JP4921222B2 - Cosmetic adhesion state analysis method, cosmetic adhesion state analysis device, cosmetic adhesion state analysis program, and recording medium on which the program is recorded - Google Patents

Description

  The present invention relates to a cosmetic adhesion state analysis method, a cosmetic adhesion state analysis apparatus, a cosmetic adhesion state analysis program, and a recording medium on which the program is recorded, and in particular, the cosmetic adhesion state from a skin image with high accuracy. The present invention relates to a cosmetic adhesion state analysis method, a cosmetic adhesion state analysis device, a cosmetic adhesion state analysis program, and a recording medium on which the program is recorded.

  Conventionally, in the field of makeup counseling and the like, various methods for analyzing the state of skin and the state of makeup are proposed. For example, there is a method of photographing a local surface condition of skin such as skin fine lines, pores, spots, freckles, etc. with a microscope or the like and analyzing the photographed contents (for example, Patent Document 1, Patent Document 2, etc.) See).

In the technique disclosed in Patent Document 1 or Patent Document 2, light is irradiated to an observation site of the skin using a microscope, a local image of the irradiated skin is acquired, and analysis of the surface state of the skin is performed from the acquired image. It is carried out.
JP 2003-24283 A JP-A-7-323013

  As described above, conventionally, there is a method for analyzing the evaluation of bare skin such as fine lines, pores, spots, freckles, etc., using a local image of the skin (skin) of a subject acquired from a measuring instrument equipped with a microscope. It was.

  However, there has been no technique for digitizing the state of adhesion of the cosmetic applied to the skin of the subject using the optimum parameters and analyzing with high accuracy from the digitized results.

  The present invention has been made in view of the above-described problems, and is a cosmetic adhesion state analysis method, a cosmetic adhesion state analysis apparatus, and a cosmetic adhesion for analyzing the adhesion state of cosmetics from a skin image with high accuracy. It is an object to provide a state analysis program and a recording medium on which the program is recorded.

  In order to solve the above-described problems, the present invention employs means for solving the problems having the following characteristics.

  The invention described in claim 1 is a cosmetic adhesion state analysis method for analyzing the adhesion state of a cosmetic using a skin image of a predetermined range of a photographed subject, and is applied from the skin image to the subject's skin. Obtained from the analysis step of analyzing at least one of the applied amount, non-uniformity, and roughness of the applied cosmetic and analyzing the applied state of the cosmetic, the skin image, and the analyzing step And an accumulating step for accumulating the analysis result in association with the subject information.

  According to the first aspect of the present invention, the adhesion state of the cosmetic applied to the skin of the subject is accurately determined using at least one of the parameters of the adhesion amount, the non-uniformity, and the roughness. Can be analyzed. Thereby, the adhesion state of cosmetics can be evaluated objectively and with good reproducibility, and can be utilized for evaluation and development of products and raw materials, for example.

  According to a second aspect of the present invention, in the analysis step, when the adhesion amount is digitized, a ternary image is acquired from the skin image, the number of pixels of the acquired ternary image, and the skin The adhesion amount is quantified based on the saturation of the green image extracted from the image.

  According to the second aspect of the present invention, noise (dust) contained in the skin image can be reduced, and the amount of adhesion can be acquired accurately.

  According to a third aspect of the present invention, in the analyzing step, when the non-uniformity is digitized, a standard deviation of a gradation of a green image extracted from the skin image and a ternary value obtained from the skin image are obtained. The non-uniformity is quantified on the basis of the flatness of the hide portion of the digitized image.

  According to the third aspect of the present invention, it is possible to acquire the non-uniformity with higher accuracy by acquiring the non-uniformity using the flatness of the hill part of the ternary image obtained from the skin image. it can.

  In the invention described in claim 4, when the analysis step digitizes the roughness, the number of pixels of the entire ternary image obtained from the skin image and the cosmetic material are attached thickly. Roughness is digitized based on the number of pixels in the portion.

  According to the fourth aspect of the present invention, by using the number of pixels of the entire ternary image obtained from the skin image and the number of pixels of the portion where the cosmetic material is thickly attached, the degree of roughness ( Aggregation degree) can be obtained.

  The invention described in claim 5 is characterized in that the analysis step analyzes the finish of makeup from at least one of the amount of adhesion, non-uniformity, and roughness of the cosmetic.

  According to the fifth aspect of the present invention, it is possible to establish a new finish evaluation method for makeup that is also used in stores, for example.

  The invention described in claim 6 has a photographing step of photographing the skin image by a photographing means, and the photographing step uses reflected light obtained by irradiating the skin of the subject with illumination in the photographing means. When receiving light, it is filtered by a polarizing filter.

  According to invention of Claim 6, a regular reflection component can be removed with a polarizing filter, and the skin image to which cosmetics were apply | coated can be image | photographed clearly.

  The invention described in claim 7 is a cosmetic adhesion state analyzing apparatus that analyzes an adhesion state of a cosmetic using a skin image of a predetermined range of a photographed subject, and applies the skin image to the subject's skin. Obtained from the analysis means for analyzing the adhesion state of the cosmetic by digitizing at least one of the applied amount, non-uniformity, and roughness of the applied cosmetic, the skin image, and the analysis means It has a storage means for storing the analysis result in association with the subject information.

  According to the seventh aspect of the present invention, the adhesion state of the cosmetic applied to the skin of the subject is accurately determined using at least one of the parameters of the adhesion amount, the non-uniformity, and the roughness. Can be analyzed. Thereby, the adhesion state of cosmetics can be evaluated objectively and with good reproducibility, and can be utilized for evaluation and development of products and raw materials, for example.

  According to an eighth aspect of the present invention, when the analysis unit digitizes the adhesion amount, the analysis unit acquires a ternary image from the skin image, the number of pixels of the acquired ternary image, and the skin The adhesion amount is quantified based on the saturation of the green image extracted from the image.

  According to the eighth aspect of the present invention, noise (dust) contained in the skin image can be reduced, and the adhesion amount can be acquired accurately.

  According to a ninth aspect of the present invention, when the non-uniformity is digitized, the analysis unit calculates a standard deviation of a gradation of a green image extracted from the skin image and a ternary value obtained from the skin image. The non-uniformity is quantified on the basis of the flatness of the hide portion of the digitized image.

  According to the ninth aspect of the present invention, it is possible to acquire the non-uniformity with higher accuracy by acquiring the non-uniformity using the flatness of the hill part of the ternary image obtained from the skin image. it can.

  According to a tenth aspect of the present invention, when the analysis means digitizes the roughness, the number of pixels of the entire ternary image obtained from the skin image and the cosmetic material are attached thickly. Roughness is digitized based on the number of pixels in the portion.

  According to the tenth aspect of the present invention, by using the number of pixels of the entire ternary image obtained from the skin image and the number of pixels of the portion where the cosmetic material is thickly attached, the degree of roughness ( Aggregation degree) can be obtained.

  The invention described in claim 11 is characterized in that the analysis means analyzes the finish of makeup from at least one of the amount of adhesion, non-uniformity, and roughness of the cosmetic.

  According to the eleventh aspect of the present invention, for example, it is possible to establish a new makeup finish evaluation method that is also used in stores.

  The invention described in claim 12 includes photographing means for photographing the skin image, and the photographing means receives irradiation light and reflection when receiving reflected light obtained by illuminating the skin of the subject. A polarizing filter is provided on the light path.

  According to the twelfth aspect of the present invention, the specular reflection component can be removed by the polarizing filter, and the skin image to which the cosmetic is applied can be clearly photographed.

  The invention described in claim 13 is a cosmetic adhesion state analysis program for operating a computer so as to execute the cosmetic adhesion state analysis method according to any one of claims 1 to 6. is there.

