JP2007252892A - Estimation method of evaluation value by visual recognition of three-dimensional shape of skin surface - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a method of estimating evaluation values by a visual recognition of the three-dimensional shape of the skin surface and an apparatus and program for calculating the evaluation values by the visual recognition of the three-dimensional shape of the skin surface and enables anybody to estimate the evaluation values by the visual recognition of the three-dimensional shape of the skin surface handily and objectively in a quantitative manner. <P>SOLUTION: Correlationship of the evaluation values by the visual recognition of the three-dimensional shape of the skin surface is utilized with a fractal dimension in the distribution of display color-based signals of images of the skin to estimate the evaluation values by the visual recognition of the three-dimensional shape of the skin surface. <P>COPYRIGHT: (C)2008,JPO&INPIT

Description

  The present invention relates to a technique for estimating a visual evaluation value of a three-dimensional shape of a skin surface, and more particularly to a technique for estimating a visual evaluation value of a three-dimensional shape of a skin surface using a fractal dimension of a skin property value as an index.

  Recognizing that the skin is beautiful by a third party is one of the great wishes of many people as well as women. For this reason, research and development of cosmetics and beauty methods for showing beautiful skin are being actively conducted. However, the skin condition varies greatly depending on the individual, and also changes depending on the aging and living environment. Therefore, in order to appropriately select the type of cosmetics, makeup method, skin care method, etc. It is necessary to objectively judge how the skin to be seen looks to a third party. For example, in department store cosmetics departments, pharmacies, and cosmetics stores, there is a demand for simple methods for evaluating the wrinkle condition and smoothness of subjects.

Various studies have been conducted on the elements that make up the visual skin beauty, and the size and number of wrinkles on the skin surface and other irregularities such as pores are known to greatly affect the skin beauty. Yes. Conventionally, evaluation of the shape of the skin surface has been carried out by directly observing the skin image, but in recent years, image information obtained by imaging the skin surface or its replica with an appropriate photoelectric conversion means is programmed. A method for quantitatively evaluating the skin surface shape and optical properties has been reported.
For example, by illuminating a skin replica with a plurality of light sources and extracting a skin groove pattern, a device for analyzing the skin groove interval and skin groove direction (Patent Document 1) and the brightness of the skin surface image in multiple stages There has been reported a method (Patent Document 2) for measuring a skin surface shape by converting a signal value and statistically processing the signal value. However, in order to estimate how the three-dimensional shape of the skin is viewed by a third party, a skin evaluation specialist analyzes the measurement results based on the specialized knowledge based on individual measurement data. There is a problem that it is necessary to perform sensory evaluation visually by a pair comparison or the like, and to perform statistical processing each time. That is, with the conventional method, it has been difficult to accurately and simply evaluate the three-dimensional shape of the skin surface.

  In such a technical background, by measuring and processing a specific property value of the skin obtained from a photograph or replica of the skin, the correlation between this value and the visual evaluation of the wrinkle state of the skin was found, and the skin Attempts have been made to evaluate the appearance of wrinkles. For example, a method has been reported in which a luminance signal is obtained by irradiating the skin surface or the like from each direction, and then a statistical calculation process is performed to obtain a characteristic value representing a skin surface shape characteristic. It has been reported that there is a correlation with the visual evaluation value of the surface (Patent Document 3). In addition, a skin surface analysis system has been reported that obtains light and dark peak data by processing a two-dimensional sample image in which the fine light and dark distribution on the skin surface is emphasized, and calculates characteristic values such as light and dark peak roughness. It has been reported that there is a correlation between the texture appearance roughness score (Patent Document 4).

  In such a technique, the relationship between a specific property value and wrinkles has been recognized in part, but in order to obtain these property values, a process such as irradiating a plurality of lights in stages is required. There were some parts that were necessary and could not be said to be simple methods. On the other hand, research and elucidation about the numerical value indicating the skin properties that correlate with the visual evaluation value of the three-dimensional shape of the skin surface are not yet sufficient, and as an index to evaluate the three-dimensional shape of the skin surface A number with higher utility value was being sought.

  On the other hand, the concept of fractal is a geometric concept used for self-similar figures created in research in the mathematical field. Moreover, it is known that many things which have a fractal shape exist in nature. As one means for expressing a shape having a fractal property, it is known to obtain a fractal dimension. In recent years, a method for determining a specific state in a living body by calculating a fractal dimension has been reported. For example, the biological signal of the subject's characteristic anxiety level is subjected to fractal analysis, and the anxiety level is evaluated from correlation with statistical data (Patent Document 5), or the reflected ultrasonic pulse signal from the tissue is subjected to fractal analysis. (Patent document 6) which investigates the state of this, and the automatic detection system (patent document 7) of the malignant cell using fractal analysis are disclosed.

