JP2021129977A - Degree of lively face estimation method, degree of lively face estimation device, and degree of lively face estimation program - Google Patents

Abstract

To provide a device and program for estimating the degree of a lively face of a subject from face image data of the subject with high accuracy and good reproductivity.SOLUTION: A degree of lively face estimation program includes estimating, on the basis of the correlation between the intensity of a space frequency obtained from face image data and the degree of a lively face, the degree of the lively face of a subject from the face image data of the subject.SELECTED DRAWING: Figure 16

Description

The present invention relates to a lively face degree estimation method, a lively face degree estimation device, and a lively face degree estimation program.

Being a "lively face" is one of the important evaluations for everyone. In particular, the evaluation of the degree of "lively face" is extremely important in various fields such as esthetics and cosmetics.

Conventionally, there is known a monitoring / recognition system that captures a face image into a computer, recognizes an age group, gender, and facial characteristics, and estimates a person. Patent Documents 1 to 3 describe an age estimation system (for example, Patent Documents 1 and 2) using image processing values such as edging and binarization, and feature quantities (position, shading) of feature points such as eyes, nose, and mouth. , The number of wrinkles) is disclosed (for example, Patent Document 3).

Further, a technique is known that focuses on the fact that the texture characteristics of an image change depending on the spatial periodicity (spatial frequency). As a technique focusing on the spatial frequency, Patent Document 4 discloses a method for creating a simulation image of skin having various textures by changing the spatial frequency.

In addition, the applicant discloses a technique for evaluating the effect of make-up on "three-dimensional appearance of face" by analyzing the pattern of spatial frequency at the time of make-up (for example, Patent Document 5).

JP-A-2009-086901 JP-A-2009-271885 Japanese Unexamined Patent Publication No. 2008-282089 Japanese Unexamined Patent Publication No. 2004-283357 Japanese Unexamined Patent Publication No. 2004-272849

In the presence of the above prior art, as a result of diligent research efforts by the present inventor, it has been found that there is a high correlation between the intensity of the spatial frequency obtained from the face image data and the degree of lively face. ..
That is, it is an object of the present invention to provide a novel technique for estimating the degree of "lively face" with high accuracy and good reproducibility.

The present invention that solves the above problems is based on the correlation between the intensity of the spatial frequency obtained from the face image data and the degree of the lively face, and the face image data of the target person is used to obtain the lively face of the target person. An estimation method that includes estimating the degree.
As shown in Examples described later, the intensity of spatial frequency has a high correlation with a lively face.
Therefore, according to the estimation method of the present invention, the degree of lively face of the subject can be estimated from the face image data of the subject with high accuracy and reproducibility.

A preferred embodiment of the present invention includes a spatial frequency calculation step of calculating the intensity of the spatial frequency obtained by using data obtained from an arbitrary channel alone or in combination among the RGB color channel data of the color face image data.
Applying the calculated spatial frequency intensity to a pre-prepared formula or model showing the correlation between the spatial frequency intensity obtained from the face image data and the lively facial degree, the subject's liveliness An evaluation process that evaluates the degree of facial appearance
It is an estimation method including.

In a preferred embodiment of the present invention, the formula is a multiple regression formula obtained by multiple regression analysis or a prediction formula obtained by PLS.
By using the multiple regression equation or the prediction equation, it is possible to estimate the degree of the subject's lively face from the subject's face image data with high accuracy and reproducibility.

In a preferred embodiment of the present invention, the degree of lively face is the brightness of the cheeks, the dullness under the eyes, the dullness of the cheeks, the plumpness of the cheeks, the complexion, the firmness, the yellowishness of the entire face, and the skin. Includes at least one degree of ruggedness and luster of the skin.

In a preferred embodiment of the present invention, the face image data is face image data of a face part or the whole face.

In a preferred embodiment of the present invention, the face image data is color face image data, and the spatial frequency is a spatial frequency obtained from at least one of RGB color channel data of the color face image data.

In a preferred embodiment of the present invention, the spatial frequency is a spatial frequency obtained from a plurality of color channel data among the RGB color channel data of the face image.
By using a combination of spatial frequency intensities obtained from a plurality of color channel data among the RGB color channel data of the face image, the subject's face image data can be used to make the subject's liveliness with high accuracy and reproducibility. The degree of face can be estimated (evaluated).

In a preferred embodiment of the present invention, the spatial frequency range (cycle / image-wise) is 0 to 512 cycles / image-wise when the image has an image length of 1024 pixels.

Further, the present invention relates to an application step of applying a skin condition improving agent and / or a cosmetological means to a subject.
A measurement step for measuring the degree of change in the degree of lively face acquired before the application step and estimated by the above-mentioned estimation method, and the degree of change in the degree of lively face after the application step.
Based on the results of the measurement step, the determination step of determining that the higher the rate of increase in the degree of lively face, the more suitable the skin condition improving agent and / or the beauty means for the subject.
It is a method of selecting a skin condition improving agent and / or a cosmetological means, which is characterized by having.

The present invention is also a method for screening a skin condition improving agent based on the correlation between the intensity of spatial frequency obtained from facial image data and the degree of lively face.

In a preferred embodiment of the method for screening a skin condition improving agent of the present invention, an application step of applying a substance to the skin and an application step
A measurement step for measuring the degree of change in the degree of lively face acquired before the application step and estimated by the above-mentioned estimation method, and the degree of change in the degree of lively face after the application step.
Based on the results of the measurement step, a determination step of determining that a skin condition improving agent having a higher rate of increase in the degree of lively face is a better skin condition improving agent.
It is characterized by having.

Further, the present invention that solves the above problems calculates the intensity of the spatial frequency obtained by using the data obtained from an arbitrary channel alone or in combination among the RGB color channel data of the color face image data. Calculation means and
The calculated spatial frequency intensity is applied to a pre-prepared formula or model showing the correlation between the spatial frequency intensity obtained from the face image data and the lively face, and the lively face of the subject is applied. Evaluation means to evaluate the degree of
With respect to an estimation device.
According to the estimation device of the present invention, it is possible to estimate the degree of lively face of the subject from the face image data of the subject with high accuracy and reproducibility.

In addition, the present invention that solves the above problems uses a computer.
Spatial frequency calculation means for calculating the intensity of the spatial frequency obtained by using the data obtained from an arbitrary channel alone or in combination among the RGB color channel data of the color face image data.
The calculated spatial frequency intensity is applied to a pre-prepared formula or model showing the correlation between the spatial frequency intensity obtained from the face image data and the lively face, and the lively face of the subject is applied. Evaluation means to evaluate the degree of
Regarding an estimation program to function as.
According to the estimation program of the present invention, it is possible to estimate the degree of lively face of the subject from the face image data of the subject with high accuracy and reproducibility from the face image data of the subject by a computer.

According to the present invention, it is possible to provide a novel technique for estimating the degree of "lively face" with high accuracy and good reproducibility.

