JP7512167B2 - Skin Classification Based on Blemish Distribution in Cheek Images - Google Patents

Description

The present invention relates to the analysis of human skin, and more specifically to skin classification based on the distribution of blemishes in cheek images.

Age spots (pigmented spots) are caused by the deposition of pigment on the skin, and refer to a state in which pigmentation is so severe that the boundary between pigmented and non-pigmented areas is clear. The main pigment components are melanin and hemoglobin.

A device is known that is used to acquire an image of a subject's face in order to analyze blemishes (Patent Document 1). A method is known for determining the amount of components in the skin based on an image acquired using such a device, and such a method can be used to determine the amount of melanin, hemoglobin, and other components in the skin (Patent Documents 2 and 3). In addition, the condition of blemishes on each person's cheeks, i.e., the number of blemishes present, and the size and darkness of the blemishes, can be quantified using the blemish analysis method disclosed in Patent Document 4. However, there is no classification method or algorithm for determining what blemish patterns exist.

Utility Model No. 3171344 Patent No. 3727807 Patent No. 3798550 Patent No. 6138745

Skin condition indicators calculated as average values by age group do not necessarily match actual changes that occur with aging in individuals. For example, it is thought that by conducting long-term follow-up surveys of how an individual's skin condition changes over time, it would be possible to build an algorithm that predicts changes in individual skin conditions, but until now, there have been no classification methods or algorithms that can determine what types of spots there are.

The present disclosure provides techniques for patterning and classifying blemishes. More specifically, the present disclosure relates to the following aspects:
[1] A method for evaluating a distribution pattern of spots on a subject, comprising the steps of: acquiring a plurality of distribution parameters related to spots from a skin image; constructing distribution information using at least two of the distribution parameters; and determining the distribution pattern of spots on the subject using the distribution information.
[2] The method of embodiment 1, further comprising the steps of: acquiring multiple color parameters relating to blemishes and/or multiple color parameters of normal areas from the skin image; constructing color information using at least one of the color parameters; and determining a distribution pattern of blemishes in the subject using the distribution information and the color information.
[3] The method according to embodiment 1 or 2, further comprising a step of visualizing the distribution information and/or color information.
[4] The method according to any one of embodiments 1 to 3, further comprising a step of visualizing the distribution pattern of spots on the subject.
[5] A method for evaluating a skin condition based on a distribution pattern of spots of a subject evaluated by the method according to any one of embodiments 1 to 4.
[6] A method for recommending an appropriate cosmetic, agent, or cosmetic method to a subject based on the distribution pattern of spots of the subject evaluated by the method according to any one of aspects 1 to 4.
[7] A method for providing a subject with safety information about a cosmetic, drug, or cosmetic method, based on the distribution pattern of spots of the subject evaluated by the method according to any one of aspects 1 to 4.
[8] An apparatus comprising: a parameter acquisition unit that acquires parameters relating to a plurality of distributions of blemishes from a skin image; and a skin classification generation unit that uses at least two of the parameters to cluster a distribution pattern of the blemishes and generate a skin classification.
[9] The device according to embodiment 8, further comprising an evaluation unit that determines a distribution pattern of spots from the skin image of the subject based on the generated skin classification.
[10] The device described in embodiment 9, further comprising a skin condition evaluation unit that evaluates the condition of the skin based on the determined distribution pattern of spots, a recommendation unit that recommends cosmetics, drugs, or cosmetic methods, or a safety information provision unit that provides the subject with safety information regarding the cosmetics, drugs, or cosmetic methods.
[11] A program for causing a computer to execute the steps of: acquiring parameters relating to a plurality of distributions of blemishes from a skin image; and clustering the distribution pattern of blemishes using at least two of the parameters to generate a skin classification.
[12] The program according to embodiment 11, further comprising a step of determining a distribution pattern of spots from a skin image of the subject based on the generated skin classification.
[13] The program according to embodiment 12, further comprising at least one of the steps of: evaluating the skin condition based on the determined distribution pattern of spots; recommending a cosmetic, drug or cosmetic method; or providing the subject with safety information regarding the cosmetic, drug or cosmetic method.