  According to the invention of claim 13, the adhesion state of the cosmetic applied to the skin of the subject is accurately determined using at least one of the parameters of the adhesion amount, the non-uniformity, and the roughness. Can be analyzed. Further, by installing the program, it is possible to easily realize the analysis of the state of adhesion of the cosmetic material according to the present invention using a general-purpose personal computer or the like.

  The invention described in claim 14 is a computer-readable recording medium on which the cosmetic material adhesion state analysis program according to claim 13 is recorded.

  According to the fourteenth aspect of the present invention, the cosmetic adhesion state analysis program can be easily installed on a plurality of other computers using a recording medium. Further, by installing the program, it is possible to easily realize the analysis of the state of adhesion of the cosmetic material according to the present invention using a general-purpose personal computer or the like.

  ADVANTAGE OF THE INVENTION According to this invention, the adhesion state of the cosmetics apply | coated to the test subject's skin can be analyzed with high precision.

<Outline of the present invention>
The present invention obtains a skin image of a predetermined range, such as a local area or the whole after makeup, and analyzes the adhesion state of the cosmetic from the acquired skin image in order to analyze the adhesion state of the cosmetic on the skin and the like. The analysis is performed using at least one of the adhesion amount, non-uniformity, and roughness (cohesion) of the cosmetic. In addition, the cosmetics in the present invention include powders (solid), liquids and the like, and components applied to the skin (skin) regardless of the shape and components thereof. Materials that can be attached (coated) are also included. That is, the present invention can be applied to the analysis of the adhesion state of all powders applied to the surface of an object, for example.

  DESCRIPTION OF EXEMPLARY EMBODIMENTS Hereinafter, embodiments of a cosmetic adhesion state analysis method, a cosmetic adhesion state analysis apparatus, a cosmetic adhesion state analysis program, and a recording medium on which the program is recorded according to the present invention will be described with reference to the drawings. .

<System configuration>
FIG. 1 is a diagram illustrating an example of a schematic configuration of a cosmetic adhesion state analysis system according to the present invention. A cosmetic adhesion state analysis system 10 shown in FIG. 1 is configured to include a skin observation device 11 and a cosmetic adhesion state analysis device 12, and the skin observation device 11 and the cosmetic adhesion state analysis device 12 are connected to the Internet. And a communication network 13 typified by LAN (Local Area Network) or the like so that data can be transmitted and received.

  The skin observation apparatus 11 captures an image of a subject whose cosmetics are applied to the skin using, for example, a CCD (Charge Coupled Device) camera, and acquires an image in a predetermined range such as a local area or the entire skin of the subject. In addition, the skin observation apparatus 11 can also measure at least one information among pores, wrinkles, spots, skin colors, and the like. In addition, the skin observation apparatus 11 transmits each piece of information as a measurement result such as a photographed skin image of a predetermined range to the cosmetic adhesion state analysis apparatus 12 via the communication network 13.

  The cosmetic adhesion state analysis device 12 is based on the skin image transmitted from the skin observation device 11 and at least one of the adhesion amount, the non-uniformity, and the roughness level of the cosmetic applied to the skin of the subject. Digitize one. Moreover, the cosmetics adhesion state analysis apparatus 12 analyzes the cosmetics adhesion state from the digitized results. The cosmetic adhesion state analysis device 12 can also analyze at least one of pores, wrinkles, spots, skin color, and the like.

  In addition, the cosmetic adhesion state analysis device 12 accumulates the skin image and the analysis result in association with the subject information, the date information on which the measurement or analysis was performed, and the like. Thereby, not only the display of the skin image and the analysis result thereof but also the analysis based on the age distribution and the change over time and the result thereof can be displayed on the display screen.

  The system configuration shown in FIG. 1 is roughly configured to have one skin observation device 11 and one cosmetic adhesion state analysis device 12, but the system configuration in the present invention is not particularly limited. A plurality of observation apparatuses 11 and / or cosmetics adhesion state analysis apparatuses 12 may be provided. Moreover, each structure for imaging | photography of the test subject's skin in the skin observation apparatus 11 may be provided in the cosmetics adhesion state analyzer 12, and the image used as the basis for analyzing the adhesion state of the cosmetics apply | coated to skin Or the like already exists, the skin observation device 11 may not be provided.

<Skin Observation Device 11>
Next, a functional configuration example of the skin observation apparatus 11 will be described with reference to the drawings. FIG. 2 is a diagram illustrating an example of a functional configuration of the skin observation apparatus. The skin observation apparatus 11 shown in FIG. 2 is configured to include an input unit 21, an output unit 22, a member management unit 23, a photographing unit 24, a storage unit 25, a transmission / reception unit 26, and a control unit 27. ing.

  The input means 21 accepts input of various data when performing registration of a member (subject) who performs analysis or the like on the adhesion state of cosmetics, registration of measurement execution date, and the like from a user or the like. In addition, the input unit 21 receives a shooting (measurement) execution instruction, a data transmission instruction to the cosmetics adhesion state analysis apparatus 12, and the like from a user or the like. The input means 21 is composed of a pointing device such as a keyboard and a mouse.

  Further, the output unit 22 displays the content input by the input unit 21, the content executed based on the input content, etc. on the screen, and performs voice output or the like. Note that the output means 22 includes a display, a speaker, and the like. Furthermore, the output means 22 may have a function such as a printer. In that case, the measurement result can be printed on a print medium such as paper and provided to a user, a subject, or the like.

  Moreover, the member management means 23 manages member information (subject information) such as personal information of members and the number of measurements. Specifically, the member management means 23 can register members, call member information that has already been registered and stored in the storage means 25, and perform reference, correction, deletion, and the like.

  The contents registered as member information include, for example, “identification No.”, “name”, “birth date”, “gender”, “photographing” for identifying each member and photographing (measurement) contents, etc. There are “parts”, “memos (remarks)”, and the like. The member information to be registered is not particularly limited in the present invention. For example, “member age” may be registered instead of “birth date”. Further, when calling a predetermined member from member information stored in the storage means 25 or the like, it is possible to search using the above-mentioned “identification No.”, “name”, or the like.

  The photographing means 24 captures (measures) a skin image in a predetermined range where the subject's cosmetic is applied from a CCD camera or the like, and acquires a digital image. The predetermined range is, for example, the entire face or a part of a preset face (local part) when photographing cosmetics applied to the face of the subject.

  Note that the analysis process using the photographed skin image can be continuously performed over time (time series) using history information. Therefore, it is necessary to prevent a difference in the position of the skin image taken over time. Therefore, the imaging unit 24 displays (previews) a part to be imaged by the subject at the time of imaging on a screen such as a display, and for example, the user or the like guides the subject while viewing the preview screen so that a predetermined part is imaged be able to. Note that a photographing method in the photographing unit 24 will be described later.

  Note that in the cosmetic adhesion state analyzing apparatus 12 described later, when analyzing at least one of pores, wrinkles, blotches, skin color, and the like, the imaging unit 24 may view the entire face of the subject at a plurality of angles (for example, front, right Face, left face, etc.), flash photography as illumination, photography using diffused light, etc. can be used selectively.

  The accumulating unit 25 accumulates various information such as the member information obtained by the member managing unit 23 and the skin image obtained by the photographing unit 24. In addition, the storage unit 25 stores the skin image obtained from the photographing unit 24 in association with member information and date / time information of photographing (measurement).

  The transmission / reception means 26 is a communication interface for transmitting / receiving data between the skin observation apparatus 11 and the cosmetics adhesion state analysis apparatus 12 via the communication network 13. Therefore, in the skin observation apparatus 11, the transmission / reception means 26 receives a request for acquiring various information such as member information and skin images from the cosmetic adhesion state analysis apparatus 12, or the input means 21 sends the request to the cosmetic adhesion state analysis apparatus 12. When the transmission instruction of the various information is received, the various information is transmitted to the cosmetics adhesion state analyzer 12 via the communication network 13.