  Further, a method for evaluating the distribution of melanin pigment in skin from the correlation between the pigment distribution of melanin and the like and the fractal dimension of the luminance of pixels constituting the skin image is disclosed (Patent Document 8). Further, it has been reported that the skin age may be estimated using the fractal dimension of the skin property value as an index (Non-patent Document 1). However, a specific method of using the fractal dimension has not been clarified, and the relationship between the fractal dimension and the skin age, the relationship between the fractal dimension and the visual evaluation value of the three-dimensional shape of the skin surface, etc. has not been found.

JP 61-64232 A Japanese Patent Laid-Open No. 2-46833 JP-A-5-329133 Japanese Patent Laid-Open No. 6-189842 JP 2001-299702 A Japanese National Patent Publication No. 11-507846 Special table 2001-512824 gazette JP 2000-135207 A “Skin age estimation method using skin image features and application for prevention of skin aging” (Masao Kasuga, New Technology Briefing Meeting from Northern University of Northern Tokyo, December 2, 2005)

  The present invention provides a method for estimating a visual evaluation value of a three-dimensional shape of a skin surface, an apparatus and a program for calculating a visual evaluation value of a three-dimensional shape of a skin surface, and who estimates the visual evaluation value of a three-dimensional shape of a skin surface. However, the objective is to make it easy and objective to perform quantitatively. In addition, the present invention further provides a method of obtaining a skin property value and processing means related to a third-party visual evaluation value of the three-dimensional shape of the skin surface, and obtaining a visual evaluation value of the three-dimensional shape of the skin surface with high accuracy. This is the issue.

As a result of repeated studies on the beauty of the skin, the present inventors have found a causal relationship between the visual evaluation value of the three-dimensional shape of the skin surface and the fractal dimension of various skin property values. Using this relationship, if the visual evaluation value of the three-dimensional shape of the skin surface is estimated from the fractal dimension of the subject, a result very close to the visual evaluation value of the three-dimensional shape of the skin surface by an actual third party can be obtained. I found out that I could do this and completed the invention.
That is, the present invention is as follows.

(1) obtaining a binary image of the skin;
Calculating a fractal dimension of the binary image;
By substituting the calculated fractal dimension into a regression equation representing the relationship between the fractal dimension of the binary image of the prepared skin and the visual evaluation value of the three-dimensional shape of the skin surface, the visual evaluation value of the three-dimensional shape of the skin surface is calculated. Process,
Method for Estimating Visual Evaluation Value of Three-dimensional Shape of Skin Surface Including
(2) The method according to (1), wherein the binary image is obtained by binarization processing of an RGB value, a YUV value, or a Munsell (HVC) value.
(3) The method according to (1) or (2), wherein the fractal dimension is calculated by a correlation dimension method.
(4) acquiring the undulation value of the skin;
Calculating a fractal dimension of the distribution of the relief values;
By substituting the calculated fractal dimension into a regression equation representing the relationship between the fractal dimension of the distribution of the undulation value of the skin and the visual evaluation value of the three-dimensional shape of the skin surface, the visual evaluation value of the three-dimensional shape of the skin surface is obtained. Process,
Method for Estimating Visual Evaluation Value of Three-dimensional Shape of Skin Surface Including
(5) The method according to (4), wherein the fractal dimension is calculated by a box counting method.
(6) In the box counting method, the box size is determined based on a standard deviation of property values in the box.
(7) means for obtaining a binary image of the skin;
Means for calculating a fractal dimension of the binary image;
By substituting the calculated fractal dimension into a regression equation representing the relationship between the fractal dimension of the binary image of the prepared skin and the visual evaluation value of the three-dimensional shape of the skin surface, the visual evaluation value of the three-dimensional shape of the skin surface is calculated. Means,
Means for displaying the calculated visual evaluation value;
Estimating device for visual evaluation value of three-dimensional shape of skin surface including
(8) means for obtaining the undulation value of the skin;
Means for calculating a fractal dimension of the distribution of the relief values;
Substituting the calculated fractal dimension into a regression equation that represents the relationship between the fractal dimension of the distribution of skin relief and the visual evaluation value of the three-dimensional shape of the skin surface, and calculating the visual evaluation value of the three-dimensional shape of the skin surface. Means to
Means for displaying the calculated visual evaluation value;
Estimating device for visual evaluation value of three-dimensional shape of skin surface including
(9) Connect the computer
Means for calculating a fractal dimension of a binary image of the skin;
By substituting the calculated fractal dimension into a regression equation representing the relationship between the fractal dimension of the binary image of the prepared skin and the visual evaluation value of the three-dimensional shape of the skin surface, the visual evaluation value of the three-dimensional shape of the skin surface is calculated. means,
For estimating the visual evaluation value of the three-dimensional shape of the skin surface for functioning as
(10) Connect the computer
Means for calculating the fractal dimension of the distribution of skin relief,
Substituting the calculated fractal dimension into a regression equation that represents the relationship between the fractal dimension of the distribution of skin relief and the visual evaluation value of the three-dimensional shape of the skin surface, and calculating the visual evaluation value of the three-dimensional shape of the skin surface. Means to
For estimating the visual evaluation value of the three-dimensional shape of the skin surface for functioning as

  By using the method and apparatus of the present invention, it is possible to easily and objectively and quantitatively estimate the visual evaluation value of the three-dimensional shape of the skin surface such as wrinkles using various skin property values. .

