subjective perception of makeup product colors does not translate well in the CIELAB color space, and as a result, slight changes in absolute color in the CIELAB color space can still lead to a large reaction in the subjective perception of makeup colors.

[0010] Human color perception goes beyond the L*a*b* coordinate system, making subjective perceptions such as the "background effect" of color important. For example, when viewing a solid-colored square surrounded by a colored background, the perception of the square's color differs depending on the background color. Regarding makeup products, the perception of lipstick color can vary depending on the user's skin tone.

[0011] As a result, providing computerized tools to assist color experts in the development of makeup product colors is difficult due to discrepancies in the digital transfer of colors, such as RGB or L*a*b* coordinates, with respect to the subjective perception of makeup colors.

[0012] Furthermore, another challenge encountered with computerized tools designed to assist color experts in developing makeup product colors lies in the fact that computer monitors cannot equally display the same range of colors, as each has a limited range of colors it can display (known as "color depth"). The resulting problem is that two different colors, each possessing distinguishable characteristics under human perception, may appear exactly the same on different monitors and therefore be unusable for analysis by makeup color experts.

[0013] Therefore, the visualization and comparison of makeup product colors are still conventionally performed under laboratory conditions using a very large number of thumbnail color samples of makeup products, and cannot be performed remotely using a computer under home or office conditions, for example.

[0014] Another challenge in developing makeup product colors is the fact that the color applied to a product can vary depending on the skin tone of the user applying the makeup, and that the subjective perception of color can also vary depending on the user's skin tone. For example, as mentioned above, the "background effect" of skin tone can alter the perception of makeup product colors. Basically, light or pale makeup colors may appear darker when applied to darker skin, while dark, rich makeup colors may appear excessively strong when applied to fair skin, and may appear to perfectly match darker skin.

[0015] Therefore, the development of makeup product colors traditionally requires trial phases on human models to analyze the actual subjective perception when the makeup is used. These trial phases are typically time-consuming and expensive. [Overview of the Initiative] [Problems that the invention aims to solve]

[0016] Therefore, there is a need to provide tools, especially computerized tools, to assist color experts in developing makeup product colors and save time. These tools should be adapted to the subjective perception of makeup colors and not be limited to the performance of computer monitors such as "color count," but should provide the ability to develop appropriate makeup colors across a variety of skin tones. [Means for solving the problem]

[0017] According to an aspect of the present invention, a computer implementation method for automatically classifying the colors of makeup products is: - Provide input coordinate data in the L*a*b* space of the makeup product's color. - Assigning color family labels (e.g., from brown, pink, orange, purple, red) to the colors of makeup products according to the identification of color family volumes within a set of color family volumes in L*a*b* space containing input coordinate data. The color family volumes are designed according to the subjective perception of makeup colors, and the colors of makeup products are classified according to the assigned labels.

[0018] The subjective perception of the makeup colors used in the design of the volume, as well as the boundary values, lines, and surfaces defined below, are advantageously defined by a human color expert, for example, according to the aforementioned susceptible subjective perception specific to the makeup colors. Advantageously, the human color expert can provide a visual database of discrete color points, and the design of the volume and boundary values, lines, and surfaces can be performed to obtain the continuity of the color points through data-driven computation configured to fit the visual database. For example, data-driven computation configured to fit the visual database may be performed by a machine learning training model.

[0019] In other words, this computer implementation method makes it possible to classify colors based on labels representing the subjective perception of makeup colors, defined by conditions established by the subjective perception inherent in the makeup colors. Therefore, the resulting classification applied to each color of a group of analyzed makeup products can provide useful information to color professionals developing makeup product colors, despite limitations in the computer representation of color (color space) and on-screen color display.

[0020] According to one embodiment, a set of color family volumes in L*a*b* space is generated from a database containing a finite number of points in L*a*b* space, each point being labeled with a respective family group label according to the subjective perception of makeup colors, and from a mathematical calculation that includes triangulation to generate an envelope enclosing all points in each respective family group, and interpolation to extend the envelopes until the opposing surfaces of adjacent envelopes coincide with each other, the envelopes defining the enclosure of each color family volume.

[0021] According to one embodiment, the color family volume is configured to separate brown, pink, orange, purple, and red in L*a*b* space according to the subjective perception of makeup colors.

[0022] According to the embodiment, this method is - According to the identification of the position of the input coordinate data, compare with at least one lightness boundary value on the lightness coordinate axis L* of the L*a*b* space, and assign a lightness sub-system group label (e.g., among light, medium, dark) to the color of the makeup product additionally include that at least one lightness boundary value is designed according to the subjective perception of the makeup color, and the color of the makeup product is classified according to the assigned label.

[0023] According to an embodiment, at least one lightness boundary value on the lightness coordinate axis L* of the L*a*b* space decreases in steps for input coordinates having a chroma value greater than a threshold value set according to the subjective perception of the makeup color.

[0024] According to an embodiment, the lightness sub-system group includes a light label assigned when the lightness input coordinate is greater than a first lightness boundary value, a medium label assigned when the lightness input coordinate is between the first lightness boundary value and the second lightness boundary value, and a dark label assigned when the lightness input coordinate is lower than the second lightness boundary value.