Figure 1 shows an example of the results of cluster analysis of the number of spots and the maximum spot area obtained from cheek images of a population of 456 subjects, which were classified into 16 clusters. FIG. 2A shows an example of the configuration of an apparatus according to the present disclosure. FIG. 2B shows an example configuration of an apparatus according to the present disclosure. FIG. 2C shows an example configuration of an apparatus according to the present disclosure. FIG. 3 shows an example of the configuration of a system according to the present disclosure. FIG. 4 is a diagram illustrating an example of a hardware configuration capable of implementing the processing according to the present disclosure. FIG. 5A is a flowchart showing an example of processing (program) by the device according to the present disclosure. FIG. 5B is a flowchart showing an example of processing (program) by the device according to the present disclosure. FIG. 5C is a flowchart showing an example of processing (program) by the device according to the present disclosure.

[Evaluation of distribution pattern of spots]
One aspect of the present disclosure relates to a method for evaluating a distribution pattern of age spots in a subject. In some embodiments, the method for evaluating a distribution pattern of age spots according to the present disclosure includes (i) acquiring a plurality of distribution parameters of age spots from a skin image, (ii) constructing distribution information using at least two of the distribution parameters, and (iii) determining a distribution pattern of age spots in the subject using the distribution information.

Some aspects of the present disclosure also relate to a method for evaluating a distribution pattern of spots on a subject, further comprising, in addition to the above steps (i) to (iii), (iv) acquiring multiple color parameters related to spots and/or multiple color parameters of normal areas from the skin image, (v) constructing color information using at least one of the color parameters, and (vi) determining a distribution pattern of spots on the subject using the distribution information and the color information.

The parameters related to the distribution include, for example, the number of spots, the average area of spots, the maximum area of spots, the total area of spots, the maximum area ratio, the total area ratio, and the variance of the spot area. The color parameters include, for example, L ^* , a ^* , b ^* , C ^* _ab , _hab , melanin, and hemoglobin. These parameters can be obtained, for example, using the method and device described in Patent No. 6138745 ("Spot evaluation device and spot evaluation program"). The area may be calculated, for example, based on the number of pixels in the image data.

To briefly explain an example of how to obtain the above parameters, first, a facial image of the subject is taken using a facial image acquisition system consisting of, for example, a diffuse lighting box and a digital camera, and then a skin image of a specific area (for example, around the eyes or cheeks) is obtained from the acquired facial image. As a facial image acquisition system, a device such as that described in the applicant's Registered Utility Model No. 3170125 can be used.

Images captured by the above-mentioned facial image acquisition system can be captured using diffuse light, for example, to reduce the effects of reflections and shadows on the skin surface, and it is possible to measure the "color" of the skin in the captured area and obtain skin color information.

The device described in the aforementioned Patent No. 6138745 performs image processing on the acquired skin image and can extract blemish areas from the analysis area of the skin image. For example, it can calculate color data Lab values, melanin components, hemoglobin components, and other pigment components of a specified analysis area of the skin image. In addition, the device described in Patent No. 6138745 can convert the analysis area into a distribution state of pigment components such as melanin components and hemoglobin components. For example, by acquiring RGB values of the RGB color system captured by a face image acquisition system as skin color information, or XYZ values of the XYZ color system converted from the RGB color system, it can convert into a distribution state of pigment components such as melanin components and hemoglobin components.

Using the method of Patent No. 3798550 etc., it is possible to perform multiple regression analysis of an absorbance model in which the transmittance in Lambert-Beer's law is replaced with the reflectance of the skin from the reflectance spectrum of the skin and the absorption coefficient spectrum of the constituents of the skin to determine the amount of components in the skin. Furthermore, using the method of Patent No. 3727807 etc., it is possible to perform multiple regression analysis of the color measurement value of the skin and the amount of components in the skin to obtain a multiple regression equation in advance, and use the multiple regression equation to obtain the amount of melanin components, hemoglobin components, etc. in the skin from the color measurement value of the skin.