It is a figure which shows the relationship between the average evaluation value (hereinafter, also referred to as a score value) of "a face that looks lively" and age. It is a figure which shows the spectrum pattern which is the result of FFT processing of the image which was divided into the color channels of 1024 × 1024 pixels. It is a figure which shows the correlation coefficient of the score value and the power value of each spatial frequency. It is a figure which shows the relationship between the estimated value of the multiple regression analysis result, and the score value of a face which seems to be lively. It is an image in which the power value of R4 c / iw is removed (0 times processing) or emphasized (5 times processing). It is an image in which the power value of R6 c / iw is removed (0 times processing) or emphasized (5 times processing). It is an image in which the power value of R10 c / iw is removed (0 times processing) or emphasized (5 times processing). It is an image in which the power value of R11 c / iw is removed (0 times processing) or emphasized (5 times processing). It is an image in which the power value of R25 c / iw is removed (0 times processing) or emphasized (5 times processing). It is an image in which the power values of G19 c / iw, G22 c / iw, and G28 c / iw are removed (0 times processing) or emphasized (5 times processing). It is an image in which the power values of B3 c / iw and B15 c / iw are removed (0 times processing) or emphasized (5 times processing). It is an image in which the power values of R62 c / iw and G75 c / iw are removed (0 times processing) or emphasized (5 times processing). It is an image in which the power values of B79 c / iw and B127 c / iw are removed (0 times processing) or emphasized (5 times processing). It is an image in which the power values of R74 c / iw and G57 c / iw are removed (0 times processing) or emphasized (5 times processing). It is an image in which the power values of B41 c / iw, B44 c / iw, and B62 c / iw are removed (0 times processing) or emphasized (5 times processing). It is a flow figure which shows the specific aspect of the estimation method of this invention. It is a hardware block diagram of the estimation device of this invention. It is a graph which shows the evaluation result of "the degree of lively face". It is a representative figure of the image used for the evaluation of "the degree of lively face". It is a graph which shows the evaluation result of "dullness of cheek". It is a graph which shows the evaluation result of "blood color". It is a graph which shows the evaluation result of "tension (elasticity)". It is a graph which shows the evaluation result of "yellowishness". It is a graph which shows the evaluation result of "stiffness (stiffness)".

<Method of estimating the degree of lively face>
The present invention estimates the degree of lively face of a subject from the face image data of the subject based on the correlation between the intensity of the spatial frequency obtained from the face image data and the degree of lively face. including.

The "lively face" referred to in the present invention refers to a face that is evaluated as a lively face based on the impression that the third party objectively sees.
Specifically, the "lively face" referred to in the present invention is a "person who looks lively" even though he has a straight face, and even if he does not have a smile or other facial expression, the impression that the third party has objectively seen. A face that is evaluated as a lively face.

The "lively face estimation" referred to in the present invention includes the brightness of the cheeks, the dullness under the eyes, the dullness of the cheeks, the plumpness of the cheeks, the complexion, the firmness, and the yellowness of the entire face, as shown in Examples described later. It is selected from dullness, rough skin, and gloss of the skin, preferably 2 or more, more preferably 3 or more, still more preferably 5 or more, and particularly preferably all degrees.

The "face image data" can be acquired according to a fixed method. As a method of acquiring "face image data", for example, a method of photographing a front face using a digital camera or the like and importing the captured information into a personal computer as digital information can be mentioned.

As the face image data of the subject used in the present invention, face image data of the whole face or a part of the face can be used.

When using face image data of all faces, it is more preferable to use all face data excluding the hair portion. Thereby, the degree of the lively face of the subject can be estimated from the face image data of the subject with high accuracy and good reproducibility.
The size of the face image in this case is about 30 cm × 30 cm in consideration of the resolution required for estimating the lively face and the degree of the lively face and the sampling theorem for calculating the intensity of the spatial frequency. The image may be taken in the range of 512 × 512 pixels or more.

Examples of the face image data of the face portion include face image data of the cheeks, under the eyes, lips, eyes, nose, forehead, cheeks, neck and the like.
Above all, facial image data of the cheeks and / or under the eyes can be preferably used.

As shown in Examples described later, the intensity of the spatial frequency obtained from the facial image data of the cheeks and / or the eyes has a high correlation with the lively face.
Therefore, by using the face image data of the cheeks and / or under the eyes, it is possible to estimate the degree of the lively face of the subject from the face image data of the subject with high accuracy and reproducibility.

When using images of the cheeks and / or under the eyes, it is preferable to use images of at least a region of about 2 cm × 2 cm of these parts. By acquiring information on the spatial frequency obtained from the facial image data of the cheeks and / or the eyes, it is possible to estimate the degree of lively face of the subject from the facial image data of the subject with high accuracy and reproducibility. Further, in these cases, the number of pixels of the face image data is preferably 256 pixels or more, more preferably 512 pixels or more.

The present invention preferably has a form of estimation using any one of R (red), G (green), and B (blue) color channel data of the face image.

In the present specification, the "color channel data of any of R (red), G (green), and B (blue) of the face image" refers to the face image data obtained by dividing the color face image into RGB color channels. Color channel data that retains a specific hue.

As a method of acquiring any one of R (red), G (green), and B (blue) color channel data of the face image, a method of providing a color face image to an image processing system and dividing the color channels can be mentioned. Can be done.

By using any of the R (red), G (green), and B (blue) color channel data of the face image, the subject's face image data can be used to obtain the subject's lively face with high accuracy and reproducibility. The degree of can be estimated.

In a preferred embodiment of the estimation method of the present invention, information on cheek brightness, dullness under the eyes, dullness of the cheeks, plumpness of the cheeks, stiff skin, and luster of the skin is effectively utilized as described above. Includes estimating the "lively face" of the skin.
In the present invention, the above-mentioned "lively face" can be obtained by effectively utilizing the information on the brightness of the cheeks, the dullness under the eyes, the dullness of the cheeks, the fluffy feeling of the cheeks, the ruggedness of the skin, and the luster of the skin. When estimating, it is preferable to use the R (red) color channel data among the R (red), G (green), and B (blue) color channel data of the face image.

In addition, a preferred embodiment of the estimation method of the present invention includes estimating the above-mentioned "lively face" by effectively utilizing information on firmness, skin stiffness, and skin gloss.
In the present invention, when the above-mentioned "lively face" is estimated by effectively utilizing the information on the firmness, the rough feeling of the skin, and the gloss of the skin, R (red) and G (green) of the face image are used. ), B (blue) color channel data, G (green) color channel data is preferably used.

Further, in a preferred embodiment of the estimation method of the present invention, the above-mentioned "lively face" is estimated by effectively utilizing the information on the yellowing of the entire face, the rough feeling of the skin, and the gloss of the skin. Including that.
In the present invention, when the above-mentioned "lively face" is estimated by effectively utilizing the information on the yellowing of the entire face, the rough feeling of the skin, and the gloss of the skin, the R (red) of the face image is used. ), G (green), and B (blue), it is preferable to use the B (blue) color channel data.

In the present invention, the spatial frequency may be a form in which the spatial frequencies obtained from preferably two or more types, more preferably three types of color channel data of the RGB color channel data of the face image are used in combination. preferable.
By using the intensity of the spatial frequency obtained from a plurality of color channel data among the RGB color channel data of the face image, it is possible to estimate the degree of the subject's lively face with high accuracy and good reproducibility. ..

"Spatial frequency" is a property of a structure having a spatial period, and refers to the number of repetitions of a structure included in a unit length. Here, the "spatial frequency" refers to the period per meter in the International System of Units, but the number of lines per millimeter is used in the field of image processing.
Further, as a unit of spatial frequency, the number of cycles per image length (cycle / image-wise) can also be used.
The maximum number of cycles included in an image is 1/2 of the number of pixels (pixels, dots) included in the length of the image. That is, if the image has an image length of 512 pixels, the spatial frequency band is 0 to 256 cycles / image-wise, and if the image has an image length of 1024 pixels, the spatial frequency band is 0 to 512 cycles / image-wise.

In the present specification, when referring to the spatial frequency range of any of the color channel data of R (red), G (green), and B (blue) of the face image, it is expressed by "hue spatial frequency range".
For example, when the spatial frequency range acquired from the R (red) color channel data among the R (red), G (green), and B (blue) color channel data of the face image is 4 c / iw. It is expressed as "R 4 c / iw". (See Table 1 Figure 5).

The "spatial frequency intensity" is an amplitude value or power (power logarithm) at each spatial frequency. The intensity of the spatial frequency can be calculated according to a general method.

Specifically, the face image data acquired by the above method is divided into color channels of either RGB, and then commercially available image analysis software (for example, a Fourier phase analysis program manufactured by Imagesense Co., Ltd. or digital) is used. -Amplitude value or power (intensity of spatial frequency) can be calculated by performing FFT (FastFourRieRTRansfoRm: Fast Fourier Transform) using PoplmaGinG manufactured by Being Kids.