  In addition, the control unit 27 controls the entire components of the skin observation apparatus 11. More specifically, for example, control is performed such that a photographed skin image is accumulated in the accumulating unit 25 together with member information, or member registration or an image acquired by photographing is transmitted from the transmission / reception unit 26 to the cosmetic adhesion state analyzing apparatus 12 I do.

<Shooting Method in Shooting Unit 24>
Here, a specific photographing technique in the photographing unit 24 will be described. FIG. 3 is a diagram illustrating an example of a configuration of a head unit in the photographing unit.

  As shown in FIG. 3, when acquiring a skin image to which cosmetics are applied in this embodiment, illumination light 30-1 from illumination provided in the photographing means 24 in order to acquire a skin image in advance. A skin image is acquired by irradiating the skin 31 to which cosmetics are applied with 30-2 and receiving reflected light 32 obtained by the irradiation with a CCD camera.

  Here, in the skin image capturing in the present embodiment, polarization filters 33-1 to 33-3 are provided in the paths of the illumination light 30 and the reflected light 32 as shown in FIG. In this way, the regular reflection component of the illumination light 30 and the reflected light 32 can be removed by the polarizing filter 33, whereby a skin image to which cosmetics such as a foundation are attached can be clearly photographed. Further, by using this skin image for analysis of the state of adhesion of the cosmetic material described later, highly accurate analysis can be realized.

  Further, when the photographing unit 24 analyzes at least one of pores, wrinkles, blotches, skin color, etc., for example, it acquires an image by flash photographing of the front face for pore analysis, or the left and right side faces for wrinkle analysis Images can also be acquired by flash photography, or images can be obtained by diffuse light photography of the sides of the left and right faces for use in spot and skin color analysis.

<Cosmetic condition analysis device 12>
Next, a functional configuration example of the cosmetics adhesion state analysis device 12 will be described with reference to the drawings. FIG. 4 is a diagram illustrating an example of a functional configuration of the cosmetic adhesion state analyzing apparatus. 4 includes an input unit 41, an output unit 42, a member management unit 43, an analysis unit 44, a display screen generation unit 45, a storage unit 46, and a transmission / reception unit 47. , And control means 48.

  The input means 41 is used by a user such as a makeup counselor to instruct member information stored in the storage means 46 and the like, and to instruct and analyze various information obtained from the skin observation apparatus 11, and the analysis result Accepts input of various data when giving instructions for screen display. The input means 41 is composed of a pointing device such as a keyboard and a mouse, for example.

  Further, the output unit 42 displays the content input by the input unit 41, the content executed based on the input content, etc. on the screen, and performs voice output or the like. Note that the output means 22 includes a display, a speaker, and the like. Furthermore, the output means 22 may have a function of a printer or the like. In that case, the analysis result or the like can be printed on a print medium such as paper and provided to the user or the subject.

  The member management unit 43 manages member information (subject information) such as the member's personal information and the number of measurements and the number of analyzes stored in the storage unit 46. Specifically, the member management unit 43 can register a member, call member information that has already been registered and stored in the storage unit 46, and perform reference, correction, deletion, and the like. The member information stored in the storage means 46 is substantially the same as the contents registered in the skin observation apparatus 11 described above, but also includes information such as the number of times analyzed by the analysis means 44 and the analysis date and time. It is.

  The analysis unit 44 analyzes the adhesion state of the cosmetic applied to the skin of the subject based on various information such as a skin image obtained from the skin observation apparatus 11. The analysis unit 44 uses at least one of the amount of cosmetic adhesion, the non-uniformity, and the roughness (cohesion) as a parameter for analyzing the adhesion state of the cosmetic. The analysis unit 44 quantifies these parameters and analyzes the adhesion state of the cosmetic based on the quantified values.

  The analyzing means 44 analyzes the finish of the subject's makeup by digitizing the parameters described above. As a result, for example, a new makeup finish evaluation method and the like that can be used in stores can be established. The specific contents of the analysis method in this embodiment will be described later.

Further, the analysis unit 44 performs pore analysis using, for example, an image obtained by flash photography of the front face, performs wrinkle analysis by flash photography of the left and right side faces, acquires images, and diffuses the left and right side faces. It is possible to perform spot color analysis by blotting with light photography.
Alternatively, at least one of pores, wrinkles, blotches, skin color, and the like may be analyzed by acquiring an image obtained by flash photography of the left and right side faces, an image obtained by photographing the diffused light of the side faces of the left and right faces.

  The display screen generation unit 45 selects a predetermined part or region (XY coordinate or region of the center of the analysis target) to be analyzed by the analysis unit 44 from image information such as a skin image acquired from the skin observation device 11 or the like. A screen for executing the analysis processing in the present embodiment, a screen for displaying the analysis results, a screen for displaying the results analyzed in the past, and the like.

  The display screen generation unit 45 outputs the generated content to the output unit 42 and displays it on the screen. The user gives a predetermined instruction from the screen generated by the display screen generating means 45 using the input means 41 such as a mouse, and analyzes the adhesion state of the cosmetic applied to the skin of the subject in this embodiment. It can be carried out.

  The storage unit 46 stores member information and various image data obtained from the skin observation apparatus 11, analysis results obtained from the analysis unit 44, and the like. The storage means 46 stores image data, analysis results, and the like in association with member (subject) information, various date information such as measurement date and time, analysis date and time. Thereby, the historical information for every subject mentioned above can be accumulated, and various data can be acquired in time series, for example, as needed.

  In order to reduce the data capacity in the storage means 46, the analysis result is not stored in the storage means 46, but only necessary information such as an image is read out and analyzed by the analysis means 44 only when there is an analysis instruction. You may perform the process which displays a result.

  The transmission / reception means 47 is a communication interface for performing transmission / reception of data between the cosmetic adhesion state analysis device 12 and the skin observation device 11 via the communication network 13. Therefore, the cosmetic adhesion state analysis device 12 receives various information acquired by the skin observation device 11 by the transmission / reception means 47. The cosmetic adhesion state analyzing apparatus 12 transmits various information acquisition requests from the transmission / reception means 47 to the skin observation apparatus 11. If there is information that has not yet been transmitted, the transmission / reception means 47 receives the information. Can do.

  The control means 48 controls the entire components of the cosmetic material adhesion state analyzer 12. Specifically, various types of information obtained from the skin observation apparatus 11 are received by the transmission / reception means 47, analyzed by the analysis means 44, a display screen is generated by the display screen generation means 45, or the analysis result is stored in the storage means 46. Control of each process such as storing various information such as.

  Here, the above-described skin observation device 11 and the cosmetic adhesion state analysis device 12 can be controlled by a dedicated device configuration having the above-described functions, but an execution program that can cause a computer to execute each function ( For example, by installing the execution program on a general-purpose personal computer, a server, or the like, it is possible to realize the cosmetic attachment state analysis process in the present invention.

<Hardware configuration>
Here, a hardware configuration example of a computer capable of realizing the cosmetic adhesion state analysis in the present invention will be described with reference to the drawings. FIG. 5 is a diagram illustrating an example of a hardware configuration capable of realizing the cosmetic adhesion state analysis according to the present invention.

  5 includes 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 for performing various controls, and a network connection device. 57 are connected to each other by a system bus B.

  The input device 51 has a pointing device such as a keyboard and a mouse operated by a user, and inputs various operation signals such as execution of a program from the user. The output device 52 has a display for displaying various windows and data necessary for operating the computer main body for performing processing according to the present invention, and displays the program execution progress, results, and the like by the control program of the CPU 56. can do.

  Here, the execution program installed in the computer main body in the present invention is provided by, for example, a recording medium 58 such as a CD-ROM. 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 an execution program according to the present invention, a control program provided in a computer, etc., and perform input / output as necessary.