In the present invention, the visual evaluation value of the three-dimensional shape of the skin surface is a statistical evaluation that represents how well the three-dimensional shape of the skin surface looks when a person visually recognizes the skin. For example, when comparing one skin with another, this is a statistical evaluation obtained by repeatedly determining which of the three-dimensional shapes of the skin surface looks better. Here, the three-dimensional shape of the skin surface refers to the skin surface irregularities formed by at least one of the skin groove / cutaneous structure, pores, acne, pimples, and these marks within a visually recognizable range. Say. The structure of the skin groove and skin hill includes “wrinkles” in which the depth of the skin groove is deeper than other skin grooves (see Yakuji Nipposha, Usefulness of Cosmetics, 2001, p. 162-177). ). Note that the visual evaluation value in the present invention does not include a subjective evaluation value obtained by processing and processing information input from the eyes by human mental activity.

  In the present invention, in order to obtain a visual evaluation value of the three-dimensional shape of the skin surface, it is necessary to obtain at least one property value selected from the binary image of the skin and the undulation value of the skin.

In order to obtain a skin binary image, first, a color system image signal is acquired for the skin surface.
Examples of the color system image signal include RGB values, YUV values, Munsell (HVC) values, L ^* a ^* b ^* values, L ^* C ^* h ^* values, Lab values, and Yxy values. Among these, it is particularly preferable to use RGB values, YUV values, and Munsell (HVC) values. The RGB value represents a color by a combination of the three primary colors of red (R), green (G), and blue (B). For example, in the case of representing each with 256 gradations, about 16.77 million. Color tone expression is possible. The YUV value represents a color by a combination of luminance (Y), color difference (U = blue-Y), and color difference (V = red-Y). The Munsell (HVC) value is a JIS color system that expresses colors with three components of hue, lightness, and saturation. At least one component constituting such a color system image signal may be a property value, or a plurality of components may be property values.

In order to obtain a color system image signal for the skin surface, first, the skin surface of the subject is imaged. The part of the skin to be imaged is not particularly limited as long as it is a part for which a visual evaluation value of the three-dimensional shape of the skin surface is to be estimated. For example, when the estimated value is used in the selection of cosmetics such as foundation and teak, it is preferable to image the cheek. In general, it is preferable to select a region that represents the skin of the subject and avoid a site with many scratches or spots.
Moreover, the range for acquiring the image is not particularly limited as long as the information necessary for the analysis can be obtained, but the range of 1 cm * 1 cm to 3 cm * 3 cm is preferable on the skin surface.

The means for acquiring the image signal of at least one color system of the skin image is not particularly limited. For example, it can be performed using devices such as a color digital microscope, a color digital camera, a color video camera, and a scanner. Such equipment may be commercially available or manufactured. Preferable examples of commercially available products include i-scope and CCD microscope manufactured by Moritex Co., Ltd., USB video microscope manufactured by Fortesimo Co., Ltd., and digital microscope manufactured by Keyence Corporation.
The imaging magnification may be a magnification suitable for an apparatus used for imaging. For example, when using a digital camera equipped with a macro lens, it is preferable to obtain a close-up photographed image at a distance of about 20 cm from the target at the same magnification, and when using a video microscope (for example, Moritex i-scope) It is preferable to enlarge the image to about 30 to 50 times and take an image. Thus, the amount of information when acquiring an image may be 300 * 300 pixels (dots, pixels) or more when converted to a range of 2 cm * 2 cm, preferably 500 * 500 pixels or more, More preferably 700 * 700 pixels or more.

Further, the specific image signal can be converted into any other image signal according to a conventional method. For example, YUV values, L ^* a ^* b ^* values, L ^* C ^* h ^* values, Lab values, and Yxy values can be converted from RGB values using a conversion formula. A conversion table can be used for conversion to Munsell (HVC) values. For example, when converting from RGB values to YUV values, the RGB values can be converted to YUV values using the following formula (A) after performing γ correction of the RGB values using commercially available software or the like.

  The color system image signal acquired in this way is transferred to a computer and then subjected to noise removal processing by a median filter, smoothing processing by a smoothing filter, low frequency cut filter processing for removing specular reflection light, etc. Pretreatment is preferably performed. It is particularly preferable to perform a smoothing process. By performing the smoothing process, a large variation in the property value for each pixel can be corrected, and the fractal dimension can be calculated with higher accuracy. The mask size in this case is

If necessary, the respective components of the preprocessed color system image signal are binarized. The threshold for binarization can be determined using the histogram of the image. Examples of such a method include “Otsu's method” (see IEICE Transactions '80 / 4 Vol. J63-D No. 4).
Next, for each bit plane of the color system image signal, a logical product (AND) of the components of the image signal is obtained to obtain a binary image of the skin.

