Information processing systems, information processing methods, and programs

Abstract

To quantitatively evaluate the finish quality of cosmetics based on the surface structure of the coating film. [Solution] The information processing system comprises a storage unit and a control unit. The storage unit stores correlation information for multiple cosmetics between a visual evaluation value relating to the quality of gloss or coverage of the cosmetic applied to the subject's skin and coating parameters quantified by analyzing the coating structure in a sample coating image obtained by imaging the reflected light of a sample of the cosmetic coating applied to a sample substrate or by extracting interference signals. The control unit receives a target coating image obtained by imaging the reflected light of a newly applied specific cosmetic coating or by extracting interference signals, analyzes the coating structure in the target coating image to calculate coating parameters, estimates an evaluation value relating to the quality of gloss or coverage of the specific cosmetic based on the calculated coating parameters and the stored correlation information, and generates and transmits evaluation information corresponding to the estimated evaluation value.

Description

[Technical Field]

[0001] The present invention relates to an information processing system, an information processing method, and a program for processing information related to the finished state of a coating film of a cosmetic (including sunscreen cosmetic) applied to a user's skin, based on an image obtained by imaging the coating film. [Background Art]

[0002] Conventionally, there have been technologies that provide users with information related to the state of a coating film such as a cosmetic applied to the user's skin.

[0003] For example, Patent Document 1 below discloses a skin evaluation method, which extracts a coefficient of variation of luminance in a measurement region set in a skin image of a subject as an optically detectable feature amount, and evaluates the freshness and firmness of the subject's skin based on the coefficient of variation of luminance. [Prior Art Documents] [Patent Documents]

[0004] [Patent Document 1] Japanese Unexamined Patent Publication No. 2022-169152 [Summary of the Invention] [Problem to be Solved by the Invention]

[0005] However, although the technology of Patent Document 1 can comprehensively quantitatively evaluate the freshness and firmness of skin based on the luminance of the skin image, it cannot quantitatively evaluate the finish quality of the cosmetic based on the coating film structure such as the uneven shape of the surface of the coating film.

[0006] An object of the present invention is to provide an information processing system, an information processing method, and a program capable of quantitatively evaluating the finish quality of a cosmetic based on a coating film structure. [Means for Solving the Problem]

[0007] An information processing system according to one embodiment of the present invention comprises a storage unit and a control unit. The storage unit stores correlation information for multiple cosmetics between a visual evaluation value relating to the quality of gloss or coverage of the cosmetic applied to a subject's skin and coating parameters quantified by analyzing the coating structure in a sample coating image obtained by imaging the reflected light of a sample of the cosmetic coating applied on a sample substrate or by extracting interference signals. The control unit receives a target coating image obtained by imaging the reflected light of a newly applied specific cosmetic coating or by extracting interference signals, analyzes the coating structure in the target coating image to calculate coating parameters, estimates an evaluation value relating to the quality of gloss or coverage of the specific cosmetic based on the calculated coating parameters and the stored correlation information, and generates and transmits evaluation information corresponding to the estimated evaluation value.

[0008] Information processing methods according to other embodiments of the present invention are: A storage unit stores correlation information for multiple cosmetics between visual evaluation values ​​regarding the quality of glossiness or coverage of the cosmetic applied to the subject's skin and coating parameters obtained by analyzing the coating structure in a sample coating image obtained by capturing reflected light from a sample of the cosmetic coating applied to a sample substrate or by extracting interference signals. The image of the target coating obtained by capturing the reflected light of the newly applied specific cosmetic coating or by extracting interference signals is received. The coating structure in the aforementioned target coating image is analyzed to calculate the coating parameters. This includes estimating an evaluation value for the glossiness or coverage quality of the specific cosmetic product based on the calculated coating parameters and the stored correlation information, and generating and transmitting evaluation information corresponding to the estimated evaluation value.

[0009] A program according to another embodiment of the present invention is used in an information processing device. The process involves storing correlation information for multiple cosmetics between visual evaluation values ​​regarding the quality of glossiness or coverage of the cosmetic applied to the subject's skin and coating parameters obtained by analyzing the coating structure in a sample coating image obtained by imaging the reflected light of the coating film of the cosmetic applied to a sample substrate or by extracting interference signals, and the visual evaluation values ​​regarding the cosmetic finish. The steps include receiving an image of a target coating obtained by capturing the reflected light of a newly applied specific cosmetic coating or by extracting interference signals from the coating, The steps include: analyzing the coating structure in the target coating image and calculating coating parameters; The system is configured to perform the following steps: estimate an evaluation value for the glossiness or coverage quality of the specific cosmetic product based on the calculated coating parameters and the stored correlation information, generate evaluation information corresponding to the estimated evaluation value, and transmit it. [Effects of the Invention]

[0010] According to an information processing system, information processing method, and program according to one embodiment of the present invention, it is possible to quantitatively evaluate the quality of the finish of a cosmetic product based on the coating film structure. However, this effect is not limited to the present invention. [Brief explanation of the drawing]

