Information processing method, information processing device, program, and information processing system

Abstract

For example, we provide a new information processing method, information processing device, and program that can be used to evaluate uneven skin tone. [Solution] The information processing method performed on a computer according to this disclosure includes an acquisition step of acquiring an image that includes at least a part of the body of the subject, A division step is performed on an image that includes at least a part of the body of the subject, in which the colors of pixels with similar colors are merged based on the similarity of the colors of the pixels in the image and the positional relationship of the pixels, and each pixel of the image is divided into multiple regions based on the merged colors. This includes an evaluation step of evaluating the color non-uniformity of each divided region.

Description

[Technical Field]

[0001] This disclosure relates to information processing methods, information processing devices, programs, and information processing systems. [Background technology]

[0002] Skin tone unevenness affects the overall appearance of the skin. Therefore, methods for evaluating skin tone unevenness have been developed. Non-patent document 1 describes a method for evaluating red tone unevenness in the skin, as red tone unevenness significantly impacts skin appearance. [Prior art documents] [Non-patent literature]

[0003] [Non-Patent Document 1] Nippon Menard Cosmetics Co., Ltd., "Uneven skin redness is more important than wrinkles for a beautiful skin impression: Nippon Menard Cosmetics develops technology to score the condition of uneven skin tone", [online], September 16, 2021, atpress, [Retrieved February 17, 2025], Internet<URL:https: / / www.atpress.ne.jp / news / 275057> [Overview of the project] [Problems that the invention aims to solve]

[0004] However, evaluating the degree of redness in skin tone can be difficult depending on race.

[0005] Therefore, this disclosure aims to provide a new information processing method, information processing device, program, and information processing system that can be used, for example, to evaluate uneven skin tone. [Means for solving the problem]

[0006] To achieve the aforementioned objective, the information processing method performed on the computer of this disclosure (hereinafter also referred to as the "information processing method") includes an acquisition step of acquiring an image that includes at least a part of the body of the subject, A division step is performed on an image that includes at least a part of the body of the subject, in which the colors of pixels with similar colors are merged based on the similarity of the colors of the pixels in the image and the positional relationship of the pixels, and each pixel of the image is divided into multiple regions based on the merged colors. This includes an evaluation step of evaluating the color non-uniformity of each divided region.

[0007] The information processing device disclosed herein includes an acquisition unit that acquires an image including at least a part of the body of the subject, A division unit that, with respect to an image including at least a part of the body of the subject, merges the colors of pixels with similar colors based on the color similarity and positional relationship of the pixels in the image, and divides each pixel of the image into multiple regions based on the merged colors, It includes an evaluation unit that evaluates the color non-uniformity of each divided region.

[0008] The program disclosed herein is installed on a computer. An acquisition process to obtain an image that includes at least a part of the target's body, For an image including at least a part of the subject's body, a division process is performed in which the colors of pixels with similar colors are merged based on the color similarity and positional relationship of the pixels in the image, and each pixel of the image is divided into multiple regions based on the merged colors. An evaluation process is performed to assess the color non-uniformity of each divided region.

[0009] This disclosure includes the terminal and server, The aforementioned terminal and the aforementioned server are connected via a communication network. The aforementioned server includes an information processing device of the Disclosure, The server evaluates the color heterogeneity from the image transmitted from the terminal, which includes at least a part of the target's body. [Effects of the Invention]

[0010] According to the present disclosure, for example, uneven skin color can also be evaluated.

Brief Description of the Drawings

[0011] [Figure 1] FIG. 1 is a block diagram showing an example of an information processing system including an information processing apparatus according to Embodiment 1. [[ID=X]] [Figure 2] FIG. 2 is a block diagram showing the hardware configuration of the information processing apparatus according to Embodiment 1. [Figure 3] [[ID=1X]]FIG. 3 is a flowchart showing the information processing method and program according to Embodiment 1. [Figure 4] FIG. 4 is a schematic diagram showing an example of the processing of the image according to Embodiment 1. [Figure 5] FIG. 5 is a block diagram showing an example of an information processing system including an information processing apparatus according to Embodiment 2. [Figure 6] FIG. 6 is a flowchart showing the information processing method according to Embodiment 2. [Figure 7] FIG. 7 is a photograph showing an image of the skin of the cheek of the subject and an image after integration of colors in Example 1. [Figure 8] FIG. 8 is a graph showing the correlation between the skin age of the subject and the index value of color non-uniformity in Example 1. [Figure 9] FIG. 9 is a graph showing the results of the human skin monitoring test in Example 1.

Modes for Carrying Out the Invention

[0013] [[ID=X5]] Note: There seems to be a formatting issue in the original text where some line numbers are repeated or have an 'X' added in the translation for clarity in case there were any missing or incorrect line number references in the original. The tags - are preserved as they are.In this specification, “subject” means an animal, in particular a human.