[0025] According to an embodiment, the method is - According to the position of the input coordinate data, compare with at least one chroma boundary line in the a*b* plane of the L*a*b* space, and assign a chroma sub-system group label (e.g., among high, medium, low) to the color of the makeup product additionally include that at least one chroma boundary line is designed according to the subjective perception of the makeup color, and the color of the makeup product is classified according to the assigned label.

[0026] According to an embodiment, at least one chroma boundary line in the a*b* plane of the L*a*b* space changes according to the hue of the input coordinate data according to the subjective perception of the makeup color.

[0027] According to one embodiment, the subgroup of saturation includes a high label assigned when the saturation of the input coordinates is greater than a first saturation boundary line, an intermediate label assigned when the saturation of the input coordinates is between the first saturation boundary line and a second saturation boundary line, and a low label assigned when the saturation of the input coordinates is lower than the second saturation boundary line.

[0028] According to the embodiment, this method is - Assigning a subgroup label (e.g., from cool, neutral, and warm) to the color of a makeup product by comparing it to at least one heattone interface inside each color family volume in L*a*b* space, according to the position of the input coordinate data. The system further includes the following: at least one heat-tone interface is designed according to the subjective perception of makeup colors, and the colors of the makeup products are classified according to the assigned labels.

[0029] According to the embodiment, at least one hyutenant boundary of each color family volume in the L*a*b* space is determined according to the subjective perception of the makeup color.

[0030] According to the embodiment, the Hutone subgroup includes a warm-colored label assigned when the input coordinate is located on one side of the first Hutone interface, a neutral-colored label assigned when the input coordinate is located between the other side of the first Hutone interface and one side of the second Hutone interface, and a cool-colored label assigned when the input coordinate is located on the other side of the second Hutone interface.

[0031] According to the embodiment, the colors of the makeup products are classified hierarchically, firstly according to a color family group label, secondly according to a sub-color tone family group label, and then according to a sub-lightness family group label and a sub-color saturation family group label.

[0032] This hierarchy allows for a convenient classification of labels, for example, for color analysis of makeup products. That is, other hierarchies can also be used, and regarding the process of assigning labels, since the lightness boundary value may depend on the saturation label, all processing steps can either be performed simultaneously, or in some cases, the lightness label may need to be processed after the saturation label.

[0033] In another embodiment, a computer implementation tool intended to be controlled by the user for assisting in the development of colors for makeup products is: - A mapping mode adapted for a user to select a group of makeup product colors from a makeup product color bank, configured to display a map of the selected colors, which is arranged in a table according to the labels assigned to each color in the selected group, using the method for classifying makeup product colors defined above, wherein each color in the selected group is classified and arranged in a table according to the assigned labels, and the table is organized by a main row for each color family group label and a main column for each luminosity subfamily group label, where each main row includes a sub-row for each lightness subfamily group label, and each main column includes a sub-column for each saturation subfamily group label. Includes.

[0034] According to the embodiment, the table is: - Five main rows for each color family label: brown, pink, orange, purple, and red. - Three main columns for the Hutone subgroup labels of cool, neutral, and warm colors, respectively. - Three sub-rows for each main row for the light, medium, and dark light subgroup labels, respectively, and - Three subcolumns for each main column, for low, medium, and high saturation subgroup labels. It is organized by [the organization / group].

[0035] According to the embodiment, the tool is - An application mode adapted to allow the user to select at least one set of makeup product colors from a displayed map (ID card) and at least one skin tone photographic model, wherein the application mode is configured to display simulated images of the selected makeup product color sets on each of the skin tone photographic models. It also includes the following.

[0036] According to the embodiment, the tool is - A color creation mode adapted to allow the user to select at least one skin tone photographic model and set parameters to generate a custom color, and configured to display an image of a simulation of the custom color application on at least one skin tone photographic model. It also includes the following.

[0037] According to the embodiment, the color creation mode is further adapted to allow the user to select a set of colors for at least one makeup product from a displayed map (ID card), and is configured to simultaneously display comparison images of the application of the custom color and the selected set of makeup product colors on at least one skin tone photographic model.

[0038] In another embodiment, a computer program product includes instructions that, when the program is executed by a computer, cause the computer to perform the methods defined above or to perform the tools defined above.

[0039] In another embodiment, the computer-readable storage medium includes instructions, when executed by a computer, that cause the computer to perform the methods defined above or to perform the tools defined above.

[0040] In other words, the embodiments and designs provide a digital system that enables immediate analysis of the hues of color cosmetics and the creation of a range of hues, based on an integrated process of: 1) data visualization of instrumental measurement data with labels that conform to the color classification of makeup products; 2) digital application of the measured hues in images showing models of various skin tones acquired using, for example, a pseudospectral imaging system; and 3) digitally conceiving and applying hues accurately to acquired images using, for example, the aforementioned pseudospectral camera system.

[0041] Therefore, methods and systems (tools) are defined that enable the integration of developing a range of shades, with particular consideration given to evaluating makeup on various skin tones, for makeup product development teams using digital platforms.