[0011] [Figure 1] This diagram shows the configuration of a makeup finish information provision system according to one embodiment of the present invention. [Figure 2] This diagram shows the hardware configuration of the above-mentioned makeup finish information provision server. [Figure 3] This diagram shows the configuration of the database owned by the above-mentioned makeup finish information server. [Figure 4] This flowchart shows the flow of the process for generating makeup finish-related information by the above-mentioned makeup finish information provision server. [Figure 5] This diagram illustrates the visual evaluation values ​​of the cosmetic finish of cosmetics, which are entered into the above-mentioned cosmetic finish information server. [Figure 6] This figure illustrates the steps of measuring a cosmetic coating film and acquiring coating film parameters from the coating film image performed by the makeup finish information providing server described above. [Figure 7] This figure illustrates the step of deriving a prediction formula for finish evaluation through correlation analysis between visual evaluation values and coating film parameters performed by the makeup finish information providing server described above. [Figure 8] This figure illustrates the step of deriving the prediction formula for finish evaluation derived by the makeup finish information providing server described above. [Figure 9] This figure shows examples of coating film parameters acquirable by the makeup finish information providing server described above. [Figure 10] This is a flowchart showing the flow of processing for providing estimated makeup finish evaluation information to developers by the makeup finish information providing server described above. [Figure 11] This figure conceptually shows the flow of processing for providing estimated makeup finish evaluation information to developers by the makeup finish information providing server described above. [Figure 12] This is a flowchart showing the flow of processing for providing estimated makeup finish evaluation information to users by the makeup finish information providing server described above. [Figure 13] This figure shows an example of a UI for selecting desired finish information output by the makeup finish information providing server described above. [Figure 14] This figure shows an example of estimated makeup finish evaluation information provided to users by the makeup finish information providing server described above. [Figure 15] This figure shows examples of coating film parameters used in another embodiment of the present invention. [Figure 16] This figure shows the prediction accuracy of the finish quality of cosmetics using coating film parameters according to another embodiment of the present invention. [Figure 17] This figure illustrates an example of evaluating non-uniformity of finish quality according to another embodiment of the present invention. [Figure 18]It is a diagram showing a comparison between the case where a coating film image is captured with visible light OCT and the case where it is captured with SEM in another embodiment of the present invention. [Figure 19] It is a table showing a comparison of coating film parameter values calculated from each image in Figure 18. [Figure 20] It is a table showing a comparison of coating film parameters calculated from each image in Figure 18, evaluated by Pearson's correlation coefficient and significance level p-value. [Figure 21] It is a diagram showing the temporal change in the finish quality of a cosmetic coating film according to another embodiment of the present invention. MODE FOR CARRYING OUT THE INVENTION

[0012] Hereinafter, embodiments of the present invention will be described with reference to the drawings.

[0013] [System Configuration] As shown in Figure 1, this system includes a cosmetic finish information providing server 100, a developer terminal 200, a counselor terminal 300, and a user terminal 400 on the Internet 50.

[0014] The cosmetic finish information providing server 100 is a server (information processing device) that provides information related to cosmetic finish when a cosmetic is applied to a user's skin. The cosmetic finish information providing server 100 is connected to the developer terminal 200, the counselor terminal 300, and the user terminal 400 via the Internet 50.

[0015] The developer terminal 200 is a terminal used, for example, by cosmetic researchers and developers in a company, and is, for example, a smartphone, a mobile phone, a tablet PC (Personal Computer), a notebook PC, a desktop PC, or the like.

[0016] For newly developed cosmetics, the researcher and developer uses the information provided by the cosmetic finish information providing server 100 to check whether the finish quality obtained by the cosmetic matches the intended quality.

[0017] The inventors have found that there is a correlation between the quality of the finish of a cosmetic product (expressions indicating this quality) and numerical values ​​(coating parameters) obtained by optically analyzing the coating structure in a coating image obtained by imaging the coating film of the cosmetic product (imaging the reflected light of the coating film or extracting interference signals). The cosmetic finish information providing server 100 generates and stores correlation information (cosmetic finish relationship information) that indicates this correlation.

[0018] The researcher applies the newly developed cosmetic onto a sample substrate and obtains a coating image, which is then transmitted from the developer terminal 200 to the cosmetic finish information server 100. The cosmetic finish information server 100 analyzes the coating structure in the image to calculate coating parameters (details described later), and based on the correlation information (cosmetic finish relationship information) between these coating parameters and the visual evaluation value regarding the cosmetic finish of the cosmetic, estimates the cosmetic finish evaluation value of the cosmetic and transmits this cosmetic finish evaluation information to the developer terminal 200.

[0019] Based on the cosmetic finish evaluation information provided by the cosmetic finish information server 100, the researchers adjust the ingredients of the cosmetic under development. Here, the cosmetic includes sunscreen cosmetics (UV protection formulations).

[0020] Furthermore, the quality of the makeup finish that is evaluated by the makeup finish evaluation score includes, for example, the quality of coverage (leaving a natural skin feel ⇔ thick) and the quality of shine (foggy ⇔ clear). These are axes that evaluate each texture, further subdividing the strength of coverage and shine. Within the texture evaluation axis, there are sub-expressions that evaluate the presence or absence in one direction, and axes set at opposite ends by selecting two of these sub-expressions can become the axis for the quality of shine and the axis for the quality of coverage. Examples of sub-expressions include freshness, smoothness, powderiness, oiliness, moisturizing feeling, water retention, uniformity of the application film, continuity of the film, unevenness of color, natural skin feel, blendability, matte finish, three-dimensionality, vitality, healthy complexion, transparency, firmness, foggy feel, adherence, luster, shine, glossy, lustrous, watery, full of life, etc.

[0021] In this embodiment, "coating film structure" includes not only the surface shape of the coating film, such as irregularities, but also the light intensity distribution, which includes color information resulting from the surface shape and depth information resulting from the wavelength of light. Factors that can affect the coating film structure include the state of the powders and liquids contained in the coating film. For example, it is thought that the shape of the coating film, such as irregularities, the resulting color information, and the light intensity distribution, which includes depth information resulting from the wavelength of light, will change depending on whether the powders and liquids are uniformly distributed in the coating film or if there is an uneven distribution.

[0022] For capturing the above coating images, for example, visible light OCT (Optical Coherence Tomography) is used. Alternatively, other OCT methods (SD-OCT (Spectral Domain-OCT), SS-OCT (Swept Source-OCT), FF-OCT (Full Field OCT), etc.), scanning electron microscopes (SEM), digital microscopes, hyperspectral cameras, digital cameras, etc., may be used. Visible light OCT and digital microscopes are particularly good in terms of resolution and consistency with the evaluation of the cosmetic finish. Among these, visible light OCT is better from the following points.

[0023] Visible light OCT is a device that uses a light source in the visible light range to non-destructively image (visualize) the surface irregularities and light reflection from the surface and within the skin. Compared to SEM, it is characterized by the fact that observation is possible immediately after application of cosmetics to a substrate and observation is possible at room temperature and atmospheric pressure. Compared to digital microscopes, it is characterized by the fact that it can visualize the fine three-dimensional structure of the surface shape, but it is also characterized by the fact that it can visualize the internal structure of the coating as information separate from the surface shape and that it is possible to compare the reflection intensity of single scattered light.