[0014] In this specification, “topical skin preparation” means a preparation used for application to the skin. The topical skin preparation is preferably a preparation applied to the skin surface of the body, such as the face or body. Depending on the form of use, the topical skin preparation may take the form of an ampoule, capsule, powder, granules, liquid, gel, foam, emulsion, sheet, mist, spray, etc. Examples of the forms of use include pharmaceuticals; quasi-drugs; topical or systemic topical skin preparations; medicinal and / or cosmetic preparations applied to the scalp and hair; bath preparations used by adding them to bathwater; other preparations; etc. Examples of topical or systemic skin preparations include basic cosmetics such as lotions, emulsions, creams, ointments, oils, and packs; facial cleansers or skin cleansers such as bar soaps, liquid soaps, and hand washes; massage agents, cleansing agents, depilatory agents, hair removal agents, shaving agents, aftershave lotions, preshave lotions, shaving creams; makeup cosmetics such as foundations, lipsticks, blushes, eyeshadows, eyeliners, and mascaras; perfumes; nail care products, nail polish, nail polish removers; poultices, plasters, tapes, sheets, patches, aerosols; and mouthwashes and other gargles. Examples of medicinal and / or cosmetic preparations applied to the scalp and hair include shampoos, conditioners, hair treatments, pre-hair treatments, permanent solutions, hair dyes, hair styling products, hair tonics, hair growth and nourishing products, poultices, plasters, tapes, sheets, aerosols, etc. Examples of other preparations include deodorants or antiperspirants, antiperspirants, sanitary products, sanitary cotton, wet wipes, etc.

[0015] The present disclosure will be described in detail below with reference to the drawings and with examples. However, the present disclosure is not limited to the following description. In Figures 1 to 6 below, the same parts are denoted by the same reference numerals, and their descriptions may be omitted. Also, in the drawings, for the sake of explanation, the structure of each part may be shown in a simplified manner, and the dimensional ratios of each part may be shown schematically and may differ from the actual dimensions. Furthermore, unless otherwise specified, each embodiment and description is interchangeable with each other, and the descriptions can be used interchangeably. In this specification, when the expression "~" is used, it means that the numerical or physical values ​​before and after it are included. Also, in this specification, the expression "A and / or B" includes "A only," "B only," and "both A and B."

[0016] (Embodiment 1) Embodiment 1 relates to an information processing device and an information processing method of the present disclosure.

[0017] This embodiment is an example of an information processing device and information processing method of the present disclosure. Figure 1 is a schematic diagram of the information processing device 10 of Embodiment 1. As shown in Figure 1, the information processing device 10 mainly comprises an acquisition unit 11, a classification unit 12, and an evaluation unit 13. In this embodiment, the information processing device 10 is configured as a server on which the program of the present disclosure is installed.

[0018] The information processing device 10 may be a personal computer (PC) on which the program of this disclosure is installed, or it may be incorporated into a server or the like as part of a system. Alternatively, the information processing device 1 in this embodiment may be a system consisting of one or more computers or servers capable of executing the program of this disclosure, i.e., a cloud computing system. The personal computers may constitute a computer cluster. Although not shown in the figures, the information processing device 10 may be configured to connect to an external terminal of a system administrator via a communication network, allowing the system administrator to manage the information processing device 10 from the external terminal.

[0019] Figure 2 illustrates a block diagram of the hardware configuration of the information processing device 10. The information processing device 10 includes, for example, a CPU (Central Processing Unit) 101, memory 102, bus 103, storage device 104, input device 107, display 108, and communication device (communication unit) 109, which are all arithmetic elements. Each part of the information processing device 10 is connected via the bus 103 through its respective interface (I / F).

[0020] The CPU 101 operates in cooperation with other components via controllers (system controller, I / O controller, etc.) and is responsible for the overall control of the information processing device 10. In the information processing device 10, the CPU 101 executes the program 105, image 106, and other programs of this disclosure, and also reads or writes various types of information such as image 106. Specifically, in this embodiment, the CPU 101 functions as an acquisition unit 11, a sorting unit 12, and an evaluation unit 13. The information processing device 10 is equipped with a CPU 101 as an arithmetic unit (arithmetic element), but it may also be equipped with other arithmetic units such as a GPU (Graphics Processing Unit) or an APU (Accelerated Processing Unit), or a combination of the CPU and these. The CPU 101 may also function as, for example, the parts other than the storage unit in other embodiments (estimation unit, second evaluation unit, third evaluation unit).

[0021] Memory 102 includes main memory. This main memory is also called primary memory. When the CPU 101 performs processing, memory 102 reads various operational programs, such as the program 105 of this disclosure, which are stored in the storage device 104 (auxiliary storage device) described later. The CPU 101 then reads and decodes the data from memory 102 and executes the program. This main memory is RAM (random access memory). Memory 102 may further include ROM (read-only memory).

[0022] Bus 103 can also be connected to external devices. Examples of such external devices include external storage devices (external databases, etc.) and printers. The information processing device 10 can be connected to a communication network, for example, by a communication device 109 connected to bus 103, and can also be connected to external devices such as external servers and terminals via the communication network.

[0023] The storage device 104 is also called an auxiliary storage device, for example, in relation to the main memory (primary memory). As described above, the storage device 104 includes an operating program, including the program 105 of this disclosure. The storage device 104 may store data, including images 106, etc. The storage device 104 includes, for example, a storage medium and a drive for reading from and writing to the storage medium. The storage medium is not particularly limited and may be internal or external, and examples include HD (hard disk), FD (floppy disk), CD-ROM, CD-R, CD-RW, MO, DVD, flash memory, memory card, etc., and the drive is not particularly limited. The storage device 104 may be, for example, a hard disk drive (HDD) or solid state drive (SSD) in which the storage medium and the drive are integrated.