FIG. 2 shows a spectrum pattern obtained by FFT processing a gray image of 1024 × 1024 pixels (in the case of color face image data, an image divided into color channels) as an example of spatial frequency analysis.

By FFT processing, the intensity (amplitude value or power value) for each spatial frequency (unit: cycle / image-width) of 0 to 1024/2 can be calculated.
The spatial frequency characteristics of the face image become clear from the calculated intensity (amplitude value or power value) of each spatial frequency.

A major advantage of the present invention is that numerical data (spatial frequency intensity (power spectrum)) necessary for estimating the degree of lively face can be easily obtained from the face image data of the subject. In the present invention, it can be easily and quantitatively calculated by using commercially available software.

The "estimation of the degree of lively face" in the present invention may be a quantitative estimated value, or may be a relative and qualitative estimation based on a preset "index of lively face".

As a quantitative estimation method, specifically, an equation or model showing the correlation between the intensity of the spatial frequency obtained from the face image data and the degree of the lively face was prepared in advance and acquired from the subject. The degree of lively face of the subject is estimated by comparing the intensity of the spatial frequency obtained from the color channel data of R (red), G (green), or B (blue) with the equation or model. The embodiment to be carried out can be preferably mentioned. The estimation accuracy can be improved by adopting such an embodiment.

Here, the correlation between the intensity of the spatial frequency obtained from the face image data and the degree of lively face can be obtained in advance by multivariate analysis such as regression analysis. As the multivariate analysis, those that can utilize the relationship between the objective variable and the explanatory variable are preferable, and discriminant analysis and regression analysis (MLR, PLS, PCR, logistic) can be preferably exemplified.

Of these, particularly preferred are multiple regression analysis (MLR) and non-linear regression analysis (PLS: PaRtialLeastSquaRes). For example, a multiple regression equation can be obtained by performing multiple regression analysis with the intensity of the spatial frequency as the explanatory variable and the lively face as the objective variable. Further, if PLS is performed in the same manner, a prediction formula (prediction model) can be obtained.

Hereinafter, a method of preparing an equation or a model showing the correlation between the intensity of the spatial frequency obtained from the face image data and the degree of the lively face will be described.

Principal component analysis, factor analysis, quantification theory class 1, quantification theory class 2, quantification theory class 3, multidimensional scaling, supervised clustering, neural networks, ensemble learning methods, as methods for obtaining accurate formulas or models. Multivariate analysis such as, etc. can be used as appropriate. Of these, neural networks, discriminant analysis and quantification theory are preferred. These multivariate analyzes can be performed using free software or commercially available products.

Here, in order to obtain an accurate formula or model, a storage unit that stores the correlation between the intensity of the spatial frequency obtained from the face image data and the degree of lively face evaluated visually in advance as input information. ,
Using the correlation as teacher data, a learning unit that generates a trained model in which variables for estimating the degree of lively face of the target person are machine-learned from the face image data of the target person.
It is also possible to use a learning device provided with.

In order to create an equation or model showing the correlation between the intensity of the spatial frequency obtained from the face image data and the degree of lively face, the intensity of the spatial frequency obtained from the face image data and the degree of lively face It is preferable to create a database (DB) with correlations. Here, the number of DBs is preferably 10 or more, more preferably 20 or more, more preferably 50 or more, more preferably 100 or more, still more preferably 200 or more.
As the structure of the DB, for example, in the case of a matrix format, the intensity of the spatial frequency obtained from the face image data can be input to the row and the degree of the lively face can be input to the column.

This DB can be updated by estimating the correlation between the intensity of the spatial frequency obtained from the newly acquired face image data of the subject and the degree of lively face, and then adding the estimated value. good. If necessary, the above-mentioned multivariate analysis can be performed on the updated DB to update the equation or model.

Hereinafter, a method of acquiring information necessary for creating an expression or a model or creating the above DB will be described.

(1) Evaluation of lively face First, in order to obtain an equation or model showing the correlation between the intensity of the spatial frequency obtained from the face image data and the degree of lively face, the evaluator asks about a plurality of persons. Visually evaluate a lively face. The number of persons evaluated is at least 50 or more, preferably 100 or more, and more preferably 500 or more. In addition, it is preferable that the number of people is about the same for each age group. Regarding a lively face, there is often a gap between the evaluation by the person and the evaluation by a third party, so it is desirable that the evaluator is a third party. The selection of evaluators is good from the viewpoint of selecting an appropriate evaluator to represent a third party, such as individual differences of evaluators, gender differences, lively facial differences, palatability, and reproducibility. It is important to consider various issues.
For example, an evaluator having experience and expertise in evaluation in the beauty field is preferably mentioned. The number of evaluators is preferably a plurality, specifically about 5 to 10 people. It is preferable to statistically process the evaluation results by a plurality of evaluators.

In addition, the average value, the median value, etc. excluding the outliers can be calculated to obtain the degree of objective and lively face of each person.
It is desirable to evaluate the degree of lively face using a face image as shown in Examples described later. This is because it is possible to exclude the influence of reducing the evaluation accuracy due to facial expressions, hairstyles and backgrounds, skin color and skin troubles.

(2) Calculation of Spatial Frequency Intensity Next, the spatial frequency intensity is calculated from the facial image data in which the plurality of persons are captured. The calculation of the intensity of the spatial frequency is as described above. The face image used here is preferably the same as the face image used for the above-mentioned lively face evaluation. This makes it possible to more accurately determine the correlation between the intensity of the spatial frequency and the degree of lively face.

Hereinafter, preferred embodiments of the spatial frequency used in the estimation method of the present invention will be described in detail.

In the estimation method of the present invention, the spatial frequency at a spatial frequency (cycle / image-wise) having a value of preferably 1/5 or less, more preferably 1/10, and even more preferably 1/15 of the image length (pixel). It is preferable to use the strength of.

In the following description, unless otherwise specified, it refers to a preferable form when face image data having an image length of 1024 pixels is used.

Further, in the estimation method of the present invention, preferably 2 or more, more preferably 3 or more, more preferably 5 or more, more preferably 8 or more, still more preferably 10 or more, still more preferably 15 or more, particularly preferably all. It is preferable to use the intensity of the spatial frequency of the spatial frequency.

The estimation method of the present invention includes R4 c / iw, R6 c / iw, R10 c / iw, R11 c / iw, R25 c / iw, G19 c / iw, G22 c / iw, G28 c / iw, and B3 c. / Iw, B15 c / iw, R62 c / iw, G75 c / iw, B79 c / iw, B127 c / iw, R74 c / iw, G57 c / iw, B41 c / iw, B44 c / iw, B62 c 1 or more, preferably 2 or more, more preferably 3 or more, more preferably 5 or more, more preferably 8 or more, still more preferably 10 or more, still more preferably 15 or more, particularly preferably all spatial frequencies, selected from / iw. It is preferable to use the intensity of the spatial frequency in.

Further, the estimation method of the present invention includes R4 c / iw, R11 c / iw, G22 c / iw, R62 c / iw, G75 c / iw, B79 c / iw, B127 c / iw, R74 c / iw, 1 or more, preferably 2 or more, more preferably 3 or more, more preferably 5 or more, more preferably 8 or more, further preferably 1 or more, selected from G57 c / iw, B41 c / iw, B44 c / iw, B62 c / iw. Is 10 or more, and it is particularly preferable to use the intensity of the spatial frequency at all spatial frequencies.

Further, the estimation method of the present invention includes 1 or more, preferably 2 or more, more preferably 3 or more selected from R62 c / iw, G75 c / iw, G57 c / iw, B44 c / iw, and B62 c / iw. Particularly preferably, it is preferable to use the intensity of the spatial frequency at all spatial frequencies.

In a particularly preferable embodiment of the present invention, it is determined that the higher the intensity of the spatial frequency of R4 c / iw, the better the brightness of the cheeks, and it is presumed that the face is lively based on the determination.

In a particularly preferable embodiment of the present invention, it is determined that the higher the intensity of the spatial frequency of R6 c / iw, the better the brightness under the eyes, and it is presumed that the face is lively based on the determination.