[0024] The counselor terminal 300 is a terminal used by counselors (who also act as sales staff) in places such as cosmetics counters, and can be a smartphone, mobile phone, tablet PC, notebook PC, or desktop PC. The user terminal 400 is a terminal used by users of cosmetics, and can be a smartphone, mobile phone, tablet PC, notebook PC, or desktop PC.

[0025] The makeup finish information server 100 can also provide the above-mentioned makeup finish evaluation information to the user regarding the cosmetics the user is considering purchasing, either via the counselor terminal 300 or directly to the user terminal 400.

[0026] In other words, when the counselor terminal 300 sells cosmetics to a user, it sends information about the desired finish of the cosmetics (desired finish information) to the cosmetics finish information providing server 100. The cosmetics finish information providing server 100 then extracts cosmetics finish evaluation information (evaluation information of the quality of the cosmetics finish) of cosmetics that have evaluation values ​​that match the desired finish information and sends it to the counselor terminal 300.

[0027] Similarly, when the user terminal 400 transmits desired finish information to the cosmetic finish information providing server 100, the cosmetic finish information providing server 100 extracts cosmetic finish evaluation information (evaluation information of the quality of the cosmetic finish) of cosmetic products that have evaluation values ​​matching the desired finish information and transmits it to the user terminal 400.

[0028] Furthermore, if equipment such as OCT, SEM, or digital microscopes is available in the cosmetics sales area, the counselor may apply the cosmetics to the user on the spot, acquire an image of the coating, and transmit the image from the counselor terminal 300 to the cosmetics finish information provision server 100. As a result of the analysis of the coating image, the counselor may receive corresponding cosmetics finish evaluation information from the cosmetics finish information provision server 100.

[0029] Alternatively, the user may take an image of the state in which they have applied the cosmetic product using a digital camera (smartphone) or the like, and send it as a coating image to the cosmetic finish information provision server 100. The system may then receive corresponding cosmetic finish evaluation information from the cosmetic finish information provision server 100 as a result of analyzing the coating image.

[0030] [Hardware configuration of the makeup finish information server] As shown in Figure 2, the makeup finish information providing server 100 includes a CPU (Central Processing Unit) 11, ROM (Read Only Memory) 12, RAM (Random Access Memory) 13, an input / output interface 15, and a bus 14 that connects these to each other.

[0031] The CPU 11 accesses RAM 13 and other memory as needed, performing various calculations and comprehensively controlling all blocks of the cosmetic finish information server 100. Multiple CPUs 11 may be provided depending on the processing. ROM 12 is a non-volatile memory in which the OS, programs, and firmware such as various parameters to be executed by the CPU 11 are permanently stored. RAM 13 is used as a working area for the CPU 11 and temporarily holds the OS, various running applications, and various data being processed.

[0032] The input / output interface 15 is connected to a display unit 16, an operation reception unit 17, a storage unit 18, a communication unit 19, and the like.

[0033] The display unit 16 is a display device that uses, for example, an LCD (Liquid Crystal Display), an OLED (Organic ElectroLuminescence Display), or a CRT (Cathode Ray Tube).

[0034] The operation reception unit 17 is, for example, a pointing device such as a mouse, a keyboard, a touch panel, or other input device. If the operation reception unit 17 is a touch panel, the touch panel may be integrated with the display unit 16.

[0035] The storage unit 18 is a non-volatile memory such as an HDD (Hard Disk Drive), flash memory (SSD; Solid State Drive), or other solid-state memory. The OS, various applications, and various data are stored in this storage unit 18.

[0036] As will be described later, in this embodiment in particular, the storage unit 18 has a coating image database, a cosmetic finish-related information database, and a cosmetic finish evaluation information database, in addition to programs such as applications necessary for the cosmetic finish information provision process described later.

[0037] The communication unit 19 is, for example, a NIC (Network Interface Card) for Ethernet or various modules for wireless communication such as wireless LAN, and is responsible for communication processing between the developer terminal 200, counselor terminal 300, or user terminal 400.

[0038] Although not shown in the diagram, the basic hardware configuration of the developer terminal 200, counselor terminal 300, or user terminal 400 is substantially the same as the hardware configuration of the cosmetic finish information provision server 100.

[0039] [Database configuration of the makeup finish information server]

[0040] As shown in Figure 3, the cosmetic finish information providing server 100 has a coating image database 31, a cosmetic finish-related information database 32, and a cosmetic finish evaluation information database 33 in its storage unit 18. Note that these databases may be stored in a storage device or server externally connected to the cosmetic finish information providing server 100, rather than in the storage unit 18.

[0041] The coating image database 31 stores coating images acquired to generate cosmetic finish-related information (sample coating images obtained by capturing reflected light from a sample coating of the same cosmetic applied to a sample substrate or by extracting interference signals), as well as coating images acquired to generate finish evaluation information for a new cosmetic to be evaluated, for each cosmetic.

[0042] The cosmetic finish-related information database 32 stores correlation information for multiple cosmetic products between visual evaluation values ​​regarding the cosmetic finish (particularly those related to the quality of gloss or coverage) of the cosmetic product applied to the subject's skin and coating parameters quantified by analyzing the coating structure in the sample coating image. The cosmetic finish-related information database 32 also stores visual evaluation value data and coating parameter data, which are the sources of the correlation information.

[0043] Specifically, this correlation information is a regression equation in which coating parameters are the explanatory variables and visual evaluation values ​​indicating the quality of the cosmetic finish are the dependent variable. This equation is generated and stored for each combination of multiple coating parameters.

[0044] The cosmetic finish evaluation information database 33 stores cosmetic finish evaluation information (visual evaluation information) generated based on the correlation information above for each new cosmetic film image, associating it with the film image data for each cosmetic and each combination of film parameters used. This estimated cosmetic finish information includes not only numerical values ​​but also the raw data for the finish evaluation graph described later.