  Among the three-dimensional shape of the skin, when it is desired to estimate the visual evaluation value for the structure of the skin and the skin, especially wrinkles, the thinning process is performed on the binary image of the skin obtained by calculating the logical product by the 8-neighbor processing. It is preferable (see FIG. 7). Such thinning process removes noises such as the effects of color and hair, stains and light reflection caused by relatively large uneven structures such as pores, acne, etc., and ensures only the crevice and skin structure. Can be extracted.

  The above-described preprocessing such as color image signal acquisition, smoothing processing, image signal binarization, logical product processing, and thinning processing can be performed using commercially available image analysis software. For example, WinROOF (registered trademark) of Mitani Shoji Co., Ltd., Adobe Photoshop (registered trademark) of Adobe Systems, NanoHunter NS2K-Pro (registered trademark) of Nano Systems Co., Ltd. can be exemplified. Note that the software for smoothing processing is also available on the Internet, so that it can also be used.

A fractal dimension is calculated for the skin binary image thus obtained.
Examples of the method for calculating the fractal dimension from the acquired binary image of the skin include a box-counting method, a correlation dimension method, and a fractional Brownian motion model method. Among these, the correlation dimension method is preferably used. A method for calculating the fractal dimension will be described later.

The undulation value is a numerical value indicating how high a point covering the surface of a certain object is from the reference plane.
The undulation value of the skin can be obtained directly from the surface of the skin, or it can be obtained by obtaining a replica of the skin surface and measuring the surface shape of the replica. From the viewpoint of obtaining an accurate undulation value, it is preferable to use a replica.

  The part of the skin from which the replica is obtained is not particularly limited as long as it is a part for which the visual evaluation value of the three-dimensional shape of the skin surface is to be estimated, and examples thereof include facial skin such as cheeks, upper arm inner part, and the like. When the evaluation value is used for selecting cosmetics, it is preferable to obtain a cheek replica. For example, a 2 cm * 2 cm measurement region of the cheek may be set, and a replica of the portion including this may be acquired. The replica agent is not particularly limited, and examples thereof include silicon ASB-01-WW manufactured by Asahi Biomed Co., Ltd. The method of collecting a replica can be performed by a conventional method used for diagnosing skin shape and the like. For example, the replica agent may be applied to the skin placed for about 20 minutes at 20 ° C. and 50% humidity after washing the face, and then collected.

Next, the undulation value of the replica thus produced is measured. The method for measuring the undulation value is not particularly limited, and a normal method can be used. For example, “Wrinkle Evaluation Method Guidance”, Journal of the Japan Cosmetic Science Society, Vol. 28, No. 2 (2004) can be referred to.
Specifically, for example, using a commercially available laser type three-dimensional surface roughness meter, laser scanning is performed in the horizontal direction (x) and the vertical direction (y) with respect to the face portion as shown in FIG. You can go and measure. As such a three-dimensional roughness meter, for example, a high-precision three-dimensional image processing apparatus LIP (for example, LIP-50) of Science Systems Co., Ltd., SURFCOM of Tokyo Seimitsu Co., Ltd., VLH, PRIMOS of Lasertec Co., Ltd. (GFM Co., Ltd.) And derma-TOP-blue (manufactured by Breuckmann).
The scan interval when measuring the undulation value using these devices is not particularly limited as long as sufficient data can be obtained to calculate the fractal dimension, but it is preferably performed at an interval of 10 μm or less.
For example, when scanning using the LIP-50, 1000 scans can be performed at 10 μm intervals in the X or Y direction with respect to the replica region where X * Y is 1 cm * 1 cm.

  When obtaining the undulation value, if the sampling periods in the x direction and the y direction are different, it is preferable to correct the sampling period using a Sinc function (see FIG. 8).

  In addition, by applying oblique illumination to the replica using an optical projection device, etc., extracting the shadow part of the replica convex part, and measuring the depth, area ratio, etc. of the concave part of the skin from its area and width, etc. You can also get a value. Acquisition of the undulation value by irradiation with such oblique illumination is preferable in terms of simplicity. The undulation value can be obtained by this method using, for example, a reflection 3D replica analysis system (Asahi BioMed).

  It is also possible to obtain the undulation value of the replica by irradiating light to the translucent replica and determining the thickness of the replica from the amount of transmitted light (translucent replica light transmission method). Acquisition of the undulation value by this method can be performed using, for example, 3D skin analysis system ASA-03 (Asahi Biomed).

  Moreover, as a method of obtaining the undulation value directly from the surface of the skin, for example, a method of applying a lattice-like light to the skin and converting the refractive index of the light to the undulation value is used, and a commercially available device or the like is used. it can. Examples of such devices include PRIMOS (manufactured by GFM), derma-TOP-blue (manufactured by Breuckmann), and the like.

  The skin undulation value thus obtained is subjected to fractal analysis, and the distribution of the skin undulation value in the measurement region, that is, the fractal dimension of the shape of the skin surface is calculated.