[0024] The information processing device 10 further includes an input device 107 and an output device, a display 108. The input device 107 may include, for example, a pointing device such as a touch panel, trackpad, or mouse; a keyboard; imaging means such as a camera or scanner; a card reader such as an IC card reader or magnetic card reader; or an audio input means such as a microphone. The display 108 may include, for example, an LED (light-emitting diode) display, an organic EL display, or a liquid crystal display. In this embodiment, the input device 107 and the display 108 are configured separately, but the input device 107 and the display 108 may be configured as an integrated unit, such as a touch panel display. Furthermore, in the information processing device 10, the input device 107 and the display 108 are of any configuration and may be omitted, or one or more of them may be included.

[0025] Next, an example of processing in the information processing device 10 of this embodiment will be explained using the flowchart in Figure 3 and the schematic diagram of the processing of image 106 in Figure 4, taking the case where image 106 is pre-stored in the storage device 104 as an example. In the explanation of the processing of the information processing device 10 of Embodiment 1, the example of evaluating the color non-uniformity of the skin (cheek) of a human being, as shown in Figure 4(A), will be used, but image 106 can also be applied to images that include other parts of the body. As shown in Figure 3, the information processing method and program of Embodiment 1 perform the processes S1 (image acquisition), S2 (categorization), and S3 (evaluation of non-uniformity) in this order. In the information processing method of Embodiment 1, step S2 includes the processes S2-1 (color integration) and S2-2 (categorization into regions).

[0026] In step S1, the acquisition unit 11 acquires one or more images 106 (S1). Specifically, the acquisition unit 11 acquires images 106 stored in the storage device 104 of the information processing device 10. The number of images 106 acquired by the acquisition unit 11 is not particularly limited. In Embodiment 1, the color system of the images 106 is the Lab color system.

[0027] Image 106 is an image of a body part (skin in Embodiment 1) in which the color non-uniformity of the subject is to be evaluated. The image may be an image of the entire body part, or an image of a part of the body part.

[0028] Next, in step S2, the division unit 12, with respect to the image 106 (Figure 4(B)) shown in region P of Figure 4(A), integrates the colors of pixels with similar colors based on the color similarity and positional relationship of the pixels within the image 106 (S2-1), and then divides each pixel of the image into multiple regions based on the integrated colors (S2-2). The image 106 acquired in step S1 reflects subtle color differences for each pixel. However, when humans perceive color variations (color unevenness), they do not perceive them as subtle color differences in accordance with the color system of the captured image 106, but rather as broad color differences. Therefore, in step S2, the division unit 12 first, when nearby pixels in the image 106 have similar colors, integrates similar colors to reduce the number of colors, thereby converting the image into one that shows the broad color differences that humans perceive. Then, the division unit 12 divides the image into regions for each color based on the image that shows the broad color differences.

[0029] In step S2-1, the division unit 12 performs clustering (superpixelization) based on the color of the pixels in the image 106, and this can be done by integrating the colors of pixels with similar colors. For example, clustering methods such as SLIC (Simple Linear Iterative Clustering) (Reference 1), k-means clustering, LSC (Linear Spectral Clustering), and SEEDS (Superpixels Extracted via Energy-Driven Sampling) can be used. This clustering can be performed, for example, using a superpixel program from OpenCV. Specifically, in step S2-1, the division unit 12 divides the image 106 into multiple clusters. In dividing into clusters, it is preferable to divide the image so that the positions of the centroids of each cluster are equally spaced, that is, so that the grid spacing S is constant. Furthermore, after dividing into clusters, the centroid of each cluster may be moved to the position where the color gradient is minimized by referring to a 3x3 pixel neighborhood centered on the centroid. Next, in step S2-1, the similarity D is calculated for the central pixel of each cluster. sCalculate it according to the following formulas (1) to (3). In the following formulas (1) and (2), the coordinates of the centroid of the cluster are (x k , y k ), and the pixel values are (l k , a k , b k ). Also, in the following formulas (1) and (2), the coordinates of the pixels of the similar determination target, that is, the other pixels in the cluster are (x i , y i ), and the pixel values are (l i , a i , b i ). Also, the ratio count m is usually a numerical value in the range of 1 to 20. When the value of m is large, pixel similarity is emphasized, and when the value of m is small, color similarity is emphasized, and clustering can be performed. m is usually set to 10. The clustering of each pixel is performed within the range that satisfies x k- S ≤ x k ≤ x k + S and y k- S ≤ y k ≤ y k + S. Reference 1: R. Achanta, A. Shaji, K. Smith, A. Lucchi, P. Fua and S. Susstrunk, "SLIC Superpixels Compared to State-of-the-Art Superpixel Methods," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 34, no. 11, pp. 2274-2282, Nov. 2012

Number

[0030] Next, in the S2-1 process, the classification unit 12 determines whether the pixel of the centroid and the pixel of the determination target are similar based on the obtained similarity D s . Specifically, in the S2-1 process, the obtained similarity Ds If the number exceeds a threshold (for example, 100 when the number of integrated independent regions (clusters) is gradually performed in the process of clustering within the measurement area), the division unit 12 determines that the centroid pixel and the pixel to be judged are not similar and proceeds to the processing of the next pixel to be judged. On the other hand, in step S2-1, the obtained similarity D s If the threshold is below the threshold, the classification unit 12 determines that the centroid pixel and the pixel to be judged are similar, and associates the pixel to be judged with the cluster of the centroid pixel. In other words, in step S2-1, the pixels of the judgment pair are assigned to the cluster of the centroid pixel. The threshold may be set such that, for example, the explanation of the number of specified colors described later can be used. In step S2-1, the same determination is made as to whether other pixels in the same cluster are similar to the centroid pixel. In step S2-1, the same determination is also made as to whether other pixels in other clusters are similar to the centroid pixel. In step S2-1, after the processing of all clusters is completed, the average value of the coordinates of each pixel and the average value of the pixel of each pixel are calculated for the centroid pixel of each cluster and the pixels associated with the centroid pixel (pixels belonging to the cluster). Then, in step S2-1, the coordinates and pixel values ​​of pixels belonging to the same cluster are changed to the average value of the calculated pixel coordinates and the average value of the pixel, respectively, to obtain a color-integrated image 106 (Figure 4(C)).