[0045] In addition, although not shown in the diagram, the makeup finish information server 100 may have a user information database containing information such as the accounts of the above-mentioned researchers and users of the user terminal 400. User information may also include preference information such as the desired makeup finish, the product name, color number, type, form, dosage form, and combination of cosmetics that the user wishes to use.

[0046] These databases are referenced and used as needed in the makeup finish information provision process by the makeup finish information provision server 100, which will be described later.

[0047] [Operation of the makeup finish information server] Next, the operation of the makeup finish information providing server 100 configured as described above will be explained. This operation is performed through the cooperation of the hardware of the makeup finish information providing server 100, such as the CPU 11 and communication unit 19, and the software stored in the storage unit 18. For convenience, in the following explanation, the CPU 11 will be considered the main operator.

[0048] (Process for generating information related to makeup finish) First, let's explain the process for generating information related to the finished look of makeup. Figure 4 is a flowchart showing the flow of the makeup finished look-related information generation process by the makeup finished look information providing server 100.

[0049] As shown in the figure, the CPU 11 first inputs a visual evaluation value of the makeup finish when the target cosmetic is applied to the subject's skin (step 41).

[0050] Figure 5 illustrates the visual evaluation values ​​for the cosmetic finish of the product in question.

[0051] In this embodiment, 0.2g of each cosmetic product was applied to the subject's (model's) face using a finger, and then five expert evaluators evaluated each finish item—coverage, shine, makeup look, quality of coverage, and quality of shine—on a five-point scale as shown at the top of the figure.

[0052] For example, coverage, shine intensity, and makeup-like appearance were evaluated on a five-point scale: "none," "slightly present," "somewhat present," "present," and "very present." The quality of coverage was evaluated on a five-point scale: "natural-looking," "somewhat natural-looking," "neither," "somewhat thick coverage," and "thick coverage," with lower scores for those that retained a natural look and higher scores for thicker coverage. The quality of shine was evaluated on a five-point scale: "clear shine," "somewhat clear shine," "neither," "somewhat foggy shine," and "foggy shine," with lower scores for clearer shines and higher scores for foggy shines.

[0053] As shown in the lower part of the figure, the evaluation scores for each item from the five expert evaluators were divided into four parts based on the number of evaluators and the number of ranks on the evaluation axis. The maximum score was divided into four levels, and the evaluation scores were converted into four levels to obtain the visual evaluation values. The generated visual evaluation value data is stored in the makeup finish-related information database 32.

[0054] Next, the CPU 11 receives an image of the cosmetic coating from the developer terminal 200 (step 42), analyzes the coating structure of the image, and obtains coating parameters (step 43).

[0055] Figure 6 illustrates the process of measuring the cosmetic coating film and obtaining coating film parameters from the coating film image in this embodiment.

[0056] As shown in the figure, five types of base makeup cosmetics A to E were uniformly applied to a glass slide using a 25 μm applicator. After drying for 60 minutes at room temperature, the coating film was measured using a digital microscope and visible light OCT to obtain an image of the surface shape of the coating film.

[0057] Specifically, for example, a 400 μm depth scan was performed, approximately 3000 horizontal cross-sectional images were captured, these images were analyzed to create approximately 800 images of light intensity distributions in the vertical cross-section, and these were then imaged as three-dimensional light intensity images.

[0058] The three-dimensional image was then converted to grayscale, for example, to analyze the surface shape, and numerical values ​​for coating parameters such as arithmetic mean height (Sa), minimum autocorrelation length (Sal), crutosys (Sku), and skewness (Ssk) were obtained. The grayscale image was also used for histogram analysis to obtain other coating parameters, and the binarized image of the three-dimensional image was used for particle size distribution analysis.

[0059] Next, CPU 11 performs a correlation analysis between the above coating parameters and the visual evaluation values ​​(step 44), selects two coating parameters, and derives a regression equation for predicting the cosmetic finish evaluation value (step 45).

[0060] Figure 7 illustrates the process of deriving a prediction formula for finish evaluation by correlation analysis between visual evaluation values ​​and coating film parameters provided by the cosmetic finish information server 100.

[0061] As shown in the figure, the significance of the correlation between the visual evaluation values ​​converted to the four levels mentioned above and the numerical values ​​of the coating parameters was evaluated by calculating the Pearson correlation coefficient and the significance level p-value. Those with a significant correlation (significance level p<0.1) were considered to be coating parameters that can indicate the quality of coverage and gloss.

[0062] In the figure, dark gray and bold cells indicate a significant correlation (p<0.05), gray cells indicate a significant trend (p<0.1), and light gray cells indicate a high probability of becoming significant by increasing the number of comparison samples (p<0.15).

[0063] The quality of the coverage can be indicated by either Sa from a digital microscope or Sa from visible light OCT, while the quality of the gloss can be indicated by either Sa, Sku, or Ssk from a digital microscope image or Sa or Ssk from a visible light OCT image.

[0064] Furthermore, the significance evaluated by the Pearson correlation coefficient and the p-value may be adjusted by processing the coating image, which is the basis for calculating the coating parameters, using a spatial frequency filter.

[0065] Figure 8 shows an example of a regression equation for predicting the finished product evaluation, derived based on the significant correlation described above.

[0066] Figure (A) shows an example of a regression equation derived based on the correlation between the visual evaluation value of the quality of the cover feel and the surface shape Sa of the visible light OCT image, and Figure (B) shows an example of a regression equation derived based on the correlation between the visual evaluation value of the quality of the gloss feel and the surface shape Ssk of the visible light OCT image.

[0067] The CPU 11 then stores the derived regression equation as finished product relationship information (correlation information) in the finished product relationship information database 32 (step 46).

[0068] Examples of coating parameters from which the above regression equation can be derived include those shown in Figure 9, in addition to those mentioned above. As shown in the same figure, typically, surface texture parameters (roughness parameters) from JIS B0601-2013 can be used as coating parameters.

[0069] Visual evaluation axes that can be represented by arithmetic mean height Sa (or Ra) may be substituted with indicators that similarly use arithmetic height; evaluation items that can be represented by minimum autocorrelation length Sal may similarly be substituted with indicators of periodicity in peaks and valleys; and visual evaluation axes that can be represented by crutch sys Sku (or Rku) and skewness Ssk (or Rsk) may similarly be substituted with indicators that similarly use the distribution of peaks and valleys.