In a particularly preferable embodiment of the present invention, it is determined that the lower the intensity of the spatial frequency of R10 c / iw, the less the dullness of the cheeks, and it is presumed that the face is lively based on the determination.

In a particularly preferable embodiment of the present invention, it is determined that the higher the intensity of the spatial frequency of R11 c / iw, the better the fluffy feeling of the cheeks, and it is presumed that the face is lively based on the determination.

In a particularly preferable embodiment of the present invention, it is determined that the lower the intensity of the spatial frequency of R25 c / iw, the better the complexion, and it is presumed that the face is lively based on the determination.

In a particularly preferred embodiment of the present invention, the lower the intensity of the spatial frequency of 1 or more, preferably 2 or more, more preferably 3 or more selected from G19 c / iw, G22 c / iw, and G28 c / iw, the cheek. It is judged that the elasticity (elasticity) of the part (entire face) is excellent, and it is estimated that the face is lively based on the judgment.

In a particularly preferable embodiment of the present invention, it is determined that the lower the intensity of the spatial frequency of 1 or 2 selected from B3 c / iw and B15 c / iw, the better the less yellowing of the entire face. Based on the judgment, it is estimated that the face is lively.

In a particularly preferred embodiment of the present invention, one or more, preferably two or more, more preferably three or more, and even more preferably all, selected from R62 c / iw, G75 c / iw, B79 c / iw, and B127 c / iw. It is determined that the lower the intensity of the spatial frequency of, the less the feeling of stiffness (stiffness), and it is presumed that the face is lively based on the determination.

In a particularly preferred embodiment of the present invention, one or more, preferably two or more, more preferably three or more, selected from R74 c / iw, G57 c / iw, B41 c / iw, B44 c / iw, and B62 c / iw. More preferably, it is determined that the lower the intensity of all spatial frequencies, the better the gloss of the skin of the entire face, and it is presumed that the face is lively based on the determination.

Hereinafter, a specific flow of the estimation method of the present invention will be described.

Further, as a specific aspect of the estimation method of the present invention,
Face image acquisition step S1 to acquire face image data from the target person,
The channel division step S2 for acquiring the color channel data of R (red), G (green), and B (blue) from the face image data acquired in the face image acquisition step, and
Spatial frequency calculation step S3 for calculating the intensity of the spatial frequency from at least one of RGB color channel data, and
Applying the calculated spatial frequency intensity to a pre-prepared formula or model showing the correlation between the spatial frequency intensity obtained from the face image data and the lively facial degree, the subject's liveliness Evaluation step S4 to evaluate the degree of the face
A display step S5 for displaying the evaluation result in the evaluation step S4, and a display step S5.
(See FIG. 16).

Here, in the present invention, it is not always necessary to perform all the steps S1 to S5 described above. For example, a spatial frequency calculation step of calculating the intensity of the spatial frequency from at least one of the RGB color channel data of the face image. S3 and
Applying the calculated spatial frequency intensity to a pre-prepared formula or model showing the correlation between the spatial frequency intensity obtained from the face image data and the lively facial degree, the subject's liveliness It may be a form including the evaluation step S4 for evaluating the degree of the face.

Further, in the present invention, it is preferable that the form includes updating the DB (database) based on the result evaluated in the evaluation step S4 and / or accumulating the result evaluated in the evaluation step S4 in the DB (database).
In particular, it is preferable that the above-mentioned update / accumulation is fed back and the evaluation is performed in the evaluation step S4.

The degree of lively face estimated by the present invention can be used as an index when selecting cosmetics.

Specifically, the present invention comprises an application step of applying a skin condition improving agent and / or a cosmetological means to a subject.
A measurement step for measuring the degree of change in the degree of lively face acquired before the application step and estimated by the above-mentioned estimation method, and the degree of change in the degree of lively face after the application step.
Based on the results of the measurement step, the determination step of determining that the higher the rate of increase in the degree of lively face, the more suitable the substance and / or cosmetological means for improving the skin condition of the subject.
It is also a method of selecting a skin condition improving agent and / or a cosmetological means, which is characterized by having.

Examples of skin condition improving agents include commercially available compounds (including peptides), known compounds (including peptides), compound groups obtained by combinatorial chemistry technology, natural components derived from plants and marine organisms, animal tissue extracts, and the like. Substances can be mentioned.

An animal or plant-derived extract is a general term for not only the animal or plant-derived extract itself, but also the extract fraction, the purified fraction, the extract or fraction, and the solvent-removed product of the purified product.
In addition, examples of plant-derived extracts include native or grown plants, extracts using those sold as raw materials for Chinese herbal medicine, and commercially available extracts.

Examples of beauty means include face packs and massage methods.

In addition, the result of the degree of lively face determined by the present invention can be a useful index in counseling regarding skin care (skin care) and makeup method.

Here, the above description can be incorporated as a preferred embodiment of the method for selecting a skin condition improving agent and / or a cosmetological means of the present invention.

<Skin condition improving agent screening method>
The present invention is also a method for screening a skin condition improving agent based on the correlation between the intensity of spatial frequency obtained from facial image data and the degree of lively face.

The present invention
The application process of applying substances to the skin and
A measurement step for measuring the degree of change in the degree of lively face acquired before the application step and estimated by the above-mentioned estimation method, and the degree of change in the degree of lively face after the application step.
Based on the results of the measurement step, the determination step of determining that the higher the rate of increase in the degree of lively face, the better the skin condition improving agent,
It can also be in the form of.

Further, the present invention includes an application step of applying two or more kinds of substances to two or more subjects, respectively.
After the application step, a measurement step for measuring the degree of change in the degree of lively face acquired in advance before the application step and the degree of change in the degree of lively face after the application step.
Based on the measurement results of the measurement step, a determination step of determining that a skin condition improving agent having a higher rate of increase in the degree of lively face is a better skin condition improving agent.
It can also be in the form of.

In the screening method of the present invention, the stain-suppressing and / or improving agent to be screened is not particularly limited, and for example, a commercially available compound (including a peptide), a known compound (including a peptide), or a combinatorial chemistry technique can be used. Examples thereof include the obtained compounds, natural components derived from plants and marine organisms, and substances such as animal tissue extracts.

An animal or plant-derived extract is a general term for not only the animal or plant-derived extract itself, but also the extract fraction, the purified fraction, the extract or fraction, and the solvent-removed product of the purified product.
In addition, examples of plant-derived extracts include native or grown plants, extracts using those sold as raw materials for Chinese herbal medicine, and commercially available extracts.

In the present invention, it is particularly preferable to screen an agent containing a plant-derived extract.

Further, in the present invention, the types of candidate substances to be applied may be 2 or more, preferably 3 or more.
According to the present invention, it is possible to screen a skin condition improving agent that exerts a synergistic skin condition improving effect when a plurality of kinds of candidate substances are applied.

In addition, the screening method of the present invention can be used as a screening target even in the form of cosmetics.
Here, the cosmetic product is preferably applied to the skin. In addition, as cosmetics, for example, wash, lotion, and milky lotion can be preferably mentioned.

Further, in the present invention, the period of the application step is preferably 2 weeks or longer, more preferably 3 weeks or longer, still more preferably 6 weeks or longer, and particularly preferably 10 weeks or longer.
By performing the application step for the above period or longer, the skin condition improving agent can be screened more accurately.

Here, a preferred embodiment of the screening method of the present invention can be referred to the above description.

<Estimator of the degree of lively face>
Hereinafter, the estimation device of the present invention will be described with reference to the hardware block diagram (FIG. 17) of the estimation device of the present invention.

The estimation device 1 of the present invention includes a face image acquisition means 11 for acquiring the face image data of the target person, a channel dividing means 12 for dividing the acquired face image data into specific color channels, and a color face image data of the target person. Of the RGB color channel data of the above, the spatial frequency calculation means 13 for calculating the intensity of the spatial frequency obtained by using the data obtained from an arbitrary channel alone or in combination, and the intensity of the spatial frequency obtained from the face image data. A storage unit 14 for storing correlation data showing a correlation with the degree of lively face, an evaluation means 15, and a display means 16 for displaying the evaluation result of the evaluation means 15 are provided.