[0031] In the information processing device 10 of Embodiment 1, the S2-1 process may be repeated after the integration. In this case, the number of repetitions of the S2-1 process is usually around 10. Alternatively, the information processing device 10 of Embodiment 1 may count the number (types) of colors in the pixel image 106 after the S2-1 process integration and repeat the S2-1 process until the number of colors is less than or equal to a specified number of colors. The specified number of colors is, for example, 50 to 200, 75 to 150, or about 100. By setting the number of colors after integration to about 100 or less, the information processing device 10 of Embodiment 1 can, for example, convert the image 106 into an image that more closely resembles an image showing the rough color differences that humans perceive. The number of colors in the pixels after integration can also be, for example, the number of independent regions (clusters) that are integrated during the process of gradually performing clustering within the measurement area. For this reason, the information processing device 10 of Embodiment 1 may count the number of clusters after the S2-1 process integration and repeat the S2-1 process until the number of clusters is less than or equal to a specified number of clusters. The number of specified clusters can be exemplified by, for example, the number of specified colors.

[0032] Next, in step SS-2, the division unit 12 divides each pixel of the image 106 into multiple regions based on the integrated color. Specifically, in step S2-2, the division unit 12 divides the image 106 into regions where the coordinates and pixel values ​​of each pixel are the same.

[0033] Next, in step S3, the evaluation unit 13 evaluates the color non-uniformity of each divided region. Examples of the color non-uniformity include the color variation (standard deviation) of each region, the area of ​​each region, the rate of color change between each region and adjacent regions (color gradient), and the average value of the lightness (L value) of each region. The color non-uniformity may also be a value obtained by combining, for example, the color variation of each region, the area of ​​each region, the rate of color change between each region and adjacent regions (color gradient), and the average value of the lightness (L value) of each region. In this case, the information processing device 10 of Embodiment 1 sets variables and formulas for each index value (color variation (standard deviation) of each region, area of ​​each region, rate of color change between each region and adjacent regions (color gradient), and average value of the brightness (L value) of each region) in such a way that they correlate with items to be evaluated using the color non-uniformity (for example, the visual impression of the skin, skin age, hair waviness, distribution of gray hair, degree of hair dyeing, etc.). Then, in step S3, for example, the evaluation unit 13 uses the value obtained by multiplying each index by a variable as the evaluation value of the color non-uniformity of each region. The setting of the variables may be done using, for example, a large-scale language model such as GPT-4o, Claude, or Gemini, or a deep learning model. The evaluation value of the non-uniformity may be corrected by, for example, the average value of the brightness of each region.

[0034] Then, the information processing method of Embodiment 1 terminates.

[0035] (Effects of Embodiment 1) In the information processing device 10 of Embodiment 1, the division unit 12 integrates the colors of pixels with similar colors based on the color similarity and positional relationship of the pixels in the image 106. As a result, the information processing device 10 of Embodiment 1 can convert the image 106 into an image that shows the general color differences that humans perceive by integrating similar colors and reducing the number of colors. Therefore, by evaluating the color non-uniformity of the integrated image 106, the information processing device 10 of Embodiment 1 can evaluate color variations that are close to human perception, i.e., color non-uniformity. For this reason, the information processing device 10 of Embodiment 1 can, for example, evaluate skin tone unevenness that is close to human perception.

[0036] In the information processing device 10 of Embodiment 1, the color system of image 106 was the Lab color system. However, in this disclosure, the color system of image 106 may be other color systems, such as the RGB color system or the CMYK color system. When using an image with a color system other than the Lab color system as image 106, the information processing device 10 of Embodiment 1 may include a conversion step (conversion unit) to convert the color system of image 106 from the other color system to the Lab color system after acquiring image 106, or it may optionally include a detection step (detection unit) to detect the color system of image 106. As mentioned above, the visual impression of a person is highly correlated with the variation (non-uniformity) of the L value (luminance) among the color information of the Lab color system. For this reason, in the information processing device 10 of Embodiment 1, for example, by converting the color system of image 106 to the Lab color system and evaluating the color non-uniformity, an evaluation value of non-uniformity that can be suitably used for the visual impression of a person can be obtained. Furthermore, if the system includes the detection step (detection unit), the information processing device 10 of Embodiment 1, for example, if the detection step detects that the color system of image 106 is a color system other than the Lab color system, converts the color system of image 106 to the Lab color system in the conversion step. The detection of the color system can be performed, for example, from the color information of image 106. The conversion can also be performed, for example, by converting the coordinates of each color system to the corresponding coordinates of the Lab color system.