[0070] Furthermore, it is predicted that there are other visual evaluation axes that can be indicated by indicators other than surface texture parameters, such as indicators using the curvature of peaks and valleys, indicators using the slope of peaks and valleys, indicators using particle size, indicators using luminance histograms, and indicators using the thickness of the coating film.

[0071] Furthermore, for coating parameters other than coating thickness, it is predicted that the significance evaluated from the Pearson correlation coefficient and the p-value can be adjusted by processing the original image using a spatial frequency filter.

[0072] Furthermore, if the quality of coverage is defined using an expression different from the combination of natural skin feel / thickness, or if the quality of glossiness is defined using an expression different from the clear / foggy combination (for example, a lower-level expression as described above), the quality of coverage and glossiness according to the new definitions can be indicated by visually evaluating the finish when multiple (three or more) cosmetics are applied to the face using the evaluation items of that definition, converting the total score of each sample to the four levels described above, and then evaluating the correlation between the visual evaluation score obtained and the numerical values ​​of the coating parameters obtained from images of the same multiple cosmetic samples measured with a digital microscope and visible light OCT, using the Pearson correlation coefficient and the significance level p-value.

[0073] (Processing of providing estimated information on makeup finish evaluation) Next, we will explain the process of providing estimated makeup finish evaluation information using the makeup finish-related information generated as described above. Figure 10 is a flowchart showing the flow of the process of providing estimated makeup finish evaluation information to developers by the makeup finish information provision server 100. Figure 11 is a conceptual diagram showing the flow of the process of providing said estimated makeup finish evaluation information.

[0074] As shown in Figure 10, the CPU 11 first receives an image of a new cosmetic coating from the developer terminal 200 (step 51). As shown in Figure 11(A), the coating image is, for example, a visible light OCT image.

[0075] Next, the CPU 11 analyzes the coating structure of the received coating image and obtains coating parameters, as described above (step 52). Two arbitrary parameters (for example, Sa and Ssk of the surface shape in the visible light OCT image) are selected from the multiple parameters mentioned above to obtain the coating parameters.

[0076] Next, the CPU 11 obtains a regression equation corresponding to the coating parameters acquired above from the finish relationship information database 32 (step 53).

[0077] Next, CPU 11 substitutes the coating parameters into the regression equation obtained above to calculate the cosmetic finish evaluation value (Step 54, Figure 11(B)).

[0078] The CPU 11 then sends information indicating the above evaluation values ​​to the developer terminal 200 (step 55). As shown in Figure 11(C), the information indicating the finish evaluation values ​​includes information showing the level and definition of the quality of the cover feel and gloss feel.

[0079] Alternatively, the CPU 11 may display a diagram as information indicating the finished product evaluation value, in which, for the quality of the coverage, the evaluation value is marked on a numerical axis with the level showing the most natural-looking coverage remaining at one end and the level showing the thickest coverage at the other end.

[0080] Similarly, the CPU 11 may display a diagram in which the evaluation values ​​are marked on a numerical axis with the level showing the clearest gloss at one end and the level showing the foggiest gloss at the other end, regarding the quality of gloss.

[0081] Figure 12 is a flowchart showing the process of providing estimated makeup finish evaluation information to the user by the makeup finish information provision server 100.

[0082] As shown in the figure, the CPU 11 receives the desired finish information from the counselor terminal 300 or the user terminal 400 (step 61).

[0083] The desired finish information is transmitted to the makeup finish information providing server 100 via a UI screen for selecting the desired finish information, for example, displayed on the counselor terminal 300 or the user terminal 400. Figure 13 shows an example of the UI for selecting the desired finish information.

[0084] As shown in the figure, the UI for selecting desired finish information includes, for example, a UI that allows the user to select from, for example, three levels of pull-down menus how much coverage is desired (or not desired) while maintaining a natural skin-like appearance, and how much thick coverage is desired (or not desired). Similarly, for glossiness, a UI that allows the user to select from, for example, five levels of pull-down menus how much foggy and clear finish is desired (or not desired). The information selected from these UIs is transmitted to the makeup finish information providing server 100 as desired finish information.

[0085] Next, the CPU 11 extracts cosmetic finish evaluation information for cosmetic products that have evaluation values ​​matching the desired finish information, and generates a finish evaluation graph based on this finish evaluation information (step 62).

[0086] The CPU 11 then sends the generated finish evaluation graph to the counselor terminal 300 or the user terminal 400 for display.

[0087] Figure 14 shows an example of the finish evaluation graph.

[0088] As shown in the figure, the finish evaluation graph 81 shows the quality of the glossiness and coverage of the cosmetic product in one of the quadrants of a first numerical axis (horizontal axis) where the first limit value is the value showing the clearest glossiness and the second limit value is the value showing the most foggy glossiness, and the second numerical axis (vertical axis) where the third limit value is the value showing the coverage that leaves the most natural skin-like appearance and the fourth limit value is the value showing the thickest coverage.

[0089] In the example shown in the figure, the desired finish information specifies a coverage quality that leaves a natural skin-like feel and a glossy finish quality that provides a clear, glossy look. Foundation A and Foundation B are extracted as cosmetics that match these specifications, and their names and evaluation levels are shown on the graph.

[0090] In addition, the evaluation information also includes detailed information 82 (brand name, description of the finished look) of the cosmetic product shown on the finish evaluation graph 81 above.

[0091] If the counselor terminal 300 or user terminal 400 receives a paint film image instead of the desired finish information (if the user's site has a paint film image acquisition device), the CPU 11 processes the paint film image in the same manner as shown in Figure 10 to generate cosmetic finish evaluation information and transmits it to the counselor terminal 300 or user terminal 400. In this case as well, the cosmetic finish evaluation information can be displayed as a graph, for example, as shown in Figure 14.

[0092] As described above, according to this embodiment, the cosmetic finish information providing server 100 can quantitatively evaluate the quality of the cosmetic finish based on the coating structure of the coating film and provide that information.