The face image acquisition means 11 is a means for acquiring a face image obtained by a device for inputting face image data such as a digital camera, a digital microscope, a digital video, or a scanner.

The channel dividing means 12 divides the face image data into RGB color channels in order to use the color face image data acquired by the face image acquiring means 11 for the spatial frequency calculating means 13 described later, and any of RGB. This is a means for generating grayscale image data (RGB color channel data of a face image) that retains hue.

The spatial frequency calculation means 13 calculates the intensity of the spatial frequency by FFT processing, and is an expression or model (correlation data) showing the relationship between the lively face (lively face or lively face) and the spatial frequency intensity. Execute processing such as calculation.

The storage unit 14 stores a program necessary for the device for estimating the degree of lively face of the present invention to function, and various formulas or models (correlation data) necessary for estimating the degree of lively face. do. The storage unit 14 may further store a database necessary for creating an expression or a model.

The evaluation means 15 is a means for evaluating the degree of the lively face of the subject based on the intensity of the spatial frequency calculated by the spatial frequency calculation means 13 and the correlation data stored in the storage unit 14. ..

The display means 16 is a means for instructing an arbitrary display device to display the evaluation result by the evaluation means 15.
Here, the display device may be any device that can display the estimation result of the degree of lively face, for example, a display device using a CRT (CathodeRayTuBu), a liquid crystal display, an audio output device such as a speaker, a printer, or the like. Can be mentioned.

In the present invention, it is not always necessary to provide the above configuration. For example, the spatial frequency calculating means 13 for calculating the intensity of the spatial frequency obtained from at least one of the RGB color channel data of the face image and the spatial frequency calculating means 13.
The calculated spatial frequency intensity is applied to a pre-prepared formula or model showing the correlation between the spatial frequency intensity obtained from the face image data and the lively face, and the lively face of the subject is applied. Evaluation means 15 for evaluating the degree of
It may be in the form of an estimation device including.

Further, the present invention estimates the degree of lively face of the subject from the face image data of the subject based on the correlation between the intensity of the spatial frequency obtained from the face image data and the degree of lively face. It may be in the form of an estimation device that includes

Here, a preferred embodiment of the estimation device of the present invention can be referred to the above description.

<Lively face degree estimation program>
In the estimation program of the present invention, the computer, other device, machine, etc. are divided into a face image acquisition means 11 for acquiring the face image data of the target person and a channel dividing means 12 for dividing the acquired face image data into specific color channels. The spatial frequency calculation means 13 for calculating the intensity of the spatial frequency obtained by using the data obtained from an arbitrary channel alone or in combination among the RGB color channel data of the subject's color face image data, and the face. As a storage unit 14 that stores correlation data showing the correlation between the intensity of the spatial frequency obtained from the image data and the degree of lively face, the evaluation means 15, and the display means 16 that displays the evaluation results of the evaluation means 15. Make it work (see Figure 17).

In the present invention, it is not necessary to be a program that functions all of the above configurations. For example, among the RGB color channel data of the color face image data of the computer, the data obtained from an arbitrary channel can be used alone. Alternatively, the spatial frequency calculating means 13 for calculating the intensity of the spatial frequency obtained by the combination and
The calculated spatial frequency intensity is applied to a pre-prepared formula or model showing the correlation between the spatial frequency intensity obtained from the face image data and the lively face, and the lively face of the subject is applied. Evaluation means 15 for evaluating the degree of
It may be in the form of an estimation program that functions as.

Further, the present invention uses a computer.
To function to estimate the degree of lively face of the subject from the face image data of the subject based on the correlation between the intensity of the spatial frequency obtained from the face image data and the degree of lively face. , May be in the form of an estimation program.

Further, the present invention may be a program in which such a program is recorded on a recording medium that can be read by a computer or the like.

Here, the above description can be incorporated as a preferred embodiment of the estimation program of the present invention.

The test results on which the present invention is based are shown below.

<1> Lively facial evaluation (1) Preparation of images to be evaluated First, facial images of 272 women aged 18 to 82 (average 49.1 years, SD = 16.91) were taken. Based on the captured face image, 1024 × 1024 pixel image data for use in the test was created. Here, in creating the image to be used for the test, hair and ears were removed from the original image, the left and right pupils were fixed at a fixed position in the image, and the size and position of the face were standardized.

(2) Impression evaluation 20 healthy women (5 in their 20s, 5 in their 30s, 5 in their 40s, 5 in their 50s, average 39.6 years old, SD = 11.3) are "lively faces". Was evaluated as.
The above evaluator evaluated "whether or not the person in the face image prepared in (1) looks lively" on the following seven stages.
In addition, in order to avoid bias in the reaction of the evaluators, the presentation order of the facial images was changed for each evaluator and used for the test. The average evaluation value (hereinafter referred to as the score value) of the "face that looks lively" for each face image was calculated.

Score 1: Very lively and invisible Grade 2: Very lively and invisible Grade 3: Somewhat lively and invisible Grade 4: Neither can be said 5: Somewhat lively grade 6: Somewhat lively grade 7: Very lively Looks lively

(3) Relationship between score value and age The score value was set on the vertical axis and the age was set on the horizontal axis, and the relationship between the score value and age was illustrated (Fig. 1).
As shown in FIG. 1, the score value did not decrease with aging.
That is, it was found that there was no correlation between the score value and age.

(4) Relationship between score value and intensity of each spatial frequency (4-1) Spatial frequency analysis of face image First, the color face image used for the test in (2) is divided into RGB color channels by an image processing system, and R. Color channel data (corresponding to face image data in the present specification) of (red), G (green), and B (blue) were obtained. Of R (red), G (green), and B (blue), color channel data holding a specific hue is used in-house spatial frequency analysis software by MATLAB (registered trademark) manufactured by TheMathWoRk for spatial frequency analysis. Was done.

Spatial frequency analysis using MATLAB® revealed that the color channel data of any of R (red), G (green), and B (blue) of the face image used in the test (2) was 1 to 512. The power value (spatial frequency intensity) of cycle / image-width (hereinafter, c / iw) was obtained.

(4-2) Derivation of the correlation coefficient between the score value and the power value of each spatial frequency For each color channel data of R (red), G (green), or B (blue), the score value and each spatial frequency The correlation coefficient of the power value was derived. The results are shown in FIG.
As shown in FIG. 3, a significant power value correlating with the score value could be confirmed.

(4-3) Multiple regression analysis Multiple regression analysis was performed on the score value and the power value of each spatial frequency, and the characteristic power value was confirmed.
Here, the multiple regression analysis was performed by the stepwise method with the score value as the objective variable and the power value of each spatial frequency as the explanatory variable.
The results are shown in Table 1. In Table 1, items in which the sign (positive or negative) of the estimated value (hereinafter, simply referred to as the estimated value) of the multiple regression analysis result and the sign (positive or negative) of the correlation coefficient shown in FIG. 3 match are selected.

Hereinafter, in this embodiment, the spatial frequency range of the data acquired from the color channel data holding a specific hue among the color channel data of any of R (red), G (green), and B (blue) is defined. When referring to it, it is expressed as "hue spatial frequency range of divided color channels".
For example, when the spatial frequency range of the data acquired from the R (red) color channel data among the R (red), G (green), and B (blue) color channel data is 4 c / iw, " It is expressed as "R 4 c / iw". (See Table 1 Figure 5).