In addition, binarization processing can be performed on the analysis area of the skin image using melanin components. In binarization processing, for example, a threshold value for the density of the melanin component is set to, for example, the average value + 0.01 to 0.30, and pixels having a melanin value (high melanin value) equal to or greater than the threshold value are determined to be high melanin areas. This makes it possible to distinguish between normal skin areas and high melanin areas. An area where pixels having continuous high melanin values are present can be recognized as a single pigmentation site (spot). Areas that are not recognized as spots can be classified as normal skin areas. Furthermore, the number of spots, the area of each spot, the average area of spots, the maximum area of spots, the total area of spots, the maximum area ratio, and the total area ratio, as well as the density of each spot, can be analyzed, and the quality of spots obtained from the analysis area of the skin image can be evaluated using the analysis results.

In the step (i) of acquiring parameters related to a plurality of distributions of blemishes from an image of the skin, the image of the skin may be an image including a facial cheek. Such images are acquired from a large population of subjects, e.g., 50 or more, 100 or more, 200 or more, 300 or more, 400 or more, 500 or more, 1000 or more, e.g., a population of about 500 subjects, to form a population for classification. Such images may also be acquired from the same subjects over time, e.g., every six months or yearly. As described above, the acquired images may be analyzed to acquire parameters related to a plurality of distributions of blemishes. The images acquired in this manner and the population of parameters related to a plurality of distributions of blemishes may be stored in a database.

In the above (ii) step of constructing distribution information using at least two of the parameters related to the distribution, cluster analysis (clustering) can be used to construct the distribution information. Clustering refers to dividing a set of objects to be classified into subsets that achieve internal cohesion and external separation. In some embodiments of the present disclosure, the k-means method, the k-means++ method, the X-means method, the DBSCAN method, and the like can be used for clustering, but are not limited to these. By performing cluster analysis, for example, the distribution pattern of spots derived from a group of subjects can be classified into multiple clusters. For example, in the k-means method, the number of clusters can be set arbitrarily, but may be set to any number between 3 and 30, for example between 4 and 20, and more specifically, for example, to be classified into 4, 6, 8, 10, 12, 14, or 16 clusters. The constructed distribution information or the results of the cluster analysis may be stored in a database.

The parameters used to construct the distribution information may be all the acquired parameters, or some parameters with low correlation may be selected and used as indices. In other words, the distribution information can be constructed using at least two of the parameters related to the distribution. For example, if seven (7-dimensional) parameters are acquired, two, three, four, five, or six of them may be selected and used. For example, if seven (7-dimensional) parameters, namely the number of spots, average spot area, maximum spot area, total spot area, maximum area ratio, total area ratio, and variance of spot area, are acquired from a skin image, at least two of them, for example, two or more parameters including the number of spots and the maximum area, may be selected and used to construct the distribution information. For example, if the number of spots and the maximum area are used as parameters to classify into about seven clusters, each cluster (distribution pattern of spots) can be given a name such as "no spots" or "scattered spots" to organize them.

In the above (iii) step of determining the distribution pattern of the subject's blemishes using the distribution information, the distribution pattern of the subject's blemishes is determined based on the distribution information constructed in the above step (ii). This can be done, for example, by calculating the distance between each cluster classified by cluster analysis and multiple parameters related to the distribution of blemishes obtained from an image of the subject's skin. For example, when a population is classified into multiple clusters in a two-dimensional vector space (plane) in which the number of blemishes and the maximum area are selected as parameters, the distance between the two-dimensional vector consisting of the number of blemishes and the maximum area obtained by analyzing an image of the subject's skin and the center of gravity of each cluster may be calculated, and it may be determined that the distribution pattern of the subject's blemishes belongs to the cluster with the closest distance. Alternatively, the parameters of the user's subject may be added to the parameters of the population and a cluster analysis may be performed to determine the cluster to which the distribution pattern of the subject's blemishes belongs.