As a method of calculating the fractal dimension from the acquired undulation value, a box counting method (box-counting), a correlation dimension method, a fractional brownian
For example, a motion model method may be used. Among these, it is preferable to use a box counting method.

Hereinafter, a method for calculating the fractal dimension will be described in detail.
In the correlation dimension method, when the correlation integral C (r) defined by the equation (1) is scaled with the equation (B), the inclination of the graph of logC (r) vs. log (r) is expressed as a correlation dimension (fractal). Dimension) D.

The box counting method is to divide a square (cube) that completely covers an object into squares (cubes) of any size, and to divide the size of the square (cube) and part of the object (cube) This is a method for obtaining the fractal dimension from the relationship with the number.
When a certain shape is specifically defined as N (h), the number of squares (cubes) covering a part of the object when a square (cube) that completely covers the object is divided by the length h of one side is N (h) Between r and N (h),
N (h) = c · h ^−D (c is a constant coefficient) (2)
When the above approximate expression holds with a good correlation, it can be said that the object has a fractal shape. At this time, D in the expression (2) becomes a fractal dimension.
Therefore, in order to obtain the fractal dimension D by the box counting method, it is only necessary to logarithmically plot c · h and N (h) and obtain the slope of the obtained straight line.

  Such a box counting method is very simple and can be processed at high speed by a computer. However, the farther the target fractal dimension is from the half integer value, the lower the analysis accuracy. Therefore, instead of simply determining whether a part of the object falls within the box as in the general box counting method, the effective box size is determined based on the standard deviation of the data in the box, It is preferred to use a method that includes determining whether a portion of the object falls within the box.

Such calculation of the fractal dimension can be specifically performed by the following method.
(1) First, as shown in FIG. 1, the two-dimensional discrete data f (x, y) existing in the size X × Y is divided into areas S _i (x, y) of size h × h (m). When the image signal is used, the discrete data existing in X × Y is a pixel, and when the undulation value is used, the data is the height from the reference plane. h can be arbitrarily determined.

(2) for each of the regions S ₁ to S _m, is obtained by equation (3) below the standard deviation σ ₁ ~σ _m of property value (see FIG. 2).

  (3) N (h) at size h is calculated by the following equation (4).

  By calculating N (h) in this way, it is possible to count the number of boxes using the standard deviation in the h × h region Si as the effective box height. It becomes possible to suppress the influence of noise. In addition, a wide scaling range of nearly 1 to 2 digits, which is indispensable for estimating the fractal dimension, can be obtained.

(4) The size h is increased and f (x, y) is subdivided, and N (h) is calculated in the same manner using the procedures (1) to (3).
(5) Repeat (4) until h = X or h = Y, and calculate N (h).
(6) The fractal dimension D is obtained from the slope of the graph representing the relationship between logN (h) and log (see FIG. 3).

  The visual evaluation value of the three-dimensional shape of the skin surface is estimated using the fractal dimension of the binary image of the skin of the subject or the fractal dimension of the distribution of the undulation value of the skin thus obtained. For this purpose, a regression equation representing the relationship between the fractal dimension of the skin binary image or the fractal dimension of the skin relief value distribution and the visual evaluation value of the three-dimensional shape of the skin surface is prepared in advance by the following method. Keep it.

The regression equation can be created, for example, by the following method, but is not limited to this method.
1) For a plurality of skins in which the skin condition, age, etc. are sufficiently distributed (hereinafter collectively referred to as samples), the fractal dimension of the skin binary image or the undulation value of the skin is calculated. Image processing, measurement of undulation values, calculation of fractal dimension, and the like can be performed according to the method described above. The number of samples used at this time is 30 or more, preferably 50 or more.

2) Next, an evaluator suitable for representing a third party is prepared, and the three-dimensional shape of the skin surface of the skin is visually evaluated. Specific evaluation criteria can be set arbitrarily. For example, the visual evaluation value of wrinkles can be obtained by performing the evaluation based on the criterion of “small wrinkles and shallow wrinkles”. Further, a visual evaluation value of the unevenness on the skin surface can be obtained based on the criterion of “small unevenness”. Further, by combining these standards, for example, a standard of “smooth” can be set. These evaluations may be absolute evaluations such as scoring, but are preferably relative evaluations such as ranking in comparison with another sample in order to ensure objectivity. . In the ranking, if there is no difference, the ranking may be the same. At this time, in order to further ensure objectivity, it will be described that the evaluation is performed only on the visible skin elements. Here, an evaluator suitable for representing a third party can recognize at least the skin surface irregularities such as the skin / drape structure, pores, acne and pimples, and these marks. What is necessary is just a thing which can judge whether a solid shape is favorable, and age and sex are not ask | required. The number of evaluators is usually 4 or more, preferably 10 or more.

  3) The operation of 2) is preferably repeated for each sample. What is necessary is just to adjust the frequency | count of work suitably by the number of evaluators. In order to obtain an objective evaluation result, the evaluation is usually repeated 3 times or more, preferably 4 times or more, more preferably 5 times or more.