  The memory device 55 stores an execution program or the like read from the auxiliary storage device 54 by the CPU 56. The memory device 55 includes a ROM (Read Only Memory), a RAM (Random Access Memory), and the like.

  The CPU 56 controls processing of the entire computer, such as various operations and input / output of data with each hardware component, based on a control program such as an OS (Operating System) and an execution program stored in the memory device 55. Thus, each process in the analysis of the adhesion state of the cosmetic can be realized. Various information such as a skin image necessary during the execution of the program can be acquired from the auxiliary storage device 54, and an execution result or the like can also be stored.

  The network connection device 57 obtains an execution program from another terminal connected to the communication network 13 by connecting to a communication network or the like, or an execution result obtained by executing the program or the present invention. The execution program itself can be provided to other terminals. With the hardware configuration as described above, the cosmetic adhesion state analysis processing in the present invention can be executed. Also, by installing the program, it is possible to easily realize the analysis of the adhesion state of the cosmetic applied to the skin in the present invention using a general-purpose personal computer or the like. Next, specific contents of the cosmetics adhesion state analysis process will be described.

<Cosmetic adhesion analysis procedure>
Next, an example of the cosmetics adhesion state analysis processing procedure in the present invention will be described using a flowchart. FIG. 6 is a flowchart showing an example of a cosmetic adhesion state analysis processing procedure in the present invention. In addition, the flowchart shown in FIG. 6 has shown the process sequence of the cosmetics adhesion state analysis system 10 whole in the skin observation apparatus 11 and the cosmetics adhesion state analysis apparatus 12 mentioned above.

  In the processing procedure shown in FIG. 6, it is first determined whether or not the subject is registered as a member when analyzing the skin with makeup (S01). If the member is not registered (NO in S01), the member is registered (S02). As described above, the registered member information includes “identification No.”, “name”, “birth date”, “sex”, “measurement site”, “memo” for identifying each measurement content. (Remarks) ”.

  Further, in the process of S01, when it is determined whether or not the subject is registered as a member, the information stored in the storage means or the like is searched using “identification No.” or “name”. , You can confirm the presence or absence of member registration.

  If the member is registered in S01 (YES in S01), or after the process of S02 is completed, various contents for analysis in the present embodiment are set (S03). Specifically, for example, information such as the XY coordinates and the area of the center of the analysis target indicating which part (at least one) of the subject's skin to which the cosmetic is applied is analyzed is set. At this time, if skin has already been measured, the same measurement or the like can be easily set by calling and referring to past measurement information from the storage means or the like. In the process of S03, when analyzing at least one of pores, wrinkles, spots, skin color, and the like, it is possible to set which analysis is performed.

  Next, in order to perform analysis based on the conditions set in the process of S03, imaging of a predetermined part such as a face is performed based on the set conditions (S04). When photographing (measuring), the measurement date and time is acquired, and the measured image is stored together with the member information and measurement date information (S05). By accumulating the date and time information, the measurement result for each member can be displayed over time (in time series) based on the history information and the like in the analysis process.

  Next, based on the photographed image, at least one of the amount of adhesion of the cosmetic to the skin, the non-uniformity, and the roughness (cohesion) is digitized and the cosmetic applied to the skin is adhered. The state is analyzed (S06). Further, a display screen for displaying the analysis result on the screen is generated (S07), and the generated screen is presented to the user or the like via output means such as a display (S08). Further, the analysis results are accumulated (S09), and the process is terminated.

  In addition, in the process of S06, in addition to the analysis of the adhesion state of the cosmetic applied to the skin, for example, at least one of pores, wrinkles, spots, skin color, and the like may be analyzed. In addition, by storing the measured images and analysis results as in the processing of S05 and S09, it is possible to compare with the analysis results for the next time or a plurality of times. Can be displayed.

  In the processes of S01 to S09 described above, S01 to S05 may be set as image acquisition processes, and S06 to S09 may be installed as a separate program as a separate program, and the same apparatus may be installed. May be installed. That is, when acquiring a predetermined part image for analyzing the state of attachment of cosmetics, the processing from S01 to S05 may be executed. When analyzing the state of attachment of cosmetics, S06 to The processing up to S09 may be performed.

  As described above, according to the cosmetic adhesion state analysis process of the present invention, the adhesion state of the cosmetic applied to the skin of the subject is determined by selecting at least one of the parameters of the adhesion amount, the non-uniformity, and the roughness. And can be analyzed with high accuracy. Thereby, the adhesion state of cosmetics can be evaluated objectively and with good reproducibility, and can be utilized for evaluation and development of products and raw materials, for example. Further, by using an image suitable for each analysis content, it is possible to calculate an optimum result value and display an analysis result. Furthermore, multi-faceted analysis of skin conditions such as the results of age distribution and time distribution can be performed with high accuracy.

<S06: Analysis processing procedure>
Next, the analysis processing procedure in S06 described above will be specifically described using a flowchart. FIG. 7 is a flowchart illustrating an example of the analysis processing procedure. Further, in the following description, a description will be given using a foundation as an example of a cosmetic, but the cosmetic in the present invention is not limited to the foundation, and a general cosmetic such as teak, eye shadow, lipstick, etc. All can be included, and further, powder applied to artificial skin and the like can also be included.

  First, when the foundation is applied to the skin of the subject acquired from the skin observation device 11, among the foundation image (OrgImg) including a partial image, the color component (R) that each pixel of the image area to be analyzed has (R A G component (green) image (green plane) (GImg) suitable for skin analysis is extracted from (red) G (green) B (blue) component) (S11).

  Next, a portion corresponding to hair is extracted from the green plane obtained by the processing of S01 (S12), and the portion corresponding to hair included in the extracted image is corrected by shading processing (S13). Further, the image obtained by the process of S13 is filtered by a differential filter to create an image (texture extraction image) for extracting skin texture (S14).

  Further, simple ternarization processing is performed from the image obtained by the processing of S14 (S15), and the texture extraction image obtained by the processing of S14 is compared with the simple ternary image obtained by the processing of S15. The image is divided into an image obtained by extracting only a portion where the foundation is determined to be attached to the skin more than a predetermined adhesion amount, and an image obtained by extracting the extracted image and the removed portion (S16).

  Next, the color information of the image is acquired from the foundation image (OrgImg) which is the original image (S17), the adhesion amount of the foundation is acquired from the brightness of the image (S18), and the nonuniformity of the foundation is acquired ( S19) Further, the roughness of the adhesion of the foundation is acquired (S20), and the adhesion state of the cosmetic is analyzed based on the acquisition results obtained by the processes of S18 to S20 (S21).

  Thereby, the adhesion state of the cosmetics applied to the subject's skin can be analyzed with high accuracy using at least one of the parameters of the adhesion amount, the non-uniformity, and the roughness. Therefore, the adhesion state of cosmetics can be evaluated objectively and with good reproducibility, and can be used for evaluation and development of products and raw materials, for example. Next, the above-described S12 to S20 will be described more specifically.

<S12: Extraction of part corresponding to hair>
First, the extraction process of the part corresponding to the hair of S12 mentioned above is demonstrated concretely. In the following description, as an example of the size of the acquired image, the original image of 640 × 480 is trimmed in the range of 420 × 420 from the center position and used for analysis. However, the image size according to the present invention is used. Is not limited to this.

  FIG. 8 is a flowchart illustrating an example of a hair extraction processing procedure. First, an average of pixels around the object (for example, 30 × 30) is acquired (S31), and an average (HAve) of blurred images (HImg) obtained by the process of S31 is acquired (S32). Further, a value (shading process image: SHImg) obtained by subtracting (HImg gradation−HAve) from the green plane (GImg) gradation obtained in S11 described above is acquired (S33). In addition, the process of S31-S33 has shown the shading process for hair extraction.