Figure 1 shows the results of cluster analysis of the number of age spots and maximum age spot area obtained from cheek images of a subject population consisting of 456 people, and classification into 16 clusters. Thus, one more specific embodiment of the present disclosure relates to a method for evaluating a distribution pattern of age spots of a subject, the method including: (i) obtaining a plurality of distribution parameters of age spots from skin images of a plurality of individuals to form a parameter population; (ii) constructing distribution information using at least two of the distribution parameters, the parameters including at least the number of age spots and maximum age spot area, and the distribution information being obtained by cluster analysis; and (iii) using the distribution information to determine a cluster to which the distribution pattern of age spots of the subject belongs.

In the above step (iv) of acquiring multiple color parameters related to blemishes and/or multiple color parameters of normal areas from the skin image, the skin image may also be an image including the cheeks of the face. Such an image may be the same as that used in step (i) above. As described above, the acquired image may be analyzed to obtain the color parameters. The images and color parameters acquired in this manner may be stored in a database.

In the above step (v) of constructing color information using at least one of the color parameters, when multiple color parameters are used, cluster analysis (clustering) can be used to construct the color information, for example. The constructed color information or the results of the cluster analysis can be stored in a database.

In the above (vi) step of determining the distribution pattern of the subject's blemishes using the distribution information and the color information, the distribution pattern of the subject's blemishes is determined based on a combination of the distribution information and the color information. For example, after classifying skin into three types (e.g., fair skin, normal skin color, healthy skin color) based on the color information, the distribution pattern of the subject's blemishes can be determined using the distribution information.

[Information visualization]
In some embodiments of the present disclosure, the method for evaluating a distribution pattern of spots according to the present disclosure further comprises a step of visualizing the distribution information and/or color information. For example, the distribution information and/or color information can be mapped onto a two-dimensional plane and displayed in a color-coded manner for each cluster.

In addition, in some embodiments of the present disclosure, the method for evaluating the distribution pattern of spots according to the present disclosure further includes a step of visualizing the distribution pattern of spots of the subject. For example, it is possible to indicate where the distribution pattern of spots of the subject belongs in the mapping of the distribution information and/or color information onto a two-dimensional plane by marking or color coding.

[Evaluation of skin condition]
One aspect of the present disclosure relates to a method for evaluating a skin condition based on a distribution pattern of spots of a subject evaluated by the method according to the present disclosure. For example, when the distribution information of spots of a subject is obtained by the method according to the present disclosure and the distribution pattern of spots of the subject is classified into a specific cluster, the skin of the subject can be evaluated as being in a skin condition corresponding to the cluster. The skin condition corresponding to each cluster may be, for example, determined in advance and recorded in a database.

[Recommendation method]
One aspect of the present disclosure relates to a method for recommending an appropriate cosmetic, drug, or makeup method to a subject based on the distribution pattern of spots of the subject evaluated by the method according to the present disclosure. For example, when the distribution information of spots of the subject is obtained by the method according to the present disclosure and the distribution pattern of spots is classified into a specific cluster, the use of the same cosmetic, drug, or makeup method as that of other individuals classified into that cluster can be recommended to the subject. The cosmetic, drug, or makeup method recommended for each cluster may be, for example, determined in advance and recorded in a database.

[Provision of safety information]
One aspect of the present disclosure relates to a method for providing safety information on cosmetics, drugs, or cosmetic methods to a subject based on the distribution pattern of spots of the subject evaluated by the method of the present disclosure. For example, when the distribution information of spots of the subject is obtained by the method of the present disclosure and the distribution pattern of spots is classified into a specific cluster, the subject can be informed of safety information on the cosmetics, drugs, or cosmetic methods similar to that provided to other individuals classified into that cluster. The safety information on the cosmetics, drugs, or cosmetic methods associated with each cluster may be, for example, determined in advance and recorded in a database.

[Equipment/System]
One aspect of the present disclosure relates to an apparatus capable of generating a skin classification. In some aspects, the apparatus includes: (i) a parameter acquisition unit that acquires parameters related to a plurality of distributions of blemishes from a skin image; and (ii) a skin classification generation unit that uses at least two of the parameters to cluster a distribution pattern of the blemishes and generate a skin classification.