R-squared: 0.444658
Degree of freedom adjustment R-squared: 0.402787
ANOVA: F value <0.0001

Estimating formula: = -2.528026029 + 1.7914917386xR4 + 0.903084107xR6-1.043600467xR10 + 1.6881883003xR11-1.052159449xR25-2.241496576xR62 + 1.95448954779xR74-0.6474420451xG19-1.634556714xG19-1.63556714x22. −0.960381395xB15 + 1.8566437495xB41 + 2.0914472xB44 + 3.7029702782xB62-1.8766045866xB79-1.65718134xB127

For each face image data acquired in (1), the score value was set on the vertical axis, and the estimated value by the multiple regression equation (hereinafter, simply referred to as the estimated value) was set on the horizontal axis, and the relationship between the score value and the estimated value was illustrated ( FIG. 4).
As shown in FIG. 4, it was found that the higher the score value, the higher the estimated value.
That is, it was found that the multiple regression equation derived in this example shows the correlation between the score value (the degree of lively face) and the estimated value.

<2> Verification of the estimated value of the degree of lively face The result derived in <1> was verified.

We verified what kind of features each power value at the spatial frequency shown in Table 1 reflected in the impression of the face.
For the above verification, an image in which the power value at a specific spatial frequency was removed or emphasized was prepared, and the image was used for evaluation by an expert specializing in skin condition technology.

(1) Verification of what characteristics the power value of the spatial frequency range R4 c / iw reflects in the face image.

As shown in Table 1, the correlation coefficient between the power value of R4 c / iw and the lively face is 1.791. The higher the power value of R4 c / iw, the more lively the face is evaluated.

To confirm the above evaluation, an image in which the power value of R4 c / iw was removed (0 times processing) or emphasized (5 times processing) was prepared. The results are shown in FIG.
As shown in FIG. 5, it was found that the higher the power value of R4 c / iw, the more vivid the face.

As shown in FIG. 5, it was found that the cheek portion was dark in the image in which the power value was removed (0 times processed), and the cheek portion was brightened in the image in which the power value was removed (5 times processed).
That is, it was found that the power value of R4 c / iw is highly related to the cheek.
And the power value of R4 c / iw changed with respect to the brightness of the cheeks.

(2) Verification of what characteristics the power value of the spatial frequency range R6 c / iw reflects in the face image.

As shown in Table 1, the correlation coefficient between the power value of R6 c / iw and the lively face is 0.0965. The higher the power value of R6 c / iw, the more lively the face is evaluated.

To confirm the above evaluation, an image in which the power value of R6 c / iw was removed (0 times processing) or emphasized (5 times processing) was prepared. The results are shown in FIG.
As shown in FIG. 6, it was found that the higher the power value of R6 c / iw, the more vivid the face.

As shown in FIG. 6, it was found that the image under the eyes was dark in the image in which the power value was removed (0 times processed), and the area under the eyes was bright in the image in which the power value was removed (processed 5 times).
That is, it was found that the power value of R6 c / iw is highly relevant under the eyes.
Then, it was found that the power value of R6 c / iw was related to the brightness under the eyes.

(3) Verification of what characteristics the power value of the spatial frequency range R10 c / iw reflects in the face image.

As shown in Table 1, the correlation coefficient between the power value of R10 c / iw and the lively face is −0.0118. The lower the power value of R10 c / iw, the more lively the face is evaluated.

To confirm the above evaluation, an image in which the power value of R10 c / iw was removed (0 times processing) or emphasized (5 times processing) was prepared. The results are shown in FIG.
As shown in FIG. 7, it was found that the lower the power value of R6 c / iw, the more vivid the face.

As shown in FIG. 7, it was found that the cheeks were bright in the image in which the power value was removed (0 times processed), and the cheeks were dull in the image in which the power value was removed (5 times processed).
That is, it was found that the power value of R10 c / iw is highly related to the cheek.
Then, it was found that the power value of R10 c / iw was related to the dullness of the cheeks.

(4) Verification of what characteristics the power value of the spatial frequency range R11 c / iw reflects in the face image.

As shown in Table 1, the correlation coefficient between the power value of R11 c / iw and the lively face is 0.1487. The higher the power value of R11 c / iw, the more lively the face is evaluated.

To confirm the above evaluation, an image in which the power value of R11 c / iw was removed (0 times processing) or emphasized (5 times processing) was prepared. The results are shown in FIG.
As shown in FIG. 8, it was found that the higher the power value of R11 c / iw, the more vivid the face.

As shown in FIG. 8, it was found that the cheeks did not feel plump in the image in which the power value was removed (0 times processed), and the cheeks appeared plump in the image in which the power value was removed (5 times processed).
That is, it was found that the power value of R11 c / iw is highly related to the cheek.
Then, it was found that the power value of R11 c / iw was related to the fluffy feeling of the cheeks.

(5) Verification of what characteristics the power value of the spatial frequency range R25 c / iw reflects in the face image.

As shown in Table 1, the correlation coefficient between the power value of R25 c / iw and the lively face is −0.1887. The lower the power value of R25 c / iw, the more lively the face is evaluated.

To confirm the above evaluation, an image in which the power value of R25 c / iw was removed (0 times processing) or emphasized (5 times processing) was prepared. The results are shown in FIG.
As shown in FIG. 9, it was found that the lower the power value of R25 c / iw, the more vibrant the face.

As shown in FIG. 9, it was found that in the image in which the power value was removed (0 times processed), the complexion of the entire face looked good, and in the image in which the power value was removed (5 times processed), the complexion of the entire face looked bad.
That is, it was found that the power value of R25 c / iw is highly related to the entire face.
Then, it was found that the power value of R25 c / iw was related to the goodness of the complexion.

(6) Verification of what characteristics the power values of the spatial frequency ranges G19 c / iw, G22 c / iw, and G28 c / iw reflect in the facial image.

As shown in Table 1, the correlation coefficient between the power value of G19 c / iw and the lively face is -0.1325. The lower the power value of G19 c / iw, the more lively the face is evaluated.

Further, as shown in Table 1, the correlation coefficient between the power value of G22 c / iw and the lively face is −0.2519. The lower the power value of G22 c / iw, the more lively the face is evaluated.

Further, as shown in Table 1, the correlation coefficient between the power value of G28 c / iw and the lively face is −0.1685. The lower the power value of G28 c / iw, the more lively the face is evaluated.

To confirm the above evaluation, an image in which the power values of G19 c / iw, G22 c / iw, and G28 c / iw were removed (0 times processing) or emphasized (5 times processing) was prepared. The results are shown in FIG.
As shown in FIG. 10, it was found that the lower the power values of G19 c / iw, G22 c / iw, and G28 c / iw, the more vivid the face.

As shown in FIG. 10, the image with the power value removed (0 times processed) has elasticity (elasticity) of the cheek (entire face), and the image with the power value (5 times processed) has the cheek (entire face). It turned out that it looked without elasticity.
That is, it was found that the power values of G19 c / iw, G22 c / iw, and G28 c / iw are highly related to the entire face.
Then, it was found that the power values of G19 c / iw, G22 c / iw, and G28 c / iw were related to the firmness (elasticity) of the cheek (whole face).

(7) Verification of what characteristics the power values of the spatial frequency ranges B3 c / iw and B15 c / iw reflect in the facial image.

As shown in Table 1, the correlation coefficient between the power value of B3 c / iw and the lively face is -0.1042. The lower the power value of B3 c / iw, the more lively the face is evaluated.

Further, as shown in Table 1, the correlation coefficient between the power value of B15 c / iw and the lively face is −0.1752. The lower the power value of B15 c / iw, the more lively the face is evaluated.

To confirm the above evaluation, an image in which the power values of B3 c / iw and B15 c / iw were removed (0 times processing) or emphasized (5 times processing) was prepared. The results are shown in FIG.
As shown in FIG. 11, it was found that the lower the power values of B3 c / iw and B15 c / iw, the more vivid the face.

As shown in FIG. 11, in the image in which the power value is removed (0 times processed), there is no yellowing of the entire face, and in the image in which the power value is removed (5 times processed), the entire face has yellowing. I understood.
That is, it was found that the power values of B3 c / iw and B15 c / iw are highly related to the entire face.
Then, it was found that the power values of B3 c / iw and B15 c / iw were related to the yellowing of the entire face.