[0042] This allows product development teams to easily create shade ranges by providing an integrated ability to visualize shades from a database of measured shades and digitally conceive new shades, resulting in higher-performing, skin-tone-matching shade ranges for color cosmetics.

[0043] Furthermore, this improves the efficiency of developing the color range and, in some cases, allows for the digital visualization and comparison of lipstick shades in dedicated classifications and simulations on the face, thus reducing the development time for the color range by approximately 25%.

[0044] Furthermore, the embodiments and models defined above enable the development of a range of shades that are considered appropriate across a variety of skin tones, which can reduce the number of years it takes to create shades, as the development team can visualize and select shades from the database to match a particular skin tone.

[0045] Other advantages and specifications of the present invention will become apparent, without limitation, in connection with the accompanying drawings in the consideration of the detailed description of the embodiments. [Brief explanation of the drawing]

[0046] [Figure 1] Here is an example of how to categorize the colors of makeup products. [Figure 2] An example of a discrete representation of the L*a*b* color space is shown. [Figure 3] This shows an example of generating a set of color family volumes in L*a*b* space. [Figure 4] This shows an example of identifying the position of input coordinate data by comparing it with at least one brightness boundary value, BndVal1, BndVal2. [Figure 5] An example of identifying the position of input coordinate data compared to at least one chroma boundary line, BndCrcl1, BndCrcl2, is shown. [Figure 6] This shows an example of identifying the position of input coordinate data compared to at least one Huetone boundary surface, BndSrfc1, BndSrfc2. [Figure 7] An embodiment of the method for classifying the colors of makeup products according to the present invention is shown. [Figure 8] This image shows an example of a conventional technique for classifying the colors of makeup products. [Figure 9] This section outlines the challenges encountered with conventional techniques. [Figure 10] Here is an example of a computer tool. [Figure 11] An example of the tool's application mode is shown. [Figure 12] An example of the tool's application mode is shown. [Figure 13] An example of the tool's application mode is shown. [Figure 14] This document illustrates an embodiment of a tool for supporting the development of colors in makeup products according to the present invention. [Modes for carrying out the invention]

[0047] Figure 1 shows a method 100 for classifying the colors of makeup products 102, designed to be performed automatically by a computer. Preferably, the makeup products 102 are lipstick products. Here, we describe a method for providing classification labels for a single color 104 of a single makeup product 102. For example, in step 102, the makeup product 102 is selected from a database of makeup product colors. However, it will be understood that the classification is intended to be applied primarily to some colors of some makeup products in order to distinguish these colors according to the subjective human perception of makeup colors. In such cases, the method is performed for each color of a set of some makeup products.

[0048] The method includes, in step 104, providing input coordinate data for the color 102 of the makeup product in the L*a*b* space. As described above and in relation to Figure 2 below, the L*a*b* space is the conventional "CIELAB" color space that represents color as three coordinates: L* for lightness, a* for greenish to reddish chromaticity, and b* for bluish to yellowish chromaticity (chromaticity represents both hue and saturation). Step 104 may include a conventional conversion of color coordinates from any other color space to coordinates in the L*a*b* color space.

[0049] The first assignment step 106 assigns color family labels (e.g., brown, pink, orange, purple, or red color family) to the colors 102-104 of the makeup product. As disclosed below in relation to Figure 3, the color family labels may be assigned according to the identification of a color family volume from a set of color family volumes in L*a*b* space containing the input coordinate data. In particular, the color family volumes are specifically designed according to the subjective perception of makeup colors. For example, as described below in relation to Figure 3, the color family volumes are advantageously determined by fitting with a visual database according to data-driven computation.

[0050] The second assignment step 108 assigns subgroup labels for lightness (e.g., light, medium, or dark), subgroup labels for saturation (e.g., high, medium, or low), and subgroup labels for huetone (e.g., cool, neutral, or warm huetone) to the colors 102-104 of the makeup product.

[0051] As described below in relation to Figure 4, the lightness subgroup labels can be assigned according to the identification of the position of the input coordinate data 104 compared to at least one lightness boundary value on the lightness coordinate axis L* in the L*a*b* space. In particular, the at least one lightness boundary value is specifically designed according to the subjective perception of makeup colors.

[0052] As described below in relation to Figure 5, the saturation subgroup labels can be assigned according to the position of the input coordinate data 104, compared to at least one saturation boundary in the a*b* plane of the L*a*b* space. In particular, at least one saturation boundary is specifically designed according to the subjective perception of makeup colors.

[0053] As described below in relation to Figure 6, the Hutone subgroup labels can be assigned according to the position of the input coordinate data 104 and compared with at least one Hutone boundary inside each color group volume 106 in L*a*b* space. In particular, the at least one Hutone boundary is specifically designed according to the subjective perception of the makeup color.

[0054] In the final step 110, the colors of the makeup products are classified according to their assigned labels within an identification information card map that is hierarchically arranged, for example, advantageously as shown later in relation to Figure 7.

[0055] Figure 2 shows an exemplary discrete representation of the L*a*b* color space, also known as the CIELAB color space. The CIELAB color space represents color using three coordinates: L* represents lightness, a* represents hues from greenish to reddish, and b* represents hues from bluish to yellowish.