The device 100 illustrated in FIG. 2A includes a parameter acquisition unit 110 and a skin classification generation unit 120. The parameter acquisition unit 110 can acquire parameters related to a plurality of distributions of blemishes from a skin image. More specifically, as illustrated in FIG. 3 illustrating a system for evaluating a distribution pattern of blemishes on a subject, the parameter acquisition unit 110 can include a skin image acquisition unit 112 that receives a skin image of a subject population, a skin image analysis unit 114 that analyzes the input skin image to acquire parameters related to a plurality of distributions of blemishes, and a parameter database (DB) unit 116 that stores the acquired parameters. The skin image acquisition unit may further include hardware such as a camera for capturing a skin image, lighting, and a control processor. The skin classification generation unit 120 can include a clustering unit 122 that performs cluster analysis on parameters related to a plurality of distributions of blemishes, and a cluster DB unit 124 that stores cluster information obtained as a result of the cluster analysis. The device 100 can include a calculation unit such as a CPU (Central Processing Unit) and a storage device such as a hard disk or a flash memory. This storage device may store a program for controlling the device and acquired data (images, parameters, etc.). The calculation device may cause device 100 to function as parameter acquisition unit 110 and skin classification generation unit 120 by executing the program stored in the storage device. In other words, parameter acquisition unit 110 and skin classification generation unit 120 may be configured as functions of a CPU. Note that device 100 may operate in cooperation with the calculation device and storage device of a server connected via a network.

In some embodiments, the device according to the present disclosure may further include a distribution pattern evaluation unit 130 that determines a distribution pattern of blemishes from the skin image of the subject based on the generated skin classification (FIG. 2B). More specifically, as shown in FIG. 3 illustrating a system for evaluating a distribution pattern of blemishes on a subject, the distribution pattern evaluation unit 130 may include a skin image acquisition unit 132 that receives a user's skin image, a skin image analysis unit 134 that analyzes the input skin image to obtain multiple parameters related to the distribution of blemishes, and a blemish distribution pattern determination unit 136 that queries a cluster DB for the user's parameters to determine the skin classification. The skin image acquisition unit may further include hardware such as a camera that captures the user's skin image, lighting, and a control processor.

In some embodiments, the device according to the present disclosure may further include a skin condition evaluation unit 140 that evaluates the skin condition based on the determined distribution pattern of spots, a recommendation unit 150 that recommends cosmetics, drugs, or makeup methods, or a safety information provision unit 160 that provides safety information on cosmetics, drugs, or makeup methods to the subject (FIG. 2C). As shown in FIG. 3, which illustrates a system for evaluating the distribution pattern of spots on a subject, the skin condition evaluation unit 140, recommendation unit 150, and safety information provision unit 160 are collectively referred to as a value provision unit 170. Each of the value provision units may include a database (DB) that links the determined distribution pattern of spots with the information to be provided. Each of the value provision units may also include a display, printer, speaker, etc. for presenting information to the user.

FIG. 3 further illustrates a system for evaluating a distribution pattern of spots on a subject. As shown in FIG. 3, the system according to the present disclosure may include a spot distribution pattern visualization unit for illustrating the generated skin classification. In addition, all elements of the system according to the present disclosure do not need to be in the same location, and may be connected via a network.

[Hardware configuration]
Here, in the above-mentioned device, an execution program that can cause a computer to execute each function is generated, and processing can be performed by installing the execution program in, for example, a general-purpose personal computer, a server, etc., or a combination of these.

Here, we will explain, using diagrams, an example of the hardware configuration of a computer that can realize the processing related to this disclosure.

Figure 4 is a diagram showing an example of a hardware configuration capable of implementing the processing according to the present disclosure. The computer main body in Figure 4 is configured to have an input device 51, an output device 52, a drive device 53, an auxiliary storage device 54, a memory device 55, a CPU (Central Processing Unit) 56 that performs various controls, and a network connection device 57, which are interconnected by a system bus B.