  4) Next, the visual evaluation value of the three-dimensional shape of the skin surface is calculated for each sample. Here, as for the visual evaluation value, the obtained score itself may be used, or when the relative evaluation is performed by ranking, even if the ranking itself is used, the three-dimensional shape of the skin surface is in ascending order. High numbers may be given. In addition, these evaluation values may be a total for each sample or an average value. For example, when ranking is performed for n samples, the average value of the total score of each sample can be obtained by setting the i-th score to n−i + 1 and can be used as the evaluation value. Further, a deviation value of each sample can be obtained from the average value and standard deviation of the samples and used as evaluation values, or these values can be divided into arbitrary stages as evaluation values.

  5) The skin binary image obtained in 1) or the fractal dimension of the skin relief value and the visual evaluation value obtained in 4) are subjected to regression analysis, and a regression equation (prediction equation) indicating the relationship between these values is obtained. Such regression analysis can be performed by a conventional method, for example, using commercially available statistical processing software.

  Next, regarding the skin of the subject, the calculated fractal dimension of the binary image of skin or the fractal dimension of the skin, and the visual observation of the fractal dimension of the skin binary image or the fractal dimension of the undulation value and the three-dimensional shape of the skin surface, respectively. The visual evaluation value of the three-dimensional shape of the skin surface of the subject can be estimated by substituting it into the regression equation representing the correlation with the evaluation value. The estimated value of the visual evaluation value of the three-dimensional shape of the skin surface thus obtained can be displayed as a numerical value as it is, but by processing it into easy-to-use data such as a deviation value and a predefined rank, This is preferable because it is easy to use in counseling and advice situations. For example, between the minimum and maximum visual evaluation values of the sample used in the creation of the regression equation used to estimate the visual evaluation value of the three-dimensional shape of the skin surface, equally divide it into any number of ranks. It can be displayed with alphabets or numbers, or can be displayed with words indicating the state of the three-dimensional shape of the skin surface, such as words indicating the state of unevenness on the skin surface, such as words indicating the wrinkle state.

  In addition, the fractal dimension of the subject can be shown on the regression line drawn by the regression equation used, the position and rank in the sample group can be shown in the figure, or it can be displayed as a photograph-like image or stereogram. it can. The display method of the figure is not particularly limited, and can be displayed on, for example, a display of a device or a print medium.

  The apparatus for estimating the visual evaluation value of the three-dimensional shape of the skin surface according to the present invention includes means for obtaining a binary image of skin, means for calculating a fractal dimension of the binary image, and a binary image of skin prepared in advance. Means for substituting the calculated fractal dimension into a regression equation representing the relationship between the fractal dimension of the skin surface and the visual evaluation value of the three-dimensional shape of the skin surface, and a means for calculating the visual evaluation value of the three-dimensional shape of the skin surface, and the calculated visual evaluation value Means for displaying.

The visual evaluation value estimation apparatus of the present invention can be configured as follows, for example. The following configuration is an example, and the present invention is not limited to the configuration of the embodiment.
FIG. 4 is a hardware block diagram of an apparatus that estimates a visual evaluation value of a three-dimensional shape of a skin surface using a binary image of skin and a fractal dimension of undulation values. As shown in FIG. 4, the evaluation apparatus 1 includes an input unit 1, a CPU (Central Processing Unit) 2, a ROM (Read Only Memory) 3, a RAM (Random Access Memory) 4, a magnetic disk device 5, a recording unit 6, and an operation. Part 7 and display part 8. These are connected to each other via a bus. The input unit 1 is a device that inputs skin image signals such as a color digital microscope, a color digital camera, a color video camera, and a scanner, and a device that measures skin undulation values such as a three-dimensional roughness meter. The input unit 1 may have either one of a means for inputting an image signal and a device for measuring the undulation value, or may have both. In accordance with the program stored in the ROM 3, the CPU 2 calculates the fractal dimension by the preprocessing, binarization of RGB values, data processing such as AND processing, thinning processing, correlation dimension method, box counting method, etc., regression Processing such as calculation of a visual evaluation value using an expression is executed. The ROM 3 stores programs necessary for the functioning of the evaluation apparatus of the present invention, various regression equations necessary for visual evaluation, and the like. The RAM 4 temporarily stores a part of OS (Operating System) programs and application programs to be executed by the CPU 2. The magnetic disk device 5 is used as an external storage of the RAM 4 and has a recording unit 6. The operation unit 7 is operated when inputting necessary data such as predetermined commands and regression equations. The display unit 8 only needs to be able to display the estimated value of the evaluation value. For example, the display unit 8 includes a CRT (Cathode Ray Tube), a liquid crystal display, a plasma display or the like, an audio output device such as a speaker, a printer, or the like. Output devices.

  Further, the present invention may be a program for causing a computer, another device, a machine, or the like to execute part or all of the processing. Further, the present invention may be a program in which such a program is recorded on a computer-readable recording medium.

  Hereinafter, the present invention will be described in detail with reference to examples, but the scope of the present invention is not limited thereby.