[0037] In the information processing device 10 of Embodiment 1, image 106 is an image including the skin of a human cheek, as shown in Figure 4(A). However, the disclosure is not limited thereto, and image 106 may also include other parts of the subject's body. These other parts of the body are, for example, parts that can be imaged by an imaging device such as a camera, and specific examples include hair, teeth, nails, etc.

[0038] (Embodiment 2) This embodiment is another example of an information processing device of the present disclosure. Figure 5 is a block diagram showing an information processing system 100 equipped with the information processing device 10A of this embodiment. As shown in Figure 5, the information processing device of this embodiment includes the information processing device 10A and a terminal 20. The information processing device 10A and the terminal 20 are configured to be interconnected via an external communication network 30. The information processing device 10A of this embodiment includes an estimation unit 14 and an output unit 15 in addition to the configuration of the information processing device 10 of Embodiment 1. The hardware configuration of the information processing device 10A is the same as that of the information processing device 10 of Figure 2, except that the CPU 101 has the configuration of the information processing device 10A of Figure 5 instead of the configuration of the information processing device 10 of Figure 1. Except for these points, the configuration of the information processing device 10A of Embodiment 2 is the same as the configuration of the information processing device 10 of Embodiment 1, and its description can be applied accordingly. In this embodiment, the information processing device 10A and the terminal 20 included in the information processing system 100 may be one or multiple. In this embodiment, the information processing device 10A is configured as a server on which the program of the present disclosure is installed.

[0039] Terminal 20 includes personal computers (PCs); mobile phones, smartphones, and tablets. Mobile devices such as redline devices; smartwatches, smart glasses, wearable devices; etc. The hardware configuration of terminal 20 is similar to that of information processing device 10, for example, and the explanation for that device can be applied.

[0040] The communication network 30 is not particularly restricted and can use any publicly known network, such as a wired or wireless network. Examples of communication networks 30 include the Internet, WWW (World Wide Web), telephone lines, LAN (Local Area Network), WiFi (Wireless Fidelity), etc.

[0041] Next, an example of the processing of the information processing system 100 equipped with the information processing device 10A of this embodiment will be explained using the flowchart in Figure 6. As shown in Figure 6, the information processing method and program of Embodiment 2 include steps S1 to S3 of the information processing method of Embodiment 1, as well as S4 (estimation of visual impression) and S5 (output to terminal). In the information processing method of Embodiment 2, S5 is an optional step and may or may not be included.

[0042] First, the information processing system 100 of this embodiment performs steps S1 to S3 in the same manner as the information processing device 10 of Embodiment 1.

[0043] Next, in step S4, the estimation unit 14 estimates the visual impression of the object based on the color non-uniformity. As shown in the embodiments described later, the visual impression of the object, for example, the age of the object, and the visual impression of the skin, correlate with the color non-uniformity. Therefore, in step S4, for example, the visual impression of the object is estimated from the color non-uniformity based on the correlation between the color non-uniformity and the visual impression of the object. The visual impression of the object can be evaluated, for example, by subjective evaluation using a monitor.

[0044] Then, in step S5, the evaluation of non-uniformity obtained in step S3 and the visual impression of the object obtained in step S4 are output to terminal 20 via the communication network 30. Terminal 20 then displays the output data on its display or other display unit.

[0045] Then, the information processing system of embodiment 2 terminates its processing.

[0046] (Effects of Embodiment 2) The information processing system 100 of Embodiment 2 can estimate the visual impression of the subject by utilizing the color non-uniformity of the image 106. Therefore, according to the information processing system 100 of Embodiment 2, evaluation items that use a part of the subject's body as an indicator, such as visual impression and age, can be evaluated.

[0047] In the information processing system 100 of Embodiment 2, the appearance of the target, such as the appearance of the target's skin and the target's age, was estimated based on the color non-uniformity of the image 106. However, the present disclosure is not limited thereto, and the color unevenness of the target's skin may be evaluated based on the image 106 which includes skin. Furthermore, if the image 106 is an image which includes hair, the waviness of the target's hair, the distribution of gray hair in the target, the degree of hair dyeing in the target, etc., may be evaluated based on the color non-uniformity of the image 106.

[0048] In the information processing system 100 of Embodiment 2, for example, a topical skin preparation for the target may be suggested based on the color non-uniformity of image 106. As mentioned above, the color non-uniformity correlates with the appearance of the target, such as the appearance of the target's skin and the target's age. Therefore, in the information processing system 100 of Embodiment 2, for example, by pre-setting the suggested topical skin preparations according to the numerical range of the index value of the color non-uniformity, a topical skin preparation suitable for the target's skin can be suggested based on the color non-uniformity of the target.

[0049] (Embodiment 3) The program of this embodiment is a program that causes a computer to execute the information processing method described herein. In the program of this embodiment, "processing" can also be expressed as, for example, "procedure" or "instruction". The program of this embodiment may also be recorded on, for example, a computer-readable storage medium. The storage medium is, for example, a non-transitory computer-readable storage medium. The storage medium is not particularly limited and includes, for example, random access memory (RAM), read-only memory (ROM), hard disk (HD), solid state drive (SSD), optical disc, floppy disk (FD), and the like. [Examples]

[0050] Next, embodiments of the present disclosure will be described. However, the present disclosure is not limited in any way by the following embodiments.

[0051] [Example 1] We confirmed that the index value of color non-uniformity obtained by the information processing method of Embodiment 1 correlates with the age of human skin.