[0093] Furthermore, the cosmetics A to E shown in Figure 6 above are described in the product descriptions as follows, for example, regarding the image of the quality of glossiness. Cosmetic product A: Thin film, moderate coverage, moderate shine Cosmetic B: A glossy finish with both a powdery feel and a natural blend into the skin. Cosmetic product C: A glossy finish that looks like it's floating on top of the skin. Cosmetic D: A natural-looking shine that sometimes appears as if you're not wearing any makeup. Cosmetic product E: High coverage and glossy finish

[0094] In the past, the quality of the finish of cosmetics could only be described using such vague expressions. However, according to this embodiment, it is possible to output a quantitative evaluation value. Therefore, for researchers and developers, it becomes easy to determine whether the cosmetic product under development has the intended quality of finish, and for users of cosmetics, it becomes easy to understand how well the expressed quality of finish for a cosmetic product they are considering purchasing matches the actual quality of finish, and this can be used as a basis for purchasing decisions.

[0095] [Differentiation] Although embodiments of the present invention have been described above, the present invention is not limited to the embodiments described above, and various modifications can be made without departing from the spirit of the present invention.

[0096] (Other embodiments) In the above-described embodiment, the coating parameters used were mainly those calculated from the surface shape of the coating film. The inventors have found that by using coating parameters calculated not only from the surface shape of the coating film but also from optical information (internal reflected light) of the internal structure of the coating film, the accuracy of predicting the finish quality of the cosmetic product (quality of coverage and quality of gloss) can be improved.

[0097] Figure 15 shows an example of coating parameters used in this embodiment. As shown in the figure, in this embodiment, in addition to Sa(Sa(Surface)) and Ssk(Ssk(Surface)) of the surface shape of the visible light OCT images of cosmetics A to E shown in the above embodiments, Sa(Sa(Depth-integrated)) and Ssk(Ssk(Depth-integrated)) of the internal structure of the visible light OCT images are also used as coating parameters.

[0098] Figure 16 shows the prediction accuracy of the finish quality of cosmetics using coating film parameters in this embodiment, compared with the embodiment described above. In this figure, bold indicates a significant correlation (p<0.05), dark gray cells indicate a significant trend (p<0.1), and light gray cells indicate a high probability of becoming significant by increasing the number of comparison samples (p<0.15).

[0099] As shown in the figure, it can be seen that using parameters for the entire coating structure, combining Sa and Ssk of the surface shape in the visible light OCT image with Sa and Ssk of the internal structure in the visible light OCT image, improves prediction accuracy in both the quality of coverage and the quality of gloss, compared to using only Sa and Ssk of the surface shape in the visible light OCT image as coating parameters.

[0100] (Introduction of an evaluation system for unevenness in the quality of the finished product) As a result of further investigation, the inventors have newly discovered that by using coating parameters calculated from the surface shape and internal structure of the coating film, it is possible to quantitatively evaluate the non-uniformity (degree of unevenness) of the cosmetic finish, in addition to estimating the quality of gloss and coverage as described above. As a result, the information processing system according to this embodiment also has the function of estimating and presenting an index of overall finish uniformity.

[0101] (Coating parameters used for evaluating non-uniformity) Examples of coating parameters used to evaluate non-uniformity include the following, among the group shown in Figure 9: (i) Variance index of surface shape or internal structure (standard deviation, coefficient of variation, etc.) (ii) Structural periodicity indices in the two-dimensional plane (minimum autocorrelation length (Sal), full width at half maximum of the autocorrelation function, etc.) (iii) Distribution shape indices that show the bias and sharpness of the structural distribution (skewness (Ssk), kurtosis (Sku), etc.) (iv) Particle size index of two-dimensional structure, (v) Indicators related to the thickness of the coating film (attenuation of interference light intensity in the depth direction, depth at which a predetermined threshold intensity is reached, etc.). The cosmetic finish information server 100 can use these parameters individually or in combination to quantify the spatial non-uniformity of the coating film, which leads to unevenness in the quality of the finish, in both the horizontal and depth directions.

[0102] (Example of heterogeneity evaluation: Figure 17) Figure 17 shows an example of evaluating the non-uniformity of the finished product quality. Two types of base makeup cosmetics, P and Q, were applied at a rate of 1.5 mg per cm² to a skin model substrate. After drying at room temperature for 70 minutes, the coating film was measured using visible light OCT to obtain images of the surface shape and internal structure. From the obtained OCT images, the full width at half maximum of the autocorrelation function representing structural periodicity was calculated for the surface shape and the internal structure just below the surface.

[0103] As a result, as shown in Figure (A), cosmetic P exhibited a larger autocorrelation function full width at half maximum in both surface shape and internal structure compared to cosmetic Q, confirming that it has a longer-period and more heterogeneous structure. In addition, as shown in Figure (B), analysis of the light intensity distribution in the depth direction revealed a mixture of regions where light penetrates shallowly and regions where it penetrates deeply. This reflects the non-uniformity of light penetration into the substrate. These findings are useful as quantitative indicators of the likelihood of unevenness occurring after coating.

[0104] (Comparison of visible light OCT and SEM: Figures 18, 19, and 20) Furthermore, the inventors compared and evaluated visible light OCT and SEM in the measurement and parameter analysis of the coating film structure. As shown in Figure 18, the previously described base makeup cosmetics A to E were uniformly applied to a plastic sheet substrate and a glass slide substrate using a 25 μm applicator, dried at room temperature for 60 minutes, and then the coating films were imaged using SEM (plastic sheet substrate) and visible light OCT (glass slide substrate) (in the observation settings for this comparison, the field of view for visible light OCT was approximately 1,880 μm, and the field of view for the SEM image was approximately 240 μm). From the obtained images, coating film parameters such as Sa, Sal, Sku, and Ssk were calculated. Figure 19 shows the calculated values ​​of the coating film parameters.

[0105] As shown in Figure 20, the relationship between leveled visual evaluation values ​​(coverage, gloss, makeup-like appearance, quality of coverage, quality of gloss) and each coating film parameter was evaluated for significance using the p-value and Pearson correlation coefficient, similar to Figure 7.