  Next, the standard deviation (Hσ) is obtained from the average (Have) obtained in S32 and the value obtained in S33 (S34), and further, pixels satisfying “gradation <Have-2Hσ” are obtained (S35). ). In other words, after correcting the shading of the green plane, the tone average / standard deviation (σ) is obtained, and the slice level for determining the portion corresponding to the hair is calculated. Extract (binarize) pixels that do not fall into.

  Further, after shrinking the image for each surrounding pixel in the region obtained in S35 (S36), the image for each surrounding pixel is expanded from the internal pixel and returned to the original size (S37), Noise (dust) consisting of a small number of pixels contained in an image is removed.

  Further, for example, when the group of collected pixels (the number of aggregated pixels) is smaller than a predetermined value (for example, 30 pixels) among the extracted pixels, the aggregate is deleted as noise (dust) (S38), and S38. The image obtained by the process is accumulated as a mask image of the portion corresponding to the hair (S39). That is, the number of pixels for each group of pixels is confirmed from an image obtained by contraction / expansion, and only a set having 30 or more pixels is extracted, and the extracted portion is set as a portion corresponding to hair. As a result, when performing processing such as simple ternary processing, which will be described later, using this image as a mask image, high-precision image processing can be realized by not using the pixel information of this portion.

  In general, the diameter of the body hair is 18 to 180 μm. However, in order to extract the portion corresponding to the hair with a certain degree of accuracy, in this embodiment, hair having a diameter of 50 μm or more is extracted as an example. Since one side of the measured pixel of the image is 10 μm, it is necessary to acquire an image having a horizontal (width) or vertical (height) of 5 pixels or more. Therefore, in this embodiment, the value 30 existing between “5 × 5” and “6 × 6” is set as a pixel that is recognized as an image corresponding to hair. Thereby, the part applicable to hair can be extracted uniformly based on a predetermined condition. The number of pixels is arbitrarily set based on image conditions such as image size and magnification.

  Here, FIG. 9 is a diagram illustrating an example of an image change until a portion corresponding to hair is extracted. As shown in FIG. 9, a G component image (green plane) 62 is extracted from the original image 61, and a hair extraction image 63 can be extracted from the extracted G component image 62 by the hair extraction process described above.

<S13: Shading process>
Next, the shading process procedure will be specifically described. FIG. 10 is a flowchart illustrating an example of a shading processing procedure. In the shading process shown in FIG. 10, first, a pixel average of 8 pixels around the target pixel in the green plane (GImg) is obtained as a reference (S41), and a blurred image (S41) is obtained by the process of S41. BImg ₋₁ ) is obtained based on a certain target pixel, and an average pixel of the surrounding eight pixels is acquired (S42).

Further, an average (Bave) of the blurred images (BImg ₋₂ ) obtained by the processing of S42 is acquired (S43), and a shading processed image (SImg) obtained by subtracting (BImg ₋₂ gradation −BAve) from the GImg gradation is obtained. Obtain (S44). In this way, by performing the shading process for analysis, when acquiring a rounded skin image, it can be corrected so that the end of the image becomes dark as a whole becomes uniform. .

<S14: Texture Extraction Image Creation Processing>
Next, the texture extraction image creation process will be specifically described. FIG. 11 is a flowchart illustrating an example of a texture extraction image creation process. First, the shading of the green plane is corrected, and a factor (an arbitrary constant) is added to the average of the gradation of a certain pixel and the gradation of 24 surrounding pixels centered on that pixel in the shading-processed image (SImg). F) The value obtained by adding (for example, 60) is compared, and if the gradation value of a target pixel is large, that pixel is extracted (S51).

  In addition, a set in which the number of set pixels of the extracted pixels is smaller than 300 pixels and the length of the set pixels is smaller than 26 pixels is deleted as noise (dust) (S52). This is because the texture is normally formed vertically with respect to the orientation of the face, and a set of vertically long images is determined as a texture image. Note that the above-described number of collective pixels and the vertically long length are not particularly limited, and can be arbitrarily set based on image conditions such as an image size and a magnification.

  Next, after shrinking the image for each surrounding pixel out of the collective pixels left in the processing of S52 (S53), the image for each surrounding pixel is expanded from the internal pixels and returned to the original size. (S54) Noise (dust) consisting of a small number of pixels contained in the image is removed, and this image is stored as a differential filter image (S55). This image is used as an image for masking a portion where the foundation is firmly attached.

  Here, FIG. 12 is a diagram illustrating an example of a texture extraction image to be acquired. As shown in FIG. 12, the texture extraction image 65 can be acquired by performing the above-described texture extraction image creation process from the shading process image 64 obtained by the process of S13.

<S15: Simple ternary processing>
Next, the simple ternary processing will be specifically described. FIG. 13 is a flowchart illustrating an example of a simple ternarization processing procedure. First, the average (Ave), standard deviation (σ), and maximum gradation value (Max) of the shading processed image (SImg) are acquired (S61), and the first slice level (sl ₁ ) set in advance is acquired. (S62) Further, the second slice level (sl ₂ ) is acquired (S63).

Next, a pixel in which the gradation of the target pixel is the first slice level (sl ₁ ) is extracted (simple binarization) (S64). Since the portion is an image (AImg ₋₁ ) with a thin foundation attached, if the set number of extracted pixels is smaller than a predetermined number of pixels (for example, 30 pixels), the set is treated as noise ( It is deleted as dust) (S65).

Further, after shrinking the image for each surrounding one pixel with respect to the set of AImg ₋₁ (S66), the image for each surrounding one pixel is expanded from the internal pixels and returned to the original size (S67), Noise (dust) consisting of a small number of pixels contained in an image is removed.

Further, when the number of extracted pixels is less than a predetermined number of pixels (for example, 30 pixels), the set is deleted as noise (dust) (S68). Moreover, it accumulates as a simple ternary first layer image (AImg ₋₁ ′) (S69).

A pixel in which the gradation of the target pixel is greater than the second slice level (sl ₂ ) is extracted (simple binarization) (S70). Since this portion is an image (AImg ₋₂ ) in which the foundation is thickly attached, this image is stored as a simple ternary second layer image (AImg ₋₂ ′) (S71).

<About slice level>
Here, an example of the first slice level (sl ₁ ) and the second slice level (sl ₂ ) described above will be described. First, acquisition of parameters used in the analysis is performed using 31 images (hereinafter referred to as teacher images) in which the foundation measured by an imaging device such as the skin observation device 11 is applied to the skin of the subject, and for a predetermined time. Verification was performed using 31 foundation images (hereinafter referred to as verification images) measured with the same device after the lapse.

  Here, the two slice levels serving as a reference for performing simple ternarization can be obtained by using mathematical formulas or the like. That is, the slice level acquisition formula of the ternary image representing the application state of the foundation first extracts a portion where the foundation is thin (including a portion where the coating is thick) in the case of the first slice level. An average value (KAve) and a standard deviation (Kσ) are acquired from the green plane gradation information of the image, the green plane is smoothed, and a maximum value (KMax) is obtained. For the maximum value (KMax), a search is performed from a gradation 255 to 0 for a predetermined gradation graph, and a gradation where the number of pixels is 10 or more is defined as KMax.

Next, the first slice level (Sl ₁ ) is acquired from the above-described Kave, Kσ, and KMax using the following mathematical formula and the like.
Sl ₁ = KAve + ((KMax−KAve + 1) / (Kσ + 12) +0.5)
As for Sl _1, gradation difference of the maximum value and the average standard deviation (Kσ) by (KMax-KAve) dividing the slice level whatever image is 5-10% of (KMax-KAve) It has been adjusted to be a value.