[0056] The L*a*b* space makes it easy to derive the values ​​of hue, saturation, and color points in the L*a*b* coordinate system. The hue of a color point is determined by the triangulation angle θ in the a*b* plane containing that point, so θ = tan -1 It can be expressed as (b* / a*). The saturation of a color point is defined by the distance from the origin (a*=0, b*=0) in the a*b* plane containing that point, so C*=(a* 2 +b* 2 ) 1 / 2 It can be expressed as follows. The value of a color point is determined by its lightness coordinate L*.

[0057] Figure 3 shows the generation of a set of color family volumes in L*a*b* space used to identify color family labels for input coordinate data in the first assignment step 106 of Method 100.

[0058] Firstly, a database is provided containing a finite number of points in the L*a*b* space for each color family, each point being labeled with its respective color family label BRN, ORG, PNK, RD, and PRP, as shown in scatter plot 302. In this step, the labels are "manually" assigned to each point in the database by a human color expert according to the subjective perception of makeup colors. These labels may correspond to evaluations of the brown color family BRN, the orange color family ORG, the pink color family PNK, the red color family RD, and the purple color family PRP. This "manual" assignment is performed once to constitute a computer-implemented classification method according to specific subjective perceptions of makeup colors. This one manual assignment may be performed according to conventional techniques for classifying makeup colors, as described below in relation to Figure 8.

[0059] Secondly, mathematical calculations are performed to extrapolate the continuous volume in L*a*b* space to the scattering diagrams of each discrete color family. As shown in plot 304, the mathematical calculations generate an envelope enclosing all points in each respective family, for example, by conventional triangulation techniques such as Delaunay triangulation and alpha shape generation.

[0060] Furthermore, mathematical calculations favorably perform interpolation to widen the envelopes, as shown in plot 306. The diffusion is configured to fill the gaps between color family volumes until the opposing surfaces of adjacent envelopes coincide with each other. This can be done, for example, by selecting the nearest neighbor according to the distance to the triangulation plane of each color family.

[0061] The envelopes obtained in plot 306 define the enclosure of each color family volume when all of the opposing surfaces of adjacent envelopes coincide with each other without any gaps between them.

[0062] Therefore, the input points placed in the L*a*b* color space according to their coordinates are assigned the respective labels BRN, ORG, PNK, RD, and PRP of the envelope surrounding the input points in the L*a*b* color space.

[0063] Figure 4 shows the identification of the location of the input coordinate data 104 compared with at least one brightness boundary value BndVal1, BndVal2 used to assign brightness subgroup labels in step 108 of method 100.

[0064] In this example, the lightness subgroup labels include the "light" lightness label LGT, the "medium" lightness label MDM, and the "dark" lightness label DRK, and are identified by comparing them to a first lightness boundary value BndVal1 and a second lightness boundary value BndVal2 that is lower than the first lightness boundary value BndVal1. The light label LGT is assigned when the lightness input coordinate L* is greater than the first lightness boundary value BndVal1, the medium label MDM is assigned when the lightness input coordinate L* is between the first lightness boundary value BndVal1 and the second lightness boundary value BndVal2, and the dark label DRK is assigned when the lightness input coordinate L* is less than the second lightness boundary value BndVal2.

[0065] Here too, both lightness boundary values ​​BndVal1 and BndVal2 are specifically designed according to the subjective perception of makeup colors, and in particular, the level of the lightness boundary value on the L* axis can be set according to the saturation of the input coordinate data.

[0066] In addition, the lightness boundary values ​​BndVal1 and BndVal2 are advantageously reduced by step C*Stp for input coordinates having a saturation value C* greater than the threshold selected according to the subjective perception of the makeup color. In fact, the lightness boundary values ​​BndVal1 and BndVal2 are slightly reduced for the highest chromatic colors, particularly the "high" saturation subgroup labels assigned in step 108 of Method 100, as described in relation to Figure 5. This advantageously allows for compensation of the effect known as the Helmholtz-Kohlrausch effect, where the subjective perception of lightness increases with saturation.

[0067] Figure 5 shows the identification of the location of input coordinate data 104 compared to at least one chroma boundary line BndCrcl1, BndCrcl2 in the a*b* plane containing the input coordinate point, which is used to assign chroma subgroup labels in step 108 of Method 100.

[0068] In this example, the subgroup labels for saturation include the "high" saturation label HGH, the "medium" saturation label INTR, and the "low" saturation label LW, and are identified by comparing them to the first saturation boundary BndCrcl1 and the second saturation boundary BndCrcl2, which is lower than the first saturation boundary BndCrcl1. In any a*b* plane, the saturation level C* is the Euclidean distance from the origin (0,0), i.e.,

number

[0069] The label HGH (high) is assigned when the saturation of input coordinate C* is greater than the first saturation boundary BndCrcl1; the label INTR (intermediate) is assigned when the saturation of input coordinate C* is between the first saturation boundary BndCrcl1 and the second saturation boundary BndCrcl2; and the label LW (low) is assigned when the saturation of input coordinate C* is lower than the second saturation boundary BndCrcl2.