<Example 1>
Correlation between fractal dimension of binary image (RGB) and visual evaluation value of three-dimensional shape of skin surface Fractal dimension of binary image of skin using images of cheeks of 39 women in their 10s and 50s A multiple regression equation representing the relationship with the visual evaluation value of the three-dimensional shape of the skin surface was obtained. That is, for the 39 persons, a part 10 * 7 mm (size 640 * 480 pixels) shown in FIG. 5 was photographed 30 minutes after washing the face using a commercially available digital microscope (Moritex i-scope) 30 × lens. did. Subsequently, a central area 5 * 5 mm (size 300 * 300 pixels) of the photographing area is extracted (see FIG. 6), and binary values of each RGB value by the low-frequency cut filter process and the histogram process are extracted in this central area. Thinning processing was performed by logical product (AND) processing and 8-neighbor processing for each bit plane (binary image with wrinkle 1 and background 0) (see FIG. 7). For this binary image, the fractal dimension was calculated using a program that causes a computer to execute the correlation dimension method for calculating the fractal dimension.

  On the other hand, a third party visually evaluated the three-dimensional shape of the skin surface of the 39 female cheeks (see FIG. 6). As a third party, 4 panelists were selected, 39 cheek photos were presented, and the three-dimensional shape of the skin surface was visually recognized based on the criteria of “low wrinkles and shallow wrinkles” They were ranked in the order they were given. Each operation was performed four times independently, and 40- (rank) when arranged in the order of visual recognition as good was used as the score. That is, the score of the best photo is 40 and the score of the poorest photo is 1. Next, for each photograph, the average value of the scores was calculated and used as a visual evaluation value for the three-dimensional shape of the skin surface.

  Furthermore, regression analysis was performed with the visual evaluation value (y) of the three-dimensional shape of the skin surface obtained above as an objective variable and the fractal dimension (x) obtained above as an explanatory variable. The obtained regression equation was y = 104.9 * x-159.2, and the correlation coefficient was 0.906 (p <0.01). Thus, it can be seen that the fractal dimension of the RGB values and the visual evaluation value of the three-dimensional shape of the skin surface have a high correlation.

<Example 2>
Estimation of wrinkle visual evaluation value using fractal dimension of binary image (RGB) Extracting wrinkle structure from RGB by the above method (see FIG. 7) using 248 cheeks of 10-50 generations as samples, The fractal dimension was calculated by the correlation dimension method. Moreover, after calculating | requiring the score of the skin wrinkle by the third party's visual evaluation similarly to Example 1, the deviation value was made into the visual evaluation value. Next, regression analysis was performed using the visual evaluation value (y) of the skin wrinkle as an objective variable and the fractal dimension (x) as an explanatory variable. The obtained regression equation was y = 167.2 * x-233.3, and the correlation coefficient was 0.890 (p <0.01).

  Next, RGB values are acquired from cheek photographs of five female subjects not included in the 248 subjects, the fractal dimension is calculated by the correlation dimension method as described above, and the calculated fractal dimension (x) is calculated as the regression. The visual evaluation value (y) of skin wrinkles was calculated by substituting into the equation. Visual evaluation values of cheek photographs of five female subjects were obtained in the same manner as described above, and the results were compared. The results are shown in Table 1. According to this, it can be seen that the estimated value of the visual evaluation value of the wrinkle of the skin using the fractal dimension and the visual evaluation value are in good agreement.

<Example 3>
Estimating visual evaluation values of unevenness using undulation values For 39 people who acquired cheek area photographs in Example 1, using a commercially available silicon from the cheek area shown in FIG. After collecting the replica specimen, three-dimensional undulation data was obtained using a high-precision three-dimensional image processing apparatus LIP-50 manufactured by Science Systems Corporation. About 1 cm * 1 cm area | region of the center part of the replica, 1000 scans were performed by the space | interval of 10 micrometers in the y direction (vertical direction). Since the sampling period in the x direction and the y direction is different from 9.4 μm and 10 μm, respectively, the LIP-50 is supplemented using the Sinc function so that the interval in the xy direction is 10 μm. The fractal dimension was calculated using the box counting method (FIG. 3).

On the other hand, a third party visually evaluated the three-dimensional shape of the skin surface of the 39 female cheeks (see FIG. 6). As a third party, four panelists were selected, 39 cheek photos were presented, and the order of the three-dimensional shape of the skin surface was determined by combining the criteria of “small unevenness”. I was given a ranking. Each operation was performed four times independently, and 40- (rank) when arranged in the order of visual recognition as good was used as the score. That is, the score of the best photo is 40 and the score of the poorest photo is 1. Next, for each photograph, the average value of the scores was calculated and used as a visual evaluation value for the three-dimensional shape of the skin surface.