(8) Verification of what characteristics the power values of the spatial frequency ranges R62 c / iw, G75 c / iw, B79 c / iw, and B127 c / iw reflect in the facial image.

As shown in Table 1, the correlation coefficient between the power value of R62 c / iw and the lively face is -0.0334. The lower the power value of R62 c / iw, the more lively the face is evaluated.

Further, as shown in Table 1, the correlation coefficient between the power value of G75 c / iw and the lively face is −0.1973. The lower the power value of G75 c / iw, the more lively the face is evaluated.

Further, as shown in Table 1, the correlation coefficient between the power value of B79 c / iw and the lively face is −0.1033. The lower the power value of B79 c / iw, the more lively the face is evaluated.

Further, as shown in Table 1, the correlation coefficient between the power value of B127 c / iw and the lively face is −0.2388. The lower the power value of B127 c / iw, the more lively the face is evaluated.

To confirm the above evaluation, an image in which the power values of R62 c / iw, G75 c / iw, B79 c / iw, and B127 c / iw were removed (0 times processing) or emphasized (5 times processing) was prepared. The results are shown in FIGS. 12 and 13.
As shown in FIGS. 12 and 13, it was found that the lower the power values of R62 c / iw, G75 c / iw, B79 c / iw, and B127 c / iw, the more vivid the face.

As shown in FIGS. 12 and 13, the entire face is smooth in the image in which the power value is removed (0 times processing), and the entire face has a stiff feeling (stiffness) in the image in which the power value is (5 times processed). I understood.
That is, it was found that the power values of R62 c / iw, G75 c / iw, B79 c / iw, and B127 c / iw are highly related to the entire face.
Then, it was found that the power values of R62 c / iw, G75 c / iw, B79 c / iw, and B127 c / iw were related to the feeling of stiffness.

(9) What features do the power values of the spatial frequency ranges R74 c / iw, G57 c / iw, B41 c / iw, B44 c / iw, and B62 c / iw reflect in the facial image? inspection

As shown in Table 1, the correlation coefficient between the power value of R74 c / iw and the lively face is 0.0598. The higher the power value of R74 c / iw, the more lively the face is evaluated.

Further, as shown in Table 1, the correlation coefficient between the power value of G57 c / iw and the lively face is 0.0182. The higher the power value of G57 c / iw, the more lively the face is evaluated.

Further, as shown in Table 1, the correlation coefficient between the power value of B41 c / iw and the lively face is 0.0922. The higher the power value of B41 c / iw, the more lively the face is evaluated.

Further, as shown in Table 1, the correlation coefficient between the power value of B44 c / iw and the lively face is 0.0717. The higher the power value of B44 c / iw, the more lively the face is evaluated.

Further, as shown in Table 1, the correlation coefficient between the power value of B62 c / iw and the lively face is 0.0177. The higher the power value of B62 c / iw, the more lively the face is evaluated.

To confirm the above evaluation, an image in which the power values of R74 c / iw, G57 c / iw, B41 c / iw, B44 c / iw, and B62 c / iw are removed (0 times processing) or emphasized (5 times processing). I prepared. The results are shown in FIGS. 14 and 15.
As shown in FIGS. 14 and 15, it was found that the higher the power value of R74 c / iw, G57 c / iw, B41 c / iw, B44 c / iw, and B62 c / iw, the more vivid the face. ..

As shown in FIGS. 14 and 15, in the image in which the power value is removed (0 times processed), the entire face is not smooth and the skin is glossy, and in the image in which the power value is removed (5 times processed), the entire face is covered with skin. It turned out to be glossy and smooth.
That is, it was found that the power values of R74 c / iw, G57 c / iw, B41 c / iw, B44 c / iw, and B62 c / iw are highly related to the entire face.
Then, it was found that the power values of R74 c / iw, G57 c / iw, B41 c / iw, B44 c / iw, and B62 c / iw were related to the luster of the skin.

(10) Results and Discussion Table 2 shows the results of the verifications (1) to (9) above.

From the results of this example, based on the correlation between the intensity of the spatial frequency obtained from the face image data and the degree of lively face, the degree of lively face of the subject is determined from the face image data of the subject. It turns out that it can be estimated.

In particular, from the results of this example, R4 c / iw, R6 c / iw, R10 c / iw, R11 c / iw, R25 c / iw, G19 c / iw, G22 c / iw, G28 c / iw, B3 c / iw, B15 c / iw, R62 c / iw, G75 c / iw, B79 c / iw, B127 c / iw, R74 c / iw, G57 c / iw, B41 c / iw, B44 c / iw, B62 It was found that the degree of lively face can be estimated by using the power value at one or more spatial frequencies selected from c / iw.

<3> Examination of a method for selecting a skin condition improving agent and / or a beauty means and a screening method for a skin condition improving agent Next, a method for selecting a skin condition improving agent and / or a beauty means based on the above findings, And, the screening method was examined.

(1) Preparation step (1-1) Preparation of test product First, the test products (wash, lotion, milky lotion) shown below were prepared.

[Wash]
A wash was prepared according to the formulation shown below.

<Wash prescription>
Fatty acid 40.0 parts by weight glycerin 19.2 parts by weight diglycerin 3.5 parts by weight carboxymethyl cellulose Na 0.4 parts by weight acrylic acid / dimethyldialylammonium chloride / acrylamide copolymer solution 2.0 parts by weight dimethyldialylammonium chloride / acrylamide Copolymer liquid 4.5 parts by weight potassium hydroxide 8.5 parts by weight alkyl glycoside 1.5 parts by weight plant extracts 0.4 parts by weight water 20 parts by weight

[Toner]
A cosmetic product, which is an external preparation for skin, was prepared according to the formulation shown below. That is, the following formulation components were heated to 80 ° C., stirred and solubilized, and stirred and cooled to obtain a lotion.

<Toner prescription>
1,2-Hexanediol 3 parts by weight 1,3-butanediol 5 parts by weight Glycerin 2 parts by weight Phenoxyethanol 0.5 parts by weight Plant extracts 2 parts by weight Polyoxyethylene hydrogenated castor oil 0.1 parts by weight Ethanol 5 parts by weight

[Emulsion]
A cosmetic product, which is an external preparation for skin of the present invention, was prepared according to the formulation shown below. That is, the components a, b, and c are each heated to 70 ° C., b is neutralized with c, a is gradually added while stirring to emulsify, homogenize with a homogenizer, and then stirred and cooled to prepare the emulsion. Obtained.

<Emulsion prescription>
Isqualan 10 parts by weight sorbitan sesquistearate 2 parts by weight plant extracts 2.1 parts by weight butylparaben 0.1 parts by weight b 1,3-butanediol 5 parts by weight xanthan gum 0.1 parts by weight alkyl methacrylate / alkyl methacrylate ( C10-30) 0.4 parts by weight methylparaben 0.1 parts by weight water 50 parts by weight potassium hydroxide 0.2 parts by weight water 30 parts by weight

(1-2) Subjects and test product usage conditions In this study, 19 female subjects were 35-49 years old (mean age 41.6 ± 4.54 years old).

During the test period, the subjects replaced with the skin care products they usually use, or additionally applied the above three types of test products (wash, lotion, and milky lotion).
At this time, the subject used the test product on the face every day (twice a day in the morning and evening) according to an appropriate usage.
The subjects continued to use the usual make-up products other than the above-mentioned test products.

(2) Measurement process (spatial frequency analysis method)
(2-1) Acquisition of images for analysis Remove hair and ears from facial images taken at 0 week (before use), 4 weeks, and 12 weeks after the start of use of the test product, and image the left and right pupils. An image of 1024 × 1024 pixels was created by fixing the image at a fixed position and standardizing the size and position of the face (see FIG. 19).

(2-2) Acquisition and selection of power value By fast Fourier transform (FFT) using spatial frequency analysis (R2009a manufactured by MATLAB (registered trademark) TheMathWoRk), 1512 cycles / image width (hereinafter, hereafter, R, G, B) for each of R, G, and B. A power value of c / iw) was obtained.