[0070] Here again, both saturation boundaries BndCrcl1 and BndCrcl2 are specifically designed according to the subjective perception of makeup colors, and in particular, these lines are defined only for hues in the a*b* plane that are susceptible to the application of makeup products. In the example of lipstick makeup products, the hues susceptible to application are approximately located in the positive half-plane of a*, i.e., from the yellowish-orange hue yORG to the bluish-purple hue bPRP.

[0071] Furthermore, the saturation boundaries BndCrcl1 and BndCrcl2 depend favorably on the hue of the input coordinate data to take into account the subjective perception of saturation corresponding to the hue of each color. In fact, for example, the orange hue yORG appears "weaker" in terms of saturation than the purple hue bPRP. As a result, both the saturation boundaries BndCrcl1 and BndCrcl2 may have the appearance of a helix with a slightly larger radius at positive values ​​on the b* side (yellow-orange hue yORG) and a slightly narrower radius at negative values ​​on the b* side (blue-violet hue bPRP) compared to the spiral radius around the zero value of b* (reddish hues at positive values ​​of a*).

[0072] Figure 6 shows the identification of the location of input coordinate data 104 compared to at least one Hutone boundary surface BndSrfc1, BndSrfc2 in the L*a*b* space, more specifically in the color group volume (Figure 3) containing the input coordinate points, which is used to assign Hutone subgroup labels in step 108 of Method 100.

[0073] In this example, the Hutone subgroup labels include the "warm" Hutone label WRM, the "neutral" Hutone label NTR, and the "cool" Hutone label CL, which are identified by comparison with the first Hutone interface BndSrfc1 and the second Hutone interface BndSrfc2, and demarcate the inner spaces of each color group volume BRN, ORG, RD, PNK, and PRP.

[0074] A warm-colored label WRM is assigned when the input point is located on one side of the first Hutone interface BndSrfc1; a neutral-colored label NTR is assigned when the input point is located between the other side of the first Hutone interface BndSrfc1 and one side of the second Hutone interface BndSrfc2; and a cool-colored label CL is assigned when the input point is located on the other side of the second Hutone interface BndSrfc2.

[0075] Here too, both huetone interfaces BndSrfc1 and BndSrfc2 are specifically designed according to the subjective perception of the makeup color, and in particular, the position of these interfaces and the range of neutral colors are determined by the visual results of a makeup color expert. The huetone gradation interfaces BndSrfc1 and BndSrfc2 are defined simultaneously along lightness (e.g., L*=20~90) and saturation (e.g., C*=0~highest level), and their coordinate definitions can be registered in a lookup table for identifying the relative position of the input coordinate data.

[0076] Figure 7 shows an example of the final step 110 of the classification method 100 described above in relation to Figures 1-6.

[0077] In the final step 110, the colors of the makeup products are classified according to their assigned labels, advantageously on the illustrated identification card map, which shows the hierarchical arrangement of colors by firstly color family group labels, secondly hue tone subfamily group labels, and then similarly lightness subfamily group labels and saturation subfamily group labels.

[0078] In the illustrated identification information card map, makeup products of multiple colors are classified together, and each color is processed in the manner described above in relation to Figures 1-6 for the assignment of its respective label, which determines the position of the color on the identification information card map.

[0079] Therefore, in the identification information card map, colors are arranged in a table organized by main rows for each color family group label: "brown," "pink," "orange," "purple," and "red," and main columns for each hue tone subfamily group label: "cool colors," "neutral colors," and "warm colors." Furthermore, each main row contains a set of subrows for each lightness subfamily group label: "light," "medium," and "dark," and each main column contains a set of subrows for each saturation subfamily group label: "low," "medium," and "high."

[0080] Alternatively, the table could be organized without the set of subcolumns for each saturation subgroup label, and replaced by sorting the colors within each lightness subrow in ascending order of their saturation values, for example, from left to right within each subrow.

[0081] Because the colors are arranged according to the labels in this identification information card map, i.e., according to the subjective perception that arises as a makeup product, color experts can perform an improved analysis of the classified group of makeup colors.

[0082] In fact, firstly, because the classification is performed automatically by a computer, identification information card maps can be generated very quickly and repeatedly for different selections of color groups of makeup products.

[0083] Therefore, this method allows color specialists to save considerable time compared to conventional techniques for this type of classification, which are performed manually by visual inspection of thumbnail color samples, as shown in Figure 8.

[0084] Secondly, the Identification Information Card Map, with its color positioning corresponding to the subjective perception evoked by makeup products, is not limited by the color display performance of a given computer monitor. In fact, a computer monitor can display the same color for two different data; for example, a low-saturation warm pink may appear identical to a low-saturation cool brown on a computer monitor because its performance is limited in terms of the "number of colors" compared to the sensitivity of human eye perception. Such a situation, without classification in the Identification Information Card Map, would lead to a misanalysis of these colors. However, the positioning of the two colors in the Identification Information Card Map provides color professionals with information about their actual differences, even though these two colors are displayed by the same signal on a computer monitor.

[0085] Figure 8 is a photograph of conventional techniques for classifying makeup product colors, for example, to compare products from different brands and franchises of the same company, or owned legacy products with competing products.