Specifically, for example, calculation is performed so that the first slice level (Sl ₁ ) is set at a position of 5 to 10% of (KMax−KAve). In one example, it is set to (KAve + 2.5) to (KAve + 4.5). Further, for example, the range of Kσ from 0 to 9.9 (average of Kσ + standard deviation 1σ) is acquired under the above-described conditions. When Kσ ≧ 9.9, the value of Sl ₂ is greater than Sl ₁ . Therefore, in the case of “Sl ₁ <Sl ₂ −2”, the conditional expression is set so that “Sl ₁ = Sl ₂ −2”.

Next, when extracting the second slice level (Sl ₂ ), that is, the portion where the foundation is applied thickly, first, the average value (KAve) and the standard deviation (Kσ) are obtained from the green plane gradation information of the image. Is obtained, the gradation is smoothed, and the maximum value (KMax) is obtained. For the maximum value (KMax), a search is performed from a gradation 255 to 0 for a predetermined gradation graph, and a gradation where the number of pixels is 10 or more is defined as KMax.

Further, the second slice level (Sl ₂ ) is acquired from KAVE, Kσ, and KMax by the following formula.
Sl ₂ = KAve + ((KMax−KAve + 1) × (22−Kσ × 2) / 30)
Since the value of Sl ₂ is smaller than Kave when Kσ> 11, the conditional expression is set so that “Sl ₂ = Kave” when “Sl ₂ <Kave”.

Note that Sl _2, as the maximum value and the gray level difference average (KMax-KAve) the maximum value of the slice level at about 75% with a standard deviation (Kσ), when the standard deviation (Kσ) is about 10 Are adjusted to be approximately the same value as the first slice level (Sl ₁ ).

Specifically, the slice level is set so as to decrease as Kσ increases (the foundation adheres more). For example, Sl ₁ and Sl ₂ have the same value when Kσ≈9.9 (average of Kσ + standard deviation 1σ range). Further, since S1 ₂ <KAve when Kσ> 11, the conditional expression is set so that “S1 ₂ = KAve” when “S12 <Kave”.

Further, when the standard deviation is close to 10, S1 ₂ <S1 ₁ is satisfied. Thus, in order to avoid that Sl ₁ is larger than Sl ₂ , if “Sl ₁ <Sl ₂ −2” after obtaining the slice level, the conditional expression is set so that “Sl ₁ = Sl ₂ −2”. It is set.

<S16: Image division>
Next, the image division process in S16 will be specifically described. In the process of S16, the differential filter image obtained by the process of S55 described above is compared with the first layer image (AImg ₋₁ ′) obtained by the simple ternarization obtained by the process of S69 described above. The image area part overlapping the image is accumulated as an image (LImg ₋₁ ) of the part (area) where the foundation is firmly attached. In addition, a portion that does not overlap with the differential filter image is accumulated as an image (OImg ₋₁ ) of other attached portions (for example, a skin portion other than skin texture).

Further, the differential filter image obtained by the process of S55 described above is compared with the second layer image (AImg- ₂ ′) obtained by the simple ternarization obtained by the process of S71 described above, and overlaps with the differential filter image. The part is accumulated as an image (LImg ₋₂ ) of a part (region) where the foundation is firmly attached. In addition, a portion that does not overlap with the differential filter image is accumulated as an image (OImg ₋₂ ) of other attached portions.

Here, FIG. 14 is a diagram illustrating an example of an image in the above-described simple ternarization processing. As shown in FIG. 14, the shading-processed image 64 is decomposed into each layer image 66 using the first and second slice levels (Sl ₁ , Sl ₂ ) described above.

Specifically, a partial (first layer) image 66-1, a partial (second layer) image 66-2 selected by a differential filter based on the first and second slice levels (Sl ₁ , Sl ₂ ), and others A simple ternarization is obtained by synthesizing two types of two-layer images composed of the partial (first layer) image 66-3 and the other partial (second layer) image 66-4 to obtain a composite image 67. Processing is performed. That is, the analysis processing in this embodiment can be performed by using an image obtained by combining one or a plurality of images from the respective layer images 66-1 to 66-4 according to the content to be analyzed, which will be described later.

<S17: Image Color Information Acquisition Processing>
Next, the acquisition process of the color information of the image in S17 used for analyzing the adhesion state of the foundation will be specifically described. In the process of S17, the saturation is acquired from the RGB gradation values of each pixel of the foundation image (OrgImg) that is the original image, and the average saturation (SAve) of all the pixels in the image is acquired. Further, the standard deviation (Gσ) of the green plane gradation value of the foundation image (OrgImg) is acquired.

<S18: Acquisition processing of adhesion amount of foundation>
Next, the foundation adhesion amount acquisition processing in S18 will be specifically described. In the process of S18, the total number of pixels (AllCnt) of the first layer image (AImg- ₁ ′) in the simple ternarization is acquired, and further, the total number of pixels (AllCnt) and the average saturation of all the pixels in the image described above. The adhesion amount of the foundation is acquired from (SAve).

  Here, regarding the foundation adhesion amount, information on the adhesion amount is acquired from the image. First, as a shape feature, a shape feature is acquired from a result obtained by simple ternarization processing and image division. Specifically, the total number of pixels of the first layer image (images 66-1, 66-3) is counted. The total number of pixels increases in proportion to the amount of foundation adhered to the skin. The total number of pixels is main information for analyzing the adhesion amount. In step S17, the color information of the image is acquired. Note that the saturation tends to be higher as the foundation is thicker on the skin. Therefore, it introduce | transduces in order to improve the analysis accuracy of the adhesion amount.

  Next, a value as an analysis result is acquired using the total number of pixels and the saturation average. Specifically, an adhesion amount raw point is acquired using the number of pixels of the entire simple ternary image and the saturation of the green plane.

Here, when obtaining a bare point, if “saturation <35”, “attachment amount elementary point = number of pixels” is set, and if “saturation ≧ 35”, “attachment amount elementary point = total attachment amount + (saturation amount)”. Degree −35) × total adhesion amount / 35 = saturation × total adhesion amount / 35 ”.
Adhering amount = 0.000045 x Adhering amount raw point + 0.516
Here, the threshold used for the saturation correction is an optimum value within the range of “saturation average ± standard deviation 1σ” of the teacher images (31 images). In this analysis of the teacher image and the verification image, the threshold value used for correcting the saturation is set to 35. However, in the present invention, the threshold value is not limited to this, and may be set between 20 and 50, for example. That's fine.

  When the saturation is equal to or greater than the threshold value, the “(saturation−35) / 35” double prime of the total adhesion amount increases as the saturation value increases. When this is confirmed by the teacher image, the value increases by about 35% at the maximum as the saturation increases.

  In addition, the above-mentioned formula is a formula for normalizing the adhesion amount raw score between 1 to 5 points as an example. By normalizing with this equation, the state of adhesion can be easily analyzed. In the present invention, the method of quantifying the amount of adhesion is not limited to this, and for example, normalization is performed in another score range, or only the above-mentioned adhesion amount raw points are used without normalization. It is possible to analyze the adhesion state of the cosmetic applied to the skin.

<S19: Foundation Uniformity Acquisition Process>
Next, the foundation uniformity acquisition process in S19 will be described in detail. In the process of S19, the flat rate (FPrm) of the first layer image (OImg ₋₁ ) in simple ternarization is acquired, and then the standard of the flat rate (FPrm) and the green plane gradation value of the foundation image (OrgImg) The foundation non-uniformity is obtained from the deviation (Gσ).

  Specifically, as the acquisition process of the non-uniformity of the foundation application, information on the adhesion amount is acquired from the image. First, as the color information of the image, the standard deviation of the green plane gradation used for the shape analysis is acquired. Note that the standard deviation used here tends to disperse the gradation of the image as the foundation attached to the skin is not uniformly attached. For this reason, the standard deviation is acquired as the main information of the nonuniformity.