[0052] Images containing approximately the same area of ​​cheek skin were obtained for the same subject at predetermined ages (38, 40, 41, 42, 43, 44, and 47 years old) (Figure 7(A)). For each age group containing cheek skin images, segmentation was performed using SLIC registered in OpenCV so that the number of color types (number of segments) in the image was 100 or less, thereby integrating the colors and dividing the regions in the image (Figure 7(B)).

[0053] For the obtained image (Figure 7(B)), the variation (standard deviation) of the color (Lab) of each region, the area of ​​each region (segment), the rate of color change (color gradient) between each region and adjacent regions, and the average value of the brightness (L value) of each region were calculated. Next, variables and formulas for each index value were set using a large-scale language model so that they correlate with the age of the target skin, which is an item to be evaluated using the obtained index values.

[0054] As a result, the L value (ω L ), a value (ω a ), b value (ω b ), area of ​​each region, color gradient (ω grad The variables for the average L value (correction coefficient) were set to L value:a value:b value:area of ​​each region:color gradient = 3:2:1.5:1:2:0.03, and the index value of color heterogeneity (corrected hybrid score) calculated using the following equations (3) to (12) correlated with the age of the target skin. Note that the values ​​in the following equations (6) to (12) are the corrected L value (L i '), a value (a i ') and b value (b i It is calculated using '). Also, the average value of the L value in formula (11) below is the corrected L value (L) of each segment. i This is the average value of '). The results are shown in Figure 8.

number

[0055] Figure 8 is a graph showing the correlation between the age of the target skin and the index value of color heterogeneity. In Figure 8, the horizontal axis represents the age of the target skin, and the vertical axis represents the index value of color heterogeneity. As shown in Figure 8, the index value of color heterogeneity showed a high correlation with the age of the target skin (r=0.7196) (age / score: 38 / 4.68, 40 / 4.78, 41 / 5.12, 42 / 5.66, 43 / 6.85, 44 / 7.42, 47 / 9.06).

[0056] [Example] Human skin monitoring test Using the information processing method described in Example 1, we investigated whether a plant extract (peony extract) could suppress uneven skin tone in human skin. Prior to the above investigation, a lotion and a placebo lotion to be used in a human skin monitoring test were prepared. The lotion used in the human skin monitoring test (Formulation Example 1) was prepared with the ingredients and proportions listed in Table 1 below. The placebo lotion (Comparative Formulation Example 1) was prepared with the ingredients and proportions listed in Table 2 below.

[0057] [Table 1]

[0058] [Table 2]

[0059] A monitoring test was conducted by applying the lotion described in Table 1 and the placebo lotion described in Table 2 to designated areas on the faces of normal human subjects (four women with an average age of 46). The monitoring test was conducted between November 18, 2024 and December 24, 2024. The lotion described in Table 1 was applied to a designated area on one side of the subject's face (Formulation Example 1), and the lotion described in Table 2 was applied to a designated area on the other side of the subject's face (Comparative Formulation Example 1). The application was performed twice a day (morning and evening) at intervals of four weeks. In the monitoring test, the designated areas were photographed using a camera on the day of application, two weeks after application, and four weeks after application. For the images obtained from the photography, an index value of color non-uniformity was calculated using the same method as the information processing method in Example 1. For the obtained index values ​​of color non-uniformity, the relative value of color non-uniformity was calculated using the index value of color non-uniformity on the day of application (0w) as the base (100). These results are shown in Figure 9.

[0060] Figure 9 is a graph showing the results of a human skin monitoring test. In Figure 9, the vertical axis shows the relative value when the index value of color non-uniformity on the day of application start (0w) is set to 100, and the horizontal axis shows the number of weeks (w) from the day of application start. In Figure 9, the value for comparative formulation example 1 after 2 weeks was 107.2, the value for comparative formulation example 1 after 4 weeks was 107.5, the value for formulation example 1 after 2 weeks was 88.7, and the value for formulation example 1 after 4 weeks was 77.5. As shown in Figure 9, the index value of color non-uniformity was lower in formulation example 1 after 4 weeks of application compared to comparative formulation example 1 after 4 weeks of application. From these results, it was found that peony extract suppresses color unevenness.

[0061] While the present disclosure has been described above with reference to embodiments and examples, the present disclosure is not limited to the above embodiments and examples. Various modifications to the structure and details of the present disclosure are possible, which will be understood by those skilled in the art within the scope of the present disclosure.