Regression analysis was performed on the visual evaluation value (y) of the unevenness on the skin surface of the 39 cheek photographs obtained above and the fractal dimension (x) calculated from the undulation value. The correlation between the two is shown in FIG. The obtained regression equation was y = 66.1 * x-133.9 and the correlation coefficient was 0.933 (p <0.01), which showed a significant and high correlation.
Next, a fractal dimension was obtained from the undulation value obtained in the same manner as described above from a replica sample of the cheek part of a 45-year-old female subject, and substituted into the regression equation to estimate the visual evaluation value of the unevenness on the skin surface. The fractal dimension of the undulation value obtained from the replica specimen of this female subject was D = 2.24, and the estimated visual evaluation value of the unevenness on the skin surface was 14.2. Separately, when visual evaluation was performed on the unevenness of the skin surface, the evaluation value was 13, and good agreement was observed.

  According to the present invention, it is possible to objectively and easily distinguish the three-dimensional shape of the skin surface such as wrinkles, which is visible to the eyes of a third party, so that anyone can estimate the visual evaluation value of the three-dimensional shape of the skin surface of the subject. Can do. By using the method and apparatus of the present invention, it is possible to provide appropriate information on the site such as advice on skin counseling, care methods and selection of cosmetics.

It is a figure which shows the concept of the division | segmentation in a box counting method. It is a figure which shows the concept of the count of a box counting method. It is a figure which shows a fractal dimension. It is a hardware block diagram of an example of the estimation apparatus of the visual evaluation value of the three-dimensional shape of the skin surface of this invention. It is a figure which shows the example of the measurement object area | region of a face. It is a figure which shows the example of a cheek part photograph used for evaluation of this invention (photograph). It is a figure which shows the wrinkle structure (thinned image) extracted by performing a thinning process to the AND image after the low frequency cut filter process of the image data and the binarization process of RGB values. It is a figure which shows what correct | amended the undulation value data obtained from the replica by the Sinc function. It is a figure which shows the relationship between the visual evaluation value of the unevenness | corrugation feeling of the skin surface, and the fractal dimension of the undulation value of the skin replica.

Claims (10)

Obtaining a binary image of the skin;
Calculating a fractal dimension of the binary image;
By substituting the calculated fractal dimension into a regression equation representing the relationship between the fractal dimension of the binary image of the prepared skin and the visual evaluation value of the three-dimensional shape of the skin surface, the visual evaluation value of the three-dimensional shape of the skin surface is calculated. Process,
Method for Estimating Visual Evaluation Value of Three-dimensional Shape of Skin Surface Including   The method according to claim 1, wherein the binary image is obtained by binarization processing of RGB values, YUV values, or Munsell (HVC) values.   The method according to claim 1, wherein the fractal dimension is calculated by a correlation dimension method. A step of obtaining a relief value of the skin;
Calculating a fractal dimension of the distribution of the relief values;
By substituting the calculated fractal dimension into a regression equation representing the relationship between the fractal dimension of the distribution of the undulation value of the skin and the visual evaluation value of the three-dimensional shape of the skin surface, the visual evaluation value of the three-dimensional shape of the skin surface is obtained. Process,
Method for Estimating Visual Evaluation Value of Three-dimensional Shape of Skin Surface Including   The method according to claim 4, wherein the fractal dimension is calculated by a box counting method.   6. The method according to claim 5, wherein in the box counting method, the box size is determined based on a standard deviation of property values in the box. Means for obtaining a binary image of the skin;
Means for calculating a fractal dimension of the binary image;
By substituting the calculated fractal dimension into a regression equation representing the relationship between the fractal dimension of the binary image of the prepared skin and the visual evaluation value of the three-dimensional shape of the skin surface, the visual evaluation value of the three-dimensional shape of the skin surface is calculated. Means,
Means for displaying the calculated visual evaluation value;
Estimating device for visual evaluation value of three-dimensional shape of skin surface including Means for obtaining skin relief values;
Means for calculating a fractal dimension of the distribution of the relief values;
Substituting the calculated fractal dimension into a regression equation that represents the relationship between the fractal dimension of the distribution of skin relief and the visual evaluation value of the three-dimensional shape of the skin surface, and calculating the visual evaluation value of the three-dimensional shape of the skin surface. Means to
Means for displaying the calculated visual evaluation value;
Estimating device for visual evaluation value of three-dimensional shape of skin surface including Computer
Means for calculating a fractal dimension of a binary image of the skin;
By substituting the calculated fractal dimension into a regression equation representing the relationship between the fractal dimension of the binary image of the prepared skin and the visual evaluation value of the three-dimensional shape of the skin surface, the visual evaluation value of the three-dimensional shape of the skin surface is calculated. means,
For estimating the visual evaluation value of the three-dimensional shape of the skin surface for functioning as Computer
Means for calculating the fractal dimension of the distribution of skin relief,
Substituting the calculated fractal dimension into a regression equation that represents the relationship between the fractal dimension of the distribution of skin relief and the visual evaluation value of the three-dimensional shape of the skin surface, and calculating the visual evaluation value of the three-dimensional shape of the skin surface. Means to
For estimating the visual evaluation value of the three-dimensional shape of the skin surface for functioning as

Images