[0106] Similar to Figure 7, in this figure, dark gray and bold cells indicate a significant correlation (p<0.05), gray cells indicate a significant trend (p<0.1), and light gray cells indicate a high probability of becoming significant by increasing the number of comparison samples (p<0.15).

[0107] As a result, regarding glossiness, makeup-like feel, coverage quality, and glossiness quality, the coating parameters derived from visible light OCT generally showed higher correlations (absolute values) and statistical significance (p<0.1), confirming that visual evaluation has high predictive accuracy.

[0108] This difference is thought to stem from the fact that visible light OCT can acquire non-destructive, depth-resolved internal reflection (internal scattering) information, and can treat the optical structure from the surface to the interior in the same coordinate system. Furthermore, because the light source is in the visible light band, the acquired reflection, scattering, and color information is more easily matched to what is perceived by the human visual system (photopic vision), and there is a tendency for a high degree of agreement between the visual evaluation of "visual finish texture" (clear / foggy, thickness, uniformity, etc.) and the coating parameters. On the other hand, SEM images are mainly based on surface shape information, and it is difficult to directly capture the contribution of optical non-uniformity inside the coating. In addition, visible light OCT does not require conductive coating or a vacuum environment, and can measure continuously while maintaining the actual state after coating and drying, so it is possible to extract parameters under the same conditions as the visual evaluation of the cosmetic finish.

[0109] Based on the above, while SEM and digital microscopes can also be used as means of acquiring the coating structure in this system, it is preferable to use visible light OCT.

[0110] (Adjustment of depth range and thickness parameters) Furthermore, the cosmetic finish information server 100 can evaluate the non-uniformity of light penetration to the substrate (slide glass, model skin, artificial leather, skin, etc.) by adjusting the analysis depth range of the OCT image and introducing thickness-related parameters such as the attenuation amount of interference light intensity in the depth direction and the depth at which a predetermined threshold intensity is reached. This allows for highly accurate quantification of unevenness in the thickness direction.

[0111] (Improved accuracy in estimating heterogeneity by comparing with facial skin information) Furthermore, the cosmetic finish information server 100 can acquire reflected light from the facial skin to be evaluated before applying the cosmetic product as an image or interference signal, calculate the surface shape parameters and internal structure parameters of the facial skin, and determine the difference with the coating film parameters obtained on the sample substrate, thereby further improving the accuracy of estimating the non-uniformity of the finish quality.

[0112] (Other embodiments: Prediction of changes in finish quality over time) The inventors have further discovered that it is possible to estimate the time-dependent changes in the quality of the finish (gloss quality, cover quality) during the drying process after coating. As shown in Figure 21, a cosmetic is uniformly applied to a glass slide substrate with a 25 μm applicator, and the coating film structure is sequentially acquired by visible light OCT at multiple time points from immediately after coating until drying is complete (e.g., immediately after coating, 1 minute, 2 minutes, 10 minutes, up to approximately 128 minutes). The cosmetic finish information server 100 calculates the aforementioned coating film parameters such as Sa, Sal, Sku, Ssk, and thickness-related parameters from the OCT images at each time point, and sequentially inputs them into a regression equation (or machine learning model) of the visual evaluation value, thereby estimating the time-dependent changes in texture (rate of change, inflection point, convergence time, etc.).

[0113] (Combination of product and process information) Furthermore, the cosmetic finish information server 100 can improve the accuracy of estimating the rate of change in gloss quality and cover quality during the drying process, as well as the timing of significant changes, by adding product information and manufacturing process information such as powder type and particle size distribution, fine / coarse particle ratio, aqueous phase / oil phase ratio, additives, coating film thickness, and ambient conditions (temperature and humidity) as explanatory variables. This makes it possible to suggest a recommended waiting time until the applied cosmetic reaches the user's desired finish level, and to identify and present the factors causing differences in finish (excess or insufficient waiting time after application).

[0114] (Application) This embodiment is useful for optimizing drying dynamics during formulation studies in the development stage, and for providing guidance on the time required to achieve the desired finish after application during in-store consultations.

[0115] (others) In the embodiment described above, the finish evaluation value was shown as one of four levels (an integer). However, the finish evaluation value may also be the numerical value obtained from the regression equation described above.

[0116] In the above-described embodiment, the counselor terminal 300 or user terminal 400 transmitted the user's desired finish information to the cosmetic finish information provision server 100, extracted the finish evaluation information of cosmetics having evaluation values ​​that matched the information, and transmitted it to the counselor terminal 300 or user terminal 400 as the graph described above. Alternatively, the counselor terminal 300 or user terminal 400 may transmit, for example, a cosmetic ID identifying a specific cosmetic product of interest to the cosmetic finish information provision server 100, extract the finish evaluation information of that cosmetic product, and transmit it to the counselor terminal 300 or user terminal 400 as the graph described above.

[0117] In the above-described embodiment, a regression equation for evaluation estimation was stored as cosmetic finish relationship information. However, the cosmetic finish relationship information is not limited to this, and for example, a machine learning model that has been trained to output an evaluation value using the above-mentioned coating film parameters as input may also be stored.

[0118] In the above-described embodiment, a coating image of a cosmetic coating applied to a slide glass as a sample substrate was used to generate cosmetic finish relationship information (regression equation as correlation information). However, instead, a coating image of a cosmetic coating applied to a skin model or actual skin as a sample substrate may be used.

[0119] In the embodiment described above, only one makeup finish information providing server 100 is shown, but the processing performed by the makeup finish information providing server 100 may be distributed and executed across multiple servers. For example, the process of generating makeup finish relationship information (regression equation as correlation information) and the process of providing makeup finish evaluation information using the said makeup finish relationship information may be executed on separate servers.