[0086] Traditionally, classification has been performed by color experts using physical samples of colors under human visual perception, for example, by individually characterizing them according to subjective perception, and using thumbnail color samples of makeup products spread out on a workbench or whiteboard.

[0087] This conventional technique is clearly time-consuming and is not adapted, or even impossible, to be run repeatedly for many different groups of makeup colors. On the other hand, as mentioned above, identification information card maps can be generated instantly and easily as many times as needed.

[0088] Figure 9 shows an example of a conventional computer representation of a group of colors, plotted here projected onto an a*b* 2D plane (i.e., by ignoring the L* coordinate). Even if CIELAB's a*b* plane were designed to present a representation approximating human color perception, such representations cannot be used to analyze makeup colors. Indeed, while identifying color families such as "brown," "orange," "pink," "red," and "purple" may be performed partially visually by color experts on such plots, other characterizations are limited to the execution of color representations on computer screens.

[0089] The aforementioned problem remains: two different color data can appear on a computer monitor as the same color signal (for example, a low-saturation warm pink may appear the same as a low-saturation cool brown), making subjective perception-based classification of makeup colors impractical.

[0090] From another perspective, saturation values ​​can be seen as the distance of a color point from the origin, but the subjective perception of saturation varies depending on the hue. As a result, for a given hue (e.g., purple), high saturation points may be plotted inconsistently closer to the origin than lower saturation points for another hue (e.g., orange), and consequently, the color points may appear mixed in an a*b* plot, appearing disorganized. Classification of makeup colors by subjective perception must remain visual, and is therefore impractical due to the limitations of computer monitor display performance.

[0091] Figure 10 shows a complete computer tool to assist color experts, i.e., "users," in the development of makeup product colors, benefiting from the classification methods and identification information card maps described above in relation to Figures 1-7.

[0092] A tool implemented by a user-controlled computer may actually be embodied as a computer program product that, when the program is executed by the computer, includes instructions causing the computer to perform the tool provided herein, or may actually be embodied as a computer-readable storage medium that, when executed by the computer, includes instructions causing the computer to perform the tool provided herein.

[0093] The tool first includes a mapping mode configured to provide an identification information card map for the selected group of makeup colors, as described above in relation to Figure 7.

[0094] Therefore, users can select a group of makeup product colors from a makeup product color bank, such as a bank containing, for example, in-house brand and franchise makeup colors and / or competitor brand and franchise makeup colors, as displayed in mapping mode.

[0095] Depending on the business division of the color bank, users can also choose the market for which the makeup products are targeted or many other options.

[0096] Therefore, in the example in Figure 7, the identification information card map classifies the selected color groups in a table organized by five main rows for brown, pink, orange, purple, and red color family group labels, three main columns for cool, neutral, and warm hue tone subfamily group labels, three sub-rows for each main row for light, medium, and dark lightness subfamily group labels, and three sub-columns for each main column for low, medium, and high saturation subfamily group labels.

[0097] Therefore, the tool's mapping mode provides the user with a data visualization of instrument measurement data in a table arranged according to the subjective perception of makeup colors. The mapping allows the user to select shades to visualize on this meaningful identification information card map, for example, the range of successful competitor shades compared to the company's own shade range, thereby understanding the gaps where the company brand currently does not cover shades.

[0098] Figures 11, 12, and 13 show the application modes of the tools adapted to digitally simulate the visualization of the applied shade range on the face, for more specific considerations of the makeup color selected by the user.

[0099] The application mode is adapted so that the user selects one or more sets of makeup product colors from the identification information card map displayed in the mapping mode, and also selects one or more skin tone photographic models. The application mode is configured to display simulated images of the application of the selected makeup product color sets on at least one skin tone photographic model.

[0100] Advantageously, the simulation of the application of each set of selected makeup product colors to at least one skin tone photographic model is performed by the pseudospectral imaging system disclosed in the scientific publication "Liu Z., Xiao K., Pointer M. et al., “Developing a multi-spectral imaging system using a RGB camera under two illuminations: Proceedings of the 28th IS&T Color and Imaging conference. 28th Color and Imaging Conference, 04-19 Nov 2020, Online. Society for Imaging Science and Technology"; or the technology disclosed in U.S. Patent No. 8,498,456 granted by the United States (titled “Method and system for applying cosmetic and / or accessoral enhancements to digital images”); or the technology disclosed in U.S. Patent Application Publication No. 2018 / 0075524 granted by the United States (“Applying virtual makeup products”).

[0101] Figure 11 shows the options available in the application mode. In this example, the user selected more than nine shades from the mapping mode and chose one skin tone photograph model.

[0102] The simulated image, which applies the selected set of makeup product shades to a selected skin tone photograph model, is displayed in a grid that dynamically adapts to the selection. In this example, the grid is a 3x3 image and is scrollable up and down to browse the grid.

[0103] To display the simulation image, two view options may be provided, such as a full-face view (see Figure 12) or a close-up view, as shown in Figure 11.

[0104] The color selection can be changed at any time using the same process as in mapping mode, for example, by using checkboxes for each image in the simulation. The changed color selection can also be automatically reflected in mapping mode.

[0105] Figure 12 shows other possible options in the application mode. In this example, the user selected two hues from the mapping mode or a previous application mode, for example from the application mode example in Figure 11, and the user selected two skin tone photographic models.