  Next, the length ratio (flattening ratio) of a set (lumps) of pixels included in the image (image 66-3) of the first layer and other portions is acquired as a shape feature. Here, the above-described length ratio will be described. FIG. 15 is a diagram illustrating an example for explaining the length ratio.

  In at least one pixel set 69 present in the image 68 shown in FIG. 15, the length ratio in each of the vertical, horizontal, right diagonal 45 degrees and left diagonal 45 degrees in the pixel set 69 as shown in FIG. 15. The longest direction with respect to is obtained, and the value obtained by dividing by the length in the direction orthogonal thereto. For example, when the longest is vertical, “vertical length / horizontal length” is set. When the longest is horizontal, “horizontal length / vertical length” is set. When the longest is 45 ° diagonally, “length 45 ° diagonally / 135 diagonally”. If the longest is 135 degrees oblique, the length is 135 degrees oblique / 45 degrees oblique.

  In addition, a rough mass flatness is acquired from the length ratio in the vertical / horizontal direction or 45 ° to the right and 45 ° to the left. The flatness ratio is closer to 1 as the mass is smaller and closer to a circle, and the value increases as the mass increases.

  The flatness referred to here is a rough acquisition of the flatness of individual masses at locations other than the portion where the foundation is firmly attached to the skin. In other words, the more portions that are firmly attached, the higher the probability that the other portions will be divided, so there seems to be a correlation in the non-uniformity. Therefore, this flatness ratio is introduced in order to increase the analysis accuracy of the nonuniformity.

Next, a value is acquired using the standard deviation and the flatness. Specifically, when obtaining the non-uniformity, a non-uniform prime point is acquired by using the standard deviation of the gradation of the green plane and the flatness ratio of the skin hill portion of the simple ternary image.
Nonuniform elementary point = standard deviation−31.34 × flattening rate The coefficient value described above is not limited to 31.34, and may be set between 5 and 50, for example.

Further, the degree of non-uniformity is obtained from the obtained non-uniform raw point using, for example, the following mathematical formula.
Non-uniformity = 0.212738 x non-uniform prime point + 7.468
Note that the coefficient of nonuniformity and gradation standard deviation used in the above-described acquisition of nonuniform elementary points and the intercept are set by analysis information of teacher images (31 images) and multiple regression analysis of visual results. Yes. For example, the coefficient is set to an optimum value for the visual result in the range of “coefficient ± standard deviation (1σ)” acquired from the multiple regression analysis.

  In addition, the above-mentioned formula is a formula for normalizing the non-uniformity between 1 to 5 points as an example. By normalizing with this equation, the state of adhesion can be easily analyzed. In the present invention, the method of quantifying the non-uniformity is not limited to this, and for example, normalization is performed in other score ranges, or the above-described non-uniformity raw points without normalization. It is possible to analyze the adhesion state of the cosmetic applied to the skin.

<S20: Acquisition processing of foundation roughness (cohesion)>
Next, the acquisition process of the roughness (cohesion degree) of the foundation in S20 will be specifically described.

First, the total number of pixels (SndCnt) of the second layer image (AImg ₋₂ ′) in the simple ternarization described above is acquired. Further, based on the total number of pixels (AllCnt) of the first layer image (AImg ₋₁ ′) in simple ternarization and the total number of pixels (SndCnt) of the second layer image (AImg ₋₂ ′) in simple ternarization. Obtain the roughness of foundation application.

  More specifically, information on the adhesion amount is first acquired from the image regarding the roughness of foundation coating. Specifically, a value (roughness ratio) obtained by dividing the total number of pixels in the second layer by the total number of pixels in the first layer is acquired as a shape feature. Here, a composite image composed of the partial (second layer) image 66-2 selected by the differential filter as shown in FIG. 14 and the other partial (second layer) image 66-4 is converted using the differential filter. A value is obtained by dividing by a composite image composed of the selected partial (first layer) image 66-1 and the other partial (first layer) image 66-3.

  In addition, since the degree of roughness tends to increase the number of pixels acquired as the second layer as the foundation is coarsely adhered, the roughness of coating can be determined by calculating the ratio of the first layer and the second layer. You can get it. Therefore, the roughness can be used as main information for the adhesion amount analysis.

In addition, the roughness raw point is obtained by using the number of pixels (Cnt ₁ ) of the entire simple ternary image and the number of pixels (Cnt ₂ ) of the portion where the foundation is thickly attached.
Roughness point = Cnt ₂ ÷ Cnt ₁
Further, the roughness degree is acquired by using, for example, the following mathematical formula or the like based on the acquired roughness raw points.
Roughness = 0.031050 × Roughness point + 1.51785
In addition, this numerical formula normalizes the result value to 1 to 5 points from the regression analysis of the visual results of the teacher images (31 sheets) and the roughness raw points. That is, the above formula is an equation for normalizing the roughness between 1 to 5 points as an example. By normalizing with this equation, the state of adhesion can be easily analyzed. In the present invention, the method of quantifying the roughness is not limited to this. For example, normalization is performed in another score range, or the above-described roughness score is obtained without normalization. It is possible to analyze the adhesion state of the cosmetic applied to the skin.

  The formulas shown in S18 to S20 and the results calculated by the formulas can be displayed on a display screen or the like so that the subject can be presented or edited.

  As described above, it is possible to analyze the adhesion state of the cosmetic applied to the skin using at least one of the digitized results obtained from each of S18 to S20 by the method shown in the present embodiment. it can. In addition, the finish of the makeup can be analyzed with high accuracy from the amount of the applied cosmetic material. Accordingly, for example, by observing and analyzing the adhesion state of the foundation powder to the skin (skin), for example, it is possible to establish a new finish evaluation method for makeup that is also used in stores.

  In addition to the analysis of the adhesion state of the cosmetic applied to the skin as described above, the subject is further analyzed by analyzing at least one of pores, wrinkles, blemishes, skin color, etc., and combining the analysis results. Detailed analysis results and advice to skin can be performed.

<Example of cosmetic adhesion state analysis processing screen>
Next, a screen example in the case of performing cosmetic adhesion state analysis processing using the cosmetic adhesion state analysis software by the execution program (cosmetic adhesion state analysis program) in the present invention will be described with reference to the drawings.

  FIG. 16 is a diagram illustrating an example of a screen for performing a cosmetics adhesion state analysis process. 16 is configured to include an analysis image designation area 71, a data storage designation area 72, an execution processing area 73, an image display area 74, and an analysis result display area 75. Has been. Note that the arrangement, size, contents, and the like of each region are not limited to this.

  The analysis image designation area 71 selects an analysis target image from a selection list of storage destination drives and folders, and selects an analysis target image from a group of images stored in the selected folder by a check mark or the like. In the analysis image designation area 71, the number of images in the selected storage folder (30 in FIG. 16) and the number of selected analysis target images (2 in FIG. 16) may be displayed. The analysis image designation area 71 has a button (All Select) for selecting all images in the selected storage folder and a selection cancel button (Not Select) for all selected images. By selecting the button, it is possible to efficiently set or cancel the target image.

  In addition, the data saving designation area 72 selects the saving destination of the analysis result value and the result image in the selection dialog, and displays the folder path of the selected saving destination. As shown in FIG. 16, the data storage designation area 72 may be provided with a display button for displaying a selection dialog.

  The execution processing area 73 includes an execution button for executing analysis of the selected image group, an end button for ending (suspending) analysis processing, and the like. Here, when the user presses the execution button, the analysis of the image groups selected in the analysis image designation area 71 is sequentially performed.