[0062] <Note> Some or all of the above embodiments and examples may be described as follows, but are not limited to the following. <Information Processing Methods> (Note 1) A division step in which, with respect to an image that includes at least a part of the subject's body, the colors of pixels with similar colors are merged based on the color similarity and positional relationship of the pixels in the image, and each pixel of the image is divided into multiple regions based on the merged colors, A computer-based information processing method, comprising an evaluation step of evaluating the color non-uniformity of each divided region. (Note 2) The information processing method described in Appendix 1, wherein the division step divides the image into a plurality of clusters, and integrates the colors of pixels with similar colors based on the color similarity and positional relationship of the pixels in each cluster. (Note 3) The information processing method described in Appendix 2, wherein in the division step, the plurality of clusters are divided such that the centers of each cluster are equally spaced. (Note 4) The information processing method according to any one of the appendices 1 to 3, wherein the sorting step evaluates the similarity of the colors based on the Euclidean distance between the pixels. (Note 5) The information processing method according to any one of the appendices 1 to 4, wherein the sorting step involves repeatedly merging the colors of pixels with similar colors until the number of colors after merging in the image is less than or equal to the number of specified colors. (Note 6) The information processing method according to any one of the appendices 1 to 5, wherein the evaluation step involves evaluating the non-uniformity using an index selected from a group consisting of the color variation of each region, the area of ​​each region, the rate of color change between each region and adjacent regions, and the average value of the brightness of each region. (Note 7) The information processing method according to any one of the appendices 1 to 6, wherein the evaluation step involves calculating an index value of non-uniformity using the color variation of each region, the area of ​​each region, and the rate of color change between each region and adjacent regions, thereby evaluating the non-uniformity. (Note 8) The information processing method described in Appendix 7, wherein the evaluation step corrects the non-uniformity index value by the average value of the brightness of each region. (Note 9) The aforementioned color is a color defined in the Lab color system, as described in any of the information processing methods described in Appendix 1 to 8. (Note 10) An information processing method according to any one of the appendices 1 to 9, which includes a conversion step of converting the color system of the aforementioned image to the Lab color system. (Note 11) The information processing method according to any one of the appendices 1 to 10, wherein the part of the body is skin, hair, teeth, and / or nails. (Note 12) The information processing method according to Appendix 11, which includes an estimation step of estimating the visual impression of the object based on the aforementioned non-uniformity. (Note 13) The aforementioned visual impression is age, as described in the information processing method in Appendix 12. (Note 14) The aforementioned image includes skin, An information processing method according to any one of Appendix 1 to 10, comprising a second evaluation step of evaluating the color unevenness of the target skin based on the aforementioned non-uniformity. (Note 15) The aforementioned image is an image that includes hair, An information processing method according to any one of Appendix 1 to 10, comprising a third evaluation step of evaluating the waviness of the target hair, the distribution of gray hair in the target, and / or the degree of hair dyeing in the target, based on the aforementioned non-uniformity. <Information Processing Device> (Note 16) A division unit that, with respect to an image including at least a part of the subject's body, merges the colors of pixels with similar colors based on the color similarity and positional relationship of the pixels in the image, and divides each pixel of the image into multiple regions based on the merged colors, A computer-operated information processing device, including an evaluation unit that evaluates the color non-uniformity of each divided region. (Note 17) The information processing apparatus described in Appendix 16, wherein the division unit divides the image into a plurality of clusters and integrates the colors of pixels with similar colors based on the color similarity and positional relationship of the pixels in each cluster. (Note 18) The information processing apparatus according to Appendix 17, wherein the division unit divides the plurality of clusters so that the centers of each cluster are equally spaced. (Note 19) The information processing apparatus according to any one of appendices 16 to 18, wherein the division unit evaluates the similarity of the colors based on the Euclidean distance between the pixels. (Note 20) The information processing device according to any one of appendices 16 to 19, wherein the division unit repeatedly performs color merging of pixels with similar colors until the number of colors after merging in the image is less than or equal to the number of specified colors. (Note 21) The information processing apparatus according to any one of appendices 16 to 20, wherein the evaluation unit evaluates the non-uniformity using an index selected from the group consisting of the color variation of each region, the area of ​​each region, the rate of color change between each region and adjacent regions, and the average value of the brightness of each region. (Note 22) The information processing apparatus according to any one of appendices 16 to 21, wherein the evaluation unit evaluates the non-uniformity by calculating an index value of non-uniformity using the color variation of each region, the area of ​​each region, and the rate of color change between each region and adjacent regions. (Note 23) The information processing apparatus described in Appendix 22, wherein the evaluation unit corrects the index value of the non-uniformity with the average value of the brightness of each region. (Note 24) The aforementioned color is a color defined in the Lab color system, as described in any of the appendices 16 to 23 of the information processing device. (Note 25) An information processing device according to any one of appendices 16 to 24, including a conversion unit that converts the color system of the aforementioned image to the Lab color system. (Note 26) The information processing apparatus according to any one of appendices 16 to 25, wherein the part of the body is skin, hair, teeth, and / or nails. (Note 27) The information processing apparatus according to Appendix 26, comprising an estimation unit for estimating the visual impression of the object based on the aforementioned non-uniformity. (Note 28) The aforementioned visual impression is age, as described in Appendix 27 of the information processing device. (Note 29) The aforementioned image includes skin, An information processing apparatus according to any one of appendices 16 to 25, comprising a second evaluation unit for evaluating the color unevenness of the target skin based on the aforementioned non-uniformity. (Note 30) The aforementioned image is an image that includes hair, An information processing apparatus according to any one of appendices 16 to 25, comprising a third evaluation unit that evaluates the waviness of the target hair, the distribution of gray hair in the target, and / or the degree of hair dyeing in the target, based on the aforementioned non-uniformity. <Program> (Note 31) On the computer, For an image containing at least a part of the subject's body, a division process is performed in which the colors of pixels with similar colors are merged based on the color similarity and positional relationship of the pixels in the image, and each pixel of the image is divided into multiple regions based on the merged colors. A program that performs an evaluation process to assess the color non-uniformity of each divided region. (Note 32) The program described in Appendix 31 divides the image into multiple clusters and merges the colors of pixels with similar colors based on the color similarity and positional relationship of the pixels in each cluster. (Note 33) The program described in Appendix 32 divides the multiple clusters so that the centers of each cluster are equally spaced. (Note 34) The program described in any of appendices 31 to 33 evaluates the similarity of the colors based on the Euclidean distance between the pixels in the classification process. (Note 35) The program described in any of appendices 31 to 34, wherein the sorting process repeatedly performs color merging of pixels with similar colors until the number of colors after merging in the image is less than or equal to the number of specified colors. (Note 36) The program described in any of appendices 31 to 35 evaluates the non-uniformity using an index selected from a group consisting of the color variation of each region, the area of ​​each region, the rate of color change between each region and adjacent regions, and the average value of the brightness of each region. (Note 37) The program described in any of appendices 31 to 36 evaluates the non-uniformity by calculating an index value of non-uniformity using the color variation of each region, the area of ​​each region, and the rate of color change between each region and adjacent regions. (Note 38) The program described in Appendix 37 corrects the non-uniformity index value by the average value of the brightness of each region in the evaluation process. (Note 39) The aforementioned color is a color defined in the Lab color system, as specified in any of the programs listed in appendices 31 to 38. (Note 40) A program according to any one of the appendices 31 to 39, which includes a conversion process to convert the color system of the aforementioned image to the Lab color system. (Note 41) The program described in any of the appendices 31 to 40, wherein the part of the body is skin, hair, teeth, and / or nails. (Note 42) The program described in Appendix 41, which includes an estimation process for estimating the visual impression of the object based on the aforementioned non-uniformity. (Note 43) The aforementioned visual impression is age, as described in Appendix 42 of the program. (Note 44) The aforementioned image includes skin, A program according to any one of appendices 31 to 40, comprising a second evaluation process for evaluating the color unevenness of the target skin based on the aforementioned non-uniformity. (Note 45) The aforementioned image is an image that includes hair, A program according to any one of appendices 31 to 40, comprising a third evaluation process for evaluating the waviness of the target hair, the distribution of gray hair in the target, and / or the degree of hair dyeing in the target, based on the aforementioned non-uniformity. <Recording medium> (Note 46) A computer-readable recording medium on which a program described in any of the appendices 31 to 45 is recorded. <System> (Note 47) Including terminals and servers, The aforementioned terminal and the aforementioned server are connected via a communication network. The server includes an information processing device as described in any of appendices 16 to 30. The server is an information processing system that evaluates color heterogeneity from an image transmitted from the terminal, which includes at least a part of the target's body. [Explanation of Symbols]