[0106] Figure 13 shows other possible options in the application mode. In this example, the user selects two hues from the mapping mode or a previous application mode, for example, from the application mode example in Figure 11, and the user selects one skin tone photograph model. When only two hues are selected, the application mode provides a parallel comparison mode, allowing the user to instantly compare the two hues by dragging the cursor left or right.

[0107] Figure 14 shows the color creation mode of a tool adapted to digitally create new shades and simulate the visualization of the shades being created on a face, as a preliminary design step for creating a new makeup product.

[0108] The color creation mode is adapted so that the user selects at least one skin tone photograph model and sets parameters to generate a custom color. The color creation mode is configured to display a simulation image of the custom color application on at least one skin tone photograph model in real time.

[0109] For example, the parameters for generating a custom color may include hue, saturation, and brightness parameters. Finish parameters such as "matte," "satin," or "glossy" may also be provided.

[0110] Furthermore, the color creation mode is advantageously adapted to allow the user to select the color of one existing makeup product from a displayed identification information card map, and is configured to simultaneously display comparison images of the application of the custom color and the selected makeup product color set, each on at least one skin tone photographic model. For example, simultaneous display of comparison images can be performed using a drag cursor as shown in Figure 13 or a grid of simulated images as shown in Figure 11 or Figure 12.

[0111] For example, by viewing the two hues digitally applied to the face side by side, the user can further compare the two hues with the displayed color difference Δ(E), L*, C*, and h(θ).

[0112] To resume, the tools described above, in relation to Figures 10-14, provide a digital system that enables immediate analysis of the creation of color cosmetics shades and shade ranges based on an integrated process interacted with by the user as follows: 1) A data visualization that represents specific subjective perceptions of makeup colors, enabling users to select shades for visualizing and performing meaningful analysis of products and markets. 2) Digital application of measured hues to images depicting models with different skin tones acquired using a pseudospectral imaging system, which enables a user to visually evaluate the hues of models with different skin types and understand their market suitability by digitally applying hues (e.g., lipstick hues) to images showing the faces of models with different skin tones. 3) The ability to digitally conceive and apply hues precisely to images acquired using the aforementioned pseudo-spectral simulation imaging system, enabling the user to digitally create hues by inputting brightness, saturation, hue, and makeup finish values ​​rendered in real time onto an image of the model's face.

Claims

1. A computer implementation method (100) for automatically classifying the colors of makeup products (102), - Provide input coordinate data in the L*a*b* color space (104) of the makeup product. - Assign a color system label (106) to the color of the makeup product according to the identification of a color system volume among the set of color system volumes (ORG, PNK, RD, PRP, BRN) in the L*a*b* space that includes the input coordinate data. A computer implementation method (100) comprising the following, wherein the color family volume (ORG, PNK, RD, PRP, BRN) is designed according to the subjective perception of makeup colors, and the colors of the makeup products are classified according to the assigned labels.

2. The method according to claim 1, wherein the set of color family volumes (ORG, PNK, RD, PRP, BRN) in the L*a*b* space is generated from a database (302) containing a finite number of points in the L*a*b* space, each point being labeled with a respective family label according to the subjective perception of the makeup color, and from a mathematical calculation comprising triangulation (304) generating an envelope enclosing all the points in each of the family volumes, and interpolation (306) extending the envelopes until the opposing surfaces of adjacent envelopes coincide with each other, the envelopes defining the enclosure of each of the color family volumes.

3. The method according to claim 1, wherein the color system volume (BRN, PNK, ORG, PRP, RD) is configured to separate the colors brown, pink, orange, purple, and red in the L*a*b* space according to the subjective perception of the makeup colors.

4. - Assign a subgroup lightness label (108) to the color of the makeup product by comparing it with at least one lightness boundary value (BndVal1, BndVal2) on the lightness coordinate axis L* of the L*a*b* space, according to the identification of the position of the input coordinate data. The method according to claim 1, further comprising, wherein the at least one lightness boundary value (BndVal1, BndVal2) is designed according to the subjective perception of the makeup color, and the color of the makeup product is classified according to the assigned label.

5. The method according to claim 4, wherein the at least one lightness boundary value (BndVal1, BndVal2) in the lightness coordinate axis L* of the L*a*b* space is reduced by a step (C*Stp) with respect to input coordinate data having a saturation value greater than a threshold set according to the subjective perception of the makeup color.

6. The method according to claim 4, wherein the subgroup of brightness categories includes a light label (LGT) assigned when the brightness of the input coordinate data is greater than a first brightness boundary value (BndVal1), a medium label (MDM) assigned when the brightness of the input coordinate data is between the first brightness boundary value (BndVal1) and a second brightness boundary value (BndVal2), and a dark label (DRK) assigned when the brightness of the input coordinate data is lower than the second brightness boundary value (BndVal2).

7. - Assign a sub-chroma group label (108) to the color of the makeup product by comparing it with at least one chroma boundary line (BndCrcl1, BndCrcl2) in the a*b* plane of the L*a*b* space, according to the identification of the position of the input coordinate data. The method according to claim 1, further comprising, wherein the at least one saturation boundary (BndCrcl1, BndCrcl2) is designed according to the subjective perception of the makeup color, and the colors of the makeup product are classified according to the assigned label.