The input device 51 has a keyboard and a pointing device such as a mouse that are operated by a user, and inputs various operation signals from the user, such as program execution. The input device 51 can also input various data, such as a facial image of the subject, obtained via a communication network from an external device connected to the network connection device 57, etc.

The output device 52 has a display that displays various windows and data necessary for operating the computer main body to perform the processing related to the present disclosure, and can display the progress and results of program execution using a control program held by the CPU 56. The output device 52 can also print the above-mentioned processing results on a print medium such as paper and present them to a user, etc.

Here, in this disclosure, the execution program installed in the computer main body is provided by a recording medium 58 such as a USB (Universal Serial Bus) memory, a CD-ROM, or a DVD. The recording medium 58 on which the program is recorded can be set in the drive device 53, and the execution program included in the recording medium 58 is installed in the auxiliary storage device 54 from the recording medium 58 via the drive device 53.

The auxiliary storage device 54 is a storage means such as a hard disk, and can store the execution program related to the present disclosure and the control program provided in the computer, and can perform input and output as needed.

The memory device 55 stores executable programs and the like read from the auxiliary storage device 54 by the CPU 56. The memory device 55 is composed of a ROM (Read Only Memory), a RAM (Random Access Memory), and the like.

The executable program may be downloaded in whole or in part from an external device via any network when necessary. Furthermore, the external device may be provided with an auxiliary storage device 54 in which the executable program is installed and/or a memory device 55 in which the installed executable program is stored. The external device may be a server. The server may be a specific server or an indefinite server such as a cloud platform. Furthermore, the executable program may be provided by a subscription-based service. A subscription-based service is one form of use of computer software, and is a service in which a fee is paid according to the period of use of the software. In this way, the form of use of the executable program may be any and is not limited.

The CPU 56 can control the overall processing of the computer, such as various calculations and data input/output to/from each hardware component, based on control programs such as the OS (Operating System) and execution programs stored in the memory device 55, to realize each process. Note that various information required during program execution can be obtained from the auxiliary storage device 54, and execution results can also be stored.

By connecting to a communication network or the like, the network connection device 57 can obtain the execution program from other terminals or the like connected to the communication network, and can provide the execution results obtained by executing the program or the execution program itself related to the present disclosure to other terminals or the like.

The hardware configuration described above makes it possible to execute the analysis process according to the present disclosure. In addition, by installing a program, the process according to the present disclosure can be easily realized on a general-purpose personal computer or the like.

[program]
Some aspects of the present disclosure relate to a program that causes a computer to execute various methods according to the present disclosure. From another perspective, the method according to the present disclosure may be a method that is executed in part or in whole on a computer. In some aspects, the program according to the present disclosure may be a program that causes a computer to execute the steps of (i) acquiring a plurality of parameters related to the distribution of blemishes from a skin image (step 100), and (ii) clustering the distribution pattern of blemishes using at least two of the parameters to generate a skin classification (step 110). FIG. 5A shows an example of processing by the device. Steps 100 to 110 are executed by a CPU of the device (which may include a server) executing the program.

In some embodiments, the program according to the present disclosure further includes a step of determining a distribution pattern of blemishes from the skin image of the subject based on the generated skin classification (step 120) (FIG. 5B). The program according to the present disclosure may include a step of receiving a user's skin image, a step of analyzing the input skin image to obtain a plurality of parameters related to the distribution of blemishes, and a step of determining the skin classification by querying the cluster DB for the user's parameters. The step of receiving the user's skin image may particularly include a step of receiving data from a camera that captures the user's skin image.

In some embodiments, the program according to the present disclosure further includes at least one of the steps of evaluating the skin condition (step 130), recommending a cosmetic, drug, or cosmetic method (step 140), or providing the subject with safety information about the cosmetic, drug, or cosmetic method (step 150) based on the determined distribution pattern of spots. An example of a process including these steps is shown in FIG. 5C. The program according to the present disclosure may include all of steps 130, 140, and 150. The program according to the present disclosure may further include the steps of querying a database (DB) and obtaining information to be provided based on the determined distribution pattern of spots, and outputting the obtained information to an output device (display, printer, speaker, etc.).