From the obtained power values, the power values related to the "degree of lively face" as shown in the table were extracted. Here, the extracted power values are R4 c / iw, R6 c / iw, R10 c / iw, R11 c / iw, R25 c / iw, G19 c / iw, G22 c / iw, G28 c / iw, B3. c / iw, B15 c / iw, R62 c / iw, G75 c / iw, B79 c / iw, B127 c / iw, R74 c / iw, G57 c / iw, B41 c / iw, B44 c / iw, B62 It is a power value at the spatial frequency of c / iw.

(3) Judgment process Based on the measured values in the measurement process, the usefulness of the candidate substance to be screened as an inhibitor and / or ameliorating agent for skin pigmentation symptoms was evaluated.

(3-1) Evaluation of "degree of lively face" The change in "degree of lively face" was calculated by substituting the extracted power value into the above-mentioned estimated value and calculating. The results are shown in FIG. A representative example of the facial image of the subject is shown in FIG.

As shown in the results of FIG. 18, it was found that the change in "the degree of lively face" can be evaluated by applying the test product.
That is, it was found that the above method makes it possible to select a skin condition improving agent and / or a cosmetological means.
It was also found that the skin condition improving agent can be screened from the candidate substances by the above method.

(3-2) Evaluation of each element of "degree of lively face" Next, each element related to "degree of lively face" was evaluated based on the extracted power value. The results are shown in FIGS. 20 to 24.

In FIG. 20, a significant decrease in the “dullness of the cheeks” was observed between the 0th week and the 4th week.
Here, as described above, the correlation coefficient sign between the rating value (see the estimation formula described above) and the power value of R10 c / iw is “−”.
Therefore, from this evaluation, it was obtained that "the test product can be presumed to be a candidate substance for improving the dullness of the cheeks".

Further, in FIG. 21, a significant decrease in the “blood color” was observed between the 0th and 4th weeks and between the 0th and 12th weeks.
Here, as described above, the correlation coefficient sign between the rating value (see the estimation formula described above) and the power value of R25 c / iw is “−”.
Therefore, from this evaluation, it was obtained that "the test product can be presumed to be a candidate substance for improving blood color".

Further, in FIG. 22, regarding "tension (elasticity)", a significant decrease was observed between the 0th week and the 4th week and the 0th week and the 12th week.
Here, as described above, the correlation coefficient code between the rating value (see the estimation formula described above) and the power value of G19 c / iw, G22 c / iw, and G28 c / iw is “−”.
Therefore, from this evaluation, it was obtained that "the test product can be presumed to be a candidate substance for improving elasticity".

Further, in FIG. 23, a significant decrease in the “yellowing of the entire face” was observed between the 0th and 4th weeks and between the 0th and 12th weeks.
Here, as described above, the correlation coefficient sign between the rating value (see the estimation formula described above) and the power values of B3 c / iw and B15 c / iw is “−”.
Therefore, from this evaluation, it was obtained that "the test product can be presumed to be a candidate substance for improving the yellowing of the entire face".

Further, in FIG. 24, a significant decrease in the “stiffness” was observed between the 0th and 4th weeks and between the 0th and 12th weeks.
Here, as described above, the correlation coefficient sign between the rating value (see the estimation formula above) and the power value of R62 c / iw, G75 c / iw, B79 c / iw, and B127 c / iw is "-". ..
Therefore, from this evaluation, it was obtained that "the test product can be presumed to be a candidate substance for improving the feeling of stiffness (stiffness)".

As shown in the results of FIGS. 20 to 24, by applying the three types of test products (wash, lotion, milky lotion), based on the judgment of each element related to the "degree of lively face", "lively" It was found that the change in "degree of face" can be evaluated.

As described above, it was found that the skin condition improving agent and / or the cosmetological means can be selected by the above method.
In addition, it was found that the skin condition improving agent can be screened from the candidate substances by the above method.

The technique for estimating the degree of lively face of the present invention can be used in the evaluation of the effects of esthetics, skin care, make-up, health foods, cosmetic shaping, etc., or in advice and counseling using the evaluation results.

Claims (14)

Estimating, including estimating the degree of lively face of the subject from the face image data of the subject, based on the correlation between the intensity of the spatial frequency obtained from the face image data and the degree of lively face. Method. Color of face image Among the RGB color channel data of face image data, the spatial frequency calculation step of calculating the intensity of the spatial frequency obtained by using the data obtained from an arbitrary channel alone or in combination, and
Applying the calculated spatial frequency intensity to a pre-prepared formula or model showing the correlation between the spatial frequency intensity obtained from the face image data and the lively facial degree, the subject's liveliness An evaluation process that evaluates the degree of facial appearance
The estimation method according to claim 1. The estimation method according to claim 2, wherein the formula is a multiple regression formula obtained by multiple regression analysis or a prediction formula obtained by PLS. In a preferred embodiment of the present invention, the degree of lively face is as follows: cheek brightness, dullness under the eyes, cheek dullness, cheek plumpness, complexion, firmness, yellowing of the entire face, skin. The estimation method according to any one of claims 1 to 3, which comprises at least one degree of ruggedness and gloss of the skin. The estimation method according to any one of claims 1 to 4, wherein the face image data is face image data of a facial part or the entire face. Any one of claims 1 to 5, wherein the face image data is color face image data, and the spatial frequency is a spatial frequency obtained from at least one of RGB color channel data of the color face image data. The estimation method described in. The estimation method according to claim 6, wherein the spatial frequency is a spatial frequency obtained from a plurality of color channel data among the RGB color channel data of the face image. The estimation method according to any one of claims 1 to 7, wherein the spatial frequency range (cycle / image-wise) of the spatial frequency is 0 to 512 cycles / image-wise when the image has an image length of 1024 pixels. The application process of applying the skin condition improving agent and / or cosmetological means to the subject, and
The degree of change in the degree of lively face estimated by the estimation method according to any one of claims 1 to 8 acquired before the application step and the degree of change in the degree of lively face after the application step. The measurement process to be measured and
Based on the results of the measurement step, the determination step of determining that the higher the rate of increase in the degree of lively face, the more suitable the skin condition improving agent and / or the beauty means for the subject.
A method for selecting a skin condition improving agent and / or a cosmetological means. A screening method for skin condition improving agents based on the correlation between the intensity of spatial frequency obtained from facial image data and the degree of lively face. The application process of applying substances to the skin and
The degree of change in the degree of lively face estimated by the estimation method according to any one of claims 1 to 8 acquired before the application step and the degree of change in the degree of lively face after the application step. The measurement process to be measured and
Based on the results of the measurement step, a determination step of determining that a skin condition improving agent having a higher rate of increase in the degree of lively face is a better skin condition improving agent.
10. The screening method according to claim 10. Spatial frequency calculation means for calculating the intensity of the spatial frequency obtained by using the data obtained from an arbitrary channel alone or in combination among the RGB color channel data of the color face image data.
Applying the calculated spatial frequency intensity to a pre-prepared formula or model showing the correlation between the spatial frequency intensity obtained from the face image data and the lively face, the subject's lively face Evaluation means to evaluate the degree and
An estimation device. Computer,
Spatial frequency calculation means for calculating the intensity of the spatial frequency obtained by using the data obtained from an arbitrary channel alone or in combination among the RGB color channel data of the color face image data.
Applying the calculated spatial frequency intensity to a pre-prepared formula or model showing the correlation between the spatial frequency intensity obtained from the face image data and the lively face, the subject's lively face Evaluation means to evaluate the degree and
An estimation program to function as. A storage unit that stores the correlation between the intensity of the spatial frequency obtained from the face image data and the degree of lively face as input information.
Using the correlation as teacher data, a learning unit that generates a trained model in which variables for estimating the degree of lively face of the target person are machine-learned from the face image data of the target person.
A learning device equipped with.

Images