[0063] 10 Information Processing Devices 11 Acquisition Department 12 Section 13 Evaluation Department 14 Estimation part 15 Output section 101 CPU 102 memory 103 Bus 104 Storage device 105 Programs 106 images 107 Input device 108 displays 109 Communication devices

Claims

1. An acquisition step to obtain an image that includes at least a part of the target's body, A division step is performed on an image that includes at least a part of the body of the subject, in which the colors of pixels with similar colors are merged based on the similarity of the colors of the pixels in the image and the positional relationship of the pixels, and each pixel of the image is divided into multiple regions based on the merged colors. A computer-based information processing method, comprising an evaluation step of evaluating the color non-uniformity of each divided region.

2. The information processing method according to claim 1, wherein the division step divides the image into a plurality of clusters, and integrates the colors of pixels with similar colors based on the color similarity and positional relationship of the pixels in each cluster.

3. The information processing method according to claim 1 or 2, wherein the sorting step involves repeatedly merging the colors of pixels with similar colors until the number of colors after merging in the image is less than or equal to the number of specified colors.

4. The information processing method according to any one of claims 1 to 3, wherein the evaluation step evaluates the non-uniformity using an index selected from the group consisting of the color variation of each region, the area of ​​each region, the rate of color change between each region and adjacent regions, and the average value of the brightness of each region.

5. The information processing method according to any one of claims 1 to 4, wherein the evaluation step involves calculating an index value of non-uniformity using the color variation of each region, the area of ​​each region, and the rate of color change between each region and adjacent regions, thereby evaluating the non-uniformity.

6. The information processing method according to claim 5, wherein in the evaluation step, the index value of the non-uniformity is corrected by the average value of the brightness of each region.

7. The information processing method according to any one of claims 1 to 6, wherein the aforementioned color is a color defined in the Lab color system.

8. The information processing method according to any one of claims 1 to 7, wherein the part of the body is skin, hair, teeth, and / or nails.

9. The information processing method according to claim 8, further comprising an estimation step of estimating the visual impression of the object based on the aforementioned non-uniformity.

10. The aforementioned visual impression is age, according to the information processing method of claim 9.

11. The aforementioned image includes skin, The information processing method according to any one of claims 1 to 7, further comprising a second evaluation step of evaluating the color unevenness of the target skin based on the aforementioned non-uniformity.

12. An acquisition unit that acquires an image including at least a part of the target's body, A division unit that, with respect to an image including at least a part of the body of the subject, merges the colors of pixels with similar colors based on the color similarity and positional relationship of the pixels in the image, and divides each pixel of the image into multiple regions based on the merged colors, An information processing apparatus including an evaluation unit that evaluates the color non-uniformity of each divided region.

13. Including terminals and servers, The aforementioned terminal and the aforementioned server are connected via a communication network. The server includes the information processing device described in claim 12, The server is an information processing system that evaluates color heterogeneity from an image transmitted from the terminal, which includes at least a part of the target's body.

Images