  The image display area 74 displays an analysis target image 81 and an analysis result image 82. Here, in the analysis result image 82, for example, cosmetics such as foundation (red part) attached to the skin groove part, cosmetics such as foundation (blue part) attached to the skin hill part, and the like are displayed. In addition, in each color, when the color is light, it indicates that the cosmetics such as foundation are thinly applied to the skin, and when the color is dark, the cosmetic such as foundation is darkly applied on the skin. It shows that.

  When there are a plurality of analysis target images 81, a plurality of analysis target images 81 and their analysis result images 82 may be arranged and displayed in the analysis order in the image display area 74. Only the analysis result image 82 may be displayed. Each analysis target image 81 and analysis result image 82 are stored in a predetermined data format (for example, BMP format, JPEG format, etc.) in the storage destination specified in the data storage specification area 72.

  The analysis result display area 75 displays analysis result values (attachment amount, nonuniformity, roughness). Each analysis target image name and analysis result value (attachment amount, non-uniformity, roughness) are also stored in a predetermined data format (for example, CSV format) in the storage destination specified in the data storage specification area 72.

  As described above, by using the cosmetic adhesion state analysis processing screen 70, the user or the like can easily analyze the cosmetic adhesion state.

  As described above, according to the present invention, the adhesion state of the cosmetic applied to the skin of the subject is highly accurate using at least one of the parameters of the adhesion amount, the non-uniformity, and the roughness. Can be analyzed. Thereby, the adhesion state of cosmetics can be objectively evaluated with good reproducibility. In addition, the analysis results in the present invention can be used for product evaluation and product information development, as well as evaluation of powders as raw materials, evaluation of prototypes of developed products, evaluation of products from other companies, and application to in-store equipment software. Etc.

  The preferred embodiments of the present invention have been described in detail above, but the present invention is not limited to such specific embodiments, and various modifications, within the scope of the gist of the present invention described in the claims, It can be changed.

It is a figure which shows an example of schematic structure of the cosmetics adhesion state analysis system in this invention. It is a figure which shows an example of a function structure of a skin observation apparatus. It is a figure which shows an example of a structure of the head part in an imaging | photography means. It is a figure which shows an example of a function structure of a cosmetics adhesion state analyzer. It is a figure which shows an example of the hardware constitutions which can implement | achieve the cosmetics adhesion state analysis in this invention. It is a flowchart which shows an example of the cosmetics adhesion state analysis processing procedure in this invention. It is a flowchart which shows an example of an analysis processing procedure. It is a flowchart which shows an example of a hair extraction process procedure. It is a figure of an example for demonstrating the change of the image until the part applicable to hair is extracted. It is a flowchart which shows an example of a shading process procedure. It is a flowchart which shows an example of a creation process of a texture extraction image. It is a figure which shows an example of the texture extraction image acquired. It is a flowchart which shows an example of a simple ternarization processing procedure. It is a figure which shows the example of the image in a simple ternary process. It is a figure of an example for demonstrating a length ratio. It is a figure which shows an example of the screen which performs cosmetics adhesion state analysis processing.

Explanation of symbols

DESCRIPTION OF SYMBOLS 10 Cosmetics adhesion state analysis system 11 Skin observation apparatus 12 Cosmetics adhesion state analysis apparatus 13 Communication network 21,41 Input means 22,42 Output means 23,43 Member management means 24 Photographing means 25,46 Accumulation means 26,47 Transmission / reception means 27, 48 Control means 30 Illumination light 31 Skin 32 Reflected light 33 Polarization filter 44 Analysis means 45 Display screen generation means 51 Input device 52 Output device 53 Drive device 54 Auxiliary storage device 55 Memory device 56 CPU
57 Network connection device 58 Recording medium 61 Original image 62 G component image 63 Hair extraction image 64 Shading processing image 65 Texture extraction image 66 Each layer image 67 Composite image 68 Image 69 Pixel set 70 Cosmetics adhesion state analysis processing screen 71 Analysis image designation area 72 Data save designation area 73 Execution processing area 74 Image display area 75 Analysis result display area 81 Analysis target image 82 Analysis result image

Claims (14)

In the cosmetics adhesion state analysis method for analyzing the adhesion state of the cosmetics using a skin image of a predetermined range of the photographed subject,
An analysis step for analyzing the adhesion state of the cosmetic by quantifying at least one of the adhesion amount, non-uniformity, and roughness of the cosmetic applied to the skin of the subject from the skin image;
A cosmetic adhesion state analysis method comprising: an accumulation step of accumulating the skin image and an analysis result obtained from the analysis step in association with subject information. The analysis step includes
When the adhesion amount is digitized, a ternary image is acquired from the skin image, and based on the number of pixels of the acquired ternary image and the saturation of the green image extracted from the skin image, The cosmetic adhesion state analysis method according to claim 1, wherein the adhesion amount is digitized. The analysis step includes
When quantifying the non-uniformity, based on the standard deviation of the gradation of the green image extracted from the skin image and the flatness ratio of the hill part of the ternary image obtained from the skin image, 3. The cosmetic adhesion state analysis method according to claim 1 or 2, wherein the non-uniformity is digitized. The analysis step includes
When the roughness degree is digitized, the roughness degree is digitized based on the number of pixels of the entire ternary image obtained from the skin image and the number of pixels of the portion where the cosmetic material is thickly adhered. The cosmetic adhesion state analysis method according to any one of claims 1 to 3, wherein: The analysis step includes
The cosmetic adhesion according to any one of claims 1 to 4, wherein a finish of the makeup is analyzed from at least one of the adhesion amount, non-uniformity, and roughness of the cosmetic. State analysis method. A photographing step of photographing the skin image by photographing means;
6. The method according to claim 1, wherein, in the photographing step, when the reflected light obtained by illuminating the skin of the subject is received by the photographing unit, filtering is performed by a polarizing filter. The cosmetic adhesion analysis method described. In the cosmetics adhesion state analysis device that analyzes the adhesion state of the cosmetics using a skin image of a predetermined range of the photographed subject,
Analyzing means for quantifying at least one of the adhesion amount, non-uniformity, and roughness of the cosmetic applied to the skin of the subject from the skin image, and analyzing the adhesion state of the cosmetic;
A cosmetic adhesion state analyzing apparatus comprising: an accumulation unit that accumulates the skin image and an analysis result obtained from the analysis unit in association with subject information. The analysis means includes
When the adhesion amount is digitized, a ternary image is acquired from the skin image, and based on the number of pixels of the acquired ternary image and the saturation of the green image extracted from the skin image, The cosmetic adhesion state analyzing apparatus according to claim 7, wherein the adhesion amount is digitized. The analysis means includes
When quantifying the non-uniformity, based on the standard deviation of the gradation of the green image extracted from the skin image and the flatness ratio of the hill part of the ternary image obtained from the skin image, The cosmetic adhesion state analyzing apparatus according to claim 7 or 8, wherein the non-uniformity is digitized. The analysis means includes
When the roughness degree is digitized, the roughness degree is digitized based on the number of pixels of the entire ternary image obtained from the skin image and the number of pixels of the portion where the cosmetic material is thickly adhered. The cosmetic adhesion state analyzing apparatus according to any one of claims 7 to 9, wherein: The analysis means includes
The cosmetic adhesion according to any one of claims 7 to 10, wherein the finish of the makeup is analyzed from at least one of the adhesion amount, non-uniformity, and roughness of the cosmetic. State analysis device. A photographing means for photographing the skin image;
The said imaging | photography means provides a polarizing filter on the path | route of irradiation light and reflected light, when receiving the reflected light obtained by irradiating illumination to the said test subject's skin, The any one of Claims 7 thru | or 11 characterized by the above-mentioned. The cosmetic adhesion analyzer according to Item 1.   A cosmetic adhesion state analysis program for operating a computer to execute the cosmetic adhesion state analysis method according to any one of claims 1 to 6.   A computer-readable recording medium on which the cosmetic adhesion state analysis program according to claim 13 is recorded.