[0120] Of the inventions described in the claims of this application, the invention described as "information processing method" is one in which each step is performed automatically by at least one device such as a computer through information processing by software, and not by a human using a computer or other device. In other words, the "information processing method" is an information processing method using computer software, and not a method in which a human operates a computer as a calculating tool. [Explanation of Symbols]

[0121] 11…CPU 18...Storage section 19… Communications Department 31…Paint film image database 32…Makeup Finish Related Information Database 33…Makeup Finish Evaluation Information Database 81…Finished product evaluation graph 100...Makeup finish information server 200… Developer terminal 300... Counselor terminal 400…User terminal

Claims

1. A storage unit stores correlation information for multiple cosmetics between visual evaluation values ​​regarding the quality of glossiness or coverage of the cosmetic applied to the subject's skin and coating parameters obtained by analyzing the coating structure in a sample coating image obtained by capturing reflected light from a sample of the cosmetic coating applied to a sample substrate or by extracting interference signals. The image of the target coating obtained by capturing the reflected light of the newly applied specific cosmetic coating or by extracting interference signals is received. The coating structure in the aforementioned target coating image is analyzed to calculate the coating parameters. Based on the calculated coating parameters and the stored correlation information, an evaluation value for the glossiness or coverage quality of the specific cosmetic is estimated, and evaluation information corresponding to the estimated evaluation value is generated and transmitted. Control unit and An information processing system equipped with the following features.

2. The storage unit stores the correlation information for each combination of multiple different types of coating parameters. The control unit calculates at least two selected coating parameters from a plurality of coating parameters for the received target coating image. The information processing system according to claim 1.

3. The control unit generates numerical information indicating the quality of gloss, or gloss level information corresponding to said numerical information, on a numerical axis where the numerical value showing the clearest gloss is set as the first limit value and the numerical value showing the foggiest gloss is set as the second limit value, as evaluation information. The information processing system according to claim 1 or 2.

4. The control unit generates numerical information indicating the quality of the coverage, or level information of the coverage corresponding to the numerical information, on a numerical axis where the value indicating the coverage that retains the most natural skin feel is the first limit value and the value indicating the thickest coverage is the second limit value, as evaluation information. The information processing system according to claim 1 or 2.

5. The control unit generates information indicating the quality of gloss and coverage in one quadrant of a Cartesian coordinate system consisting of a first numerical axis where the value representing the clearest gloss is the first limit value and the value representing the most foggy gloss is the second limit value, and a second numerical axis where the value representing the coverage that retains the most natural skin feel is the third limit value and the value representing the thickest coverage is the fourth limit value. The information processing system according to claim 1 or 2.

6. The control unit estimates evaluation values ​​for the gloss quality and coverage quality by calculating at least one parameter from the target coating image as the coating parameter, which is selected from arithmetic mean height (Sa), minimum autocorrelation length (Sal), crutosys (Sku), and skewness (Ssk). The information processing system according to claim 1 or 2.

7. The control unit estimates the evaluation value of the cosmetic finish from the target coating image using the surface shape parameter calculated for the surface shape of the coating and the internal structure parameter calculated for the internal structure of the coating as coating parameters. The information processing system according to claim 1 or 2.

8. The control unit calculates at least one of the following as coating film parameters: a dispersion parameter indicating the variability of the surface shape or internal structure of the coating film; a parameter indicating the periodicity of the two-dimensional structure; a parameter indicating the bias or sharpness of the structural distribution; a parameter indicating the particle size of the structure; or a parameter indicating the coating film thickness; and estimates an evaluation value regarding the non-uniformity of the cosmetic finish based on the calculated parameter. The information processing system according to claim 1 or 2.

9. The control unit calculates the difference between the coating parameters calculated from the target coating image and the skin structure parameters calculated by capturing the reflected light of the subject's skin before application of the specific cosmetic or by extracting interference signals, and estimates an evaluation value regarding the non-uniformity of the finish quality based on this difference. The information processing system according to claim 8.

10. The control unit receives a visible light OCT (Optical Coherence Tomography) image obtained as the target coating image, and calculates the coating parameters based on the visible light OCT image. The information processing system according to claim 1 or 2.

11. The control unit calculates the coating parameters at each of the target coating images acquired at multiple different time points after the application of the cosmetic, and estimates the time-dependent changes in the gloss quality and / or coverage quality based on the time-dependent changes in the coating parameters. The information processing system according to claim 1 or 2.

12. The control unit calculates a recommended waiting time for the specific cosmetic to reach a predetermined finish level after application, based on the estimated results of the change over time, and outputs information indicating the recommended waiting time as evaluation information. The information processing system according to claim 11.

13. The control unit estimates the change over time using at least one external piece of information, including the type or particle size distribution of the powder, the ratio of the aqueous phase to the oil phase, additives, coating film thickness, temperature, or humidity, and the coating film parameters, as explanatory variables. The information processing system according to claim 11 or 12.

14. A storage unit stores correlation information for multiple cosmetics between visual evaluation values ​​regarding the quality of glossiness or coverage of the cosmetic applied to the subject's skin and coating parameters obtained by analyzing the coating structure in a sample coating image obtained by capturing reflected light from a sample of the cosmetic coating applied to a sample substrate or by extracting interference signals. The image of the target coating obtained by capturing the reflected light of the newly applied specific cosmetic coating or by extracting interference signals is received. The coating structure in the aforementioned target coating image is analyzed to calculate the coating parameters. Based on the calculated coating parameters and the stored correlation information, an evaluation value for the glossiness or coverage quality of the specific cosmetic is estimated, and evaluation information corresponding to the estimated evaluation value is generated and transmitted. Information processing methods.

15. In an information processing device, The process involves storing correlation information for multiple cosmetics between visual evaluation values ​​regarding the quality of glossiness or coverage of the cosmetic applied to the subject's skin and coating parameters obtained by analyzing the coating structure in a sample coating image obtained by capturing reflected light from a sample of the cosmetic coating applied to a sample substrate or by extracting interference signals, and the visual evaluation values ​​regarding the cosmetic finish. The steps include receiving an image of a target coating obtained by capturing the reflected light of a newly applied specific cosmetic coating or by extracting interference signals from the coating, The steps include: analyzing the coating structure in the aforementioned coating image and calculating coating parameters; The steps include: estimating an evaluation value for the glossiness or coverage quality of the specific cosmetic product based on the calculated coating parameters and the stored correlation information, generating and transmitting evaluation information corresponding to the estimated evaluation value; A program that executes the command.

Images