8. The method according to claim 7, wherein the at least one chroma boundary line (BndCrcl1, BndCrcl2) in the a*b* plane of the L*a*b* space changes according to the hue of the input coordinate data, in accordance with the subjective perception of the makeup color.

9. The method according to claim 7, wherein the subgroup of saturation includes a high label (HGH) assigned when the saturation of the input coordinate data is greater than a first saturation boundary line (BndCrcl1), an intermediate label (INTR) assigned when the saturation of the input coordinate data is between the first saturation boundary line (BndCrcl1) and a second saturation boundary line (BndCrcl2), and a low label (LW) assigned when the saturation of the input coordinate data is lower than the second saturation boundary line (BndCrcl2).

10. - Assigning a subgroup label (108) to the color of the makeup product by comparing it with at least one Hutone boundary surface (BndSrfc1, BndSrfc2) inside each of the color group volumes in the L*a*b* space, according to the identification of the position of the input coordinate data. The method according to claim 1, further comprising, wherein the at least one futon interface (BndSrfc1, BndSrfc2) is designed according to the subjective perception of makeup color, and the colors of the makeup product are classified according to the assigned label.

11. The method according to claim 10, wherein the at least one hutone interface (BndSrfc1, BndSrfc2) of each color system volume in the L*a*b* space is determined according to the subjective perception of the makeup color.

12. The method according to claim 10, wherein the Hutone subgroup includes a warm-colored label (WRM) assigned when the input coordinate data is located on one side of the first Hutone boundary surface (BndSrfc1), a neutral-colored label (NTR) assigned when the input coordinate data is located between the other side of the first Hutone boundary surface (BndSrfc1) and one side of the second Hutone boundary surface (BndSrfc2), and a cool-colored label (CL) assigned when the input coordinate data is located on the other side of the second Hutone boundary surface (BndSrfc2).

13. - Assigning a subgroup label (108) to the color of the makeup product by comparing it with at least one huteon boundary surface (BndSrfc1, BndSrfc2) inside each of the color group volumes in the L*a*b* space, according to the identification of the position of the input coordinate data, - Assign a subgroup lightness label (108) to the color of the makeup product by comparing it with at least one lightness boundary value (BndVal1, BndVal2) on the lightness coordinate axis L* of the L*a*b* space, according to the identification of the position of the input coordinate data. - Assign a sub-chroma group label (108) to the color of the makeup product by comparing it with at least one chroma boundary line (BndCrcl1, BndCrcl2) in the a*b* plane of the L*a*b* space, according to the identification of the position of the input coordinate data. It also includes, The method according to claim 1, wherein the colors of the makeup product are classified hierarchically, first according to the color family group label, second according to the hue tone sub-family group label, and then according to the lightness sub-family group label and the saturation sub-family group label.

14. A computer-controlled implementation tool intended to assist in the development of makeup product colors, - A mapping mode (Figure 10) adapted for the user to select a group of makeup product colors from a makeup product color bank, configured to classify each color in the selected group of colors using the method for classifying makeup product colors according to claim 1, and configured to display a map of the selected colors arranged in a table according to the respective assigned labels, wherein the table is organized by a main row for each color group label and optionally a main column for each huetone subgroup label, each main row optionally including a sub-row for each lightness subgroup label, and each main column optionally including a sub-row for each saturation subgroup label, the mapping mode Computer implementation tools including

15. The aforementioned table is, - Five main rows for each color family label: brown, pink, orange, purple, and red. - Three main columns for the subgroup labels of cool, neutral, and warm hue tones, respectively. - For each of the light, medium, and dark subgroup labels, there are three sub-rows for each main row, and - Three subcolumns for each main column, for low, medium, and high saturation subgroup labels. The tool according to claim 14, which is organized by...

16. - An application mode (Figures 11, 12, and 13) adapted to the user selecting at least one set of makeup product colors from the displayed map (ID card) and at least one skin tone photographic model, wherein the application mode is configured to display simulated images of the application of the selected set of makeup product colors on each of the at least one skin tone photographic models. The tool according to claim 14, further comprising:

17. - A color creation mode (Figure 14) adapted to allow the user to select at least one skin tone photographic model and set parameters to generate a custom color, wherein the color creation mode is configured to display an image of a simulation of the application of the custom color on the at least one skin tone photographic model. The tool according to claim 14, further comprising:

18. The tool according to claim 17, wherein the color creation mode (Figure 14) is further adapted to allow the user to select a set of colors for at least one makeup product from the displayed map, and is configured to simultaneously display comparison images of the application of the custom color and the selected set of makeup product colors on the at least one skin tone photographic model.

19. A computer program product that, when executed by a computer, includes an instruction to cause the computer to perform the method described in any one of claims 1 to 13, or to cause the computer to perform the tool described in any one of claims 14 to 18.

20. A computer-readable storage medium that, when executed by a computer, includes instructions that cause the computer to perform the method described in any one of claims 1 to 13, or to perform the tool described in any one of claims 14 to 18.

Images