All documents referred to in this specification are incorporated herein by reference in their entirety. The technical scope of this disclosure is limited only by the claims, and the examples in this specification do not limit the technical scope of this disclosure. Modifications of this disclosure, such as additions, deletions, and substitutions of constituent elements of this disclosure, may be made without departing from the spirit of this disclosure.

51 Input Devices
52 Output Device
53 Drive device
54 Auxiliary Storage Device
55 Memory Device
56 CPU
57 Network connection device
58 Recording media
100 Equipment
110 Parameter Acquisition Unit
112 Skin image acquisition unit
114 Skin Image Analysis Unit
116 Parameter DB section
120 Skin Classification Generation Unit
122 Clustering Department
124 Cluster DB Section
130 Distribution Pattern Evaluation Unit
132 Skin image acquisition unit
134 Skin Image Analysis Unit
136 Spot distribution pattern determination unit
140 Skin Condition Evaluation Department
150 Recommendation Department
160 Safety Information Department
170 Value Providing Department
180 Spot distribution pattern visualization section
010 Subject population
020 User

Claims (14)

1. A method for evaluating a distribution pattern of age spots in a subject, comprising:
Obtaining parameters relating to a plurality of distributions of spots from a skin image;
A step of constructing a distribution pattern of spots as distribution information by cluster analysis using at least two of the parameters related to the distribution, and a step of determining the distribution pattern of spots of the subject using the distribution information. 2. The method of claim 1, wherein the distribution parameter is selected from the group consisting of number of blemishes, average blemish area, maximum blemish area, total blemish area, maximum blemish area percentage, total blemish area percentage, and variance of blemish area. obtaining a plurality of color parameters relating to blemishes and/or a plurality of color parameters of normal areas from the skin image;
The method of claim 1 or 2, further comprising: constructing color information using at least one of the color parameters; and determining a distribution pattern of blemishes in the subject using the distribution information and the color information. The method according to claim 1 , further comprising the step of visualizing the distribution information and/or color information. The method according to any one of claims 1 to 4 , further comprising a step of visualizing a distribution pattern of spots on the subject. A method for evaluating a skin condition based on a distribution pattern of spots of a subject evaluated by the method according to any one of claims 1 to 5 . A method for recommending an appropriate cosmetic, drug or makeup method to a subject based on the distribution pattern of spots of the subject evaluated by the method according to any one of claims 1 to 5 . A method for providing a subject with safety information regarding a cosmetic, drug or cosmetic method, based on the distribution pattern of spots of the subject evaluated by the method according to any one of claims 1 to 5 . A parameter acquisition unit that acquires parameters related to a plurality of distributions of spots from a skin image;
An apparatus for implementing the method according to any one of claims 1 to 8, comprising: a skin classification generating unit that uses at least two of the parameters to cluster the distribution pattern of spots through cluster analysis and generate a skin classification. The apparatus according to claim 9 , further comprising an evaluation unit for determining a distribution pattern of blemishes from the skin image of the subject based on the generated skin classification. The device of claim 10, further comprising a skin condition evaluation unit that evaluates the condition of the skin based on the determined distribution pattern of spots , a recommendation unit that recommends cosmetics, drugs or cosmetic methods, or a safety information provision unit that provides the subject with safety information regarding cosmetics, drugs or cosmetic methods. obtaining parameters relating to a plurality of distributions of blemishes from a skin image;
A program for implementing the method according to any one of claims 1 to 8, which causes a computer to execute a step of clustering the distribution pattern of spots by cluster analysis using at least two of the parameters to generate a skin classification. The program of claim 12 , further comprising a step of determining a distribution pattern of blemishes from a skin image of the subject based on the generated skin classification. The program of claim 13, further comprising at least one of a step of evaluating the skin condition based on the determined distribution pattern of spots, a step of recommending a cosmetic, drug or cosmetic method, or a step of providing the subject with safety information regarding the cosmetic, drug or cosmetic method.

Images