JP6527765B2 - Wrinkle state analyzer and method - Google Patents

Description

  The present invention relates to analysis technology of skin image.

  Wrinkles that occur on the face, neck, etc. are factors that greatly affect the appearance age of human impression. However, the evaluation of the wrinkle state is generally performed by visual observation, and a method of quantifying is being considered. The following Patent Document 1 proposes a method for evaluating the wrinkle state of the skin. The proposed method extracts wrinkle information including the position and size of each wrinkle from the skin image, and evaluates the wrinkle state by comparing the extracted wrinkle information with the wrinkle information obtained in the past. .

  Patent Document 2 below proposes a wrinkle state analysis method for quantifying the wrinkle state of the skin based on the skin image. The proposed method extracts linear texture images for each of a plurality of predetermined angles from the skin luminance image of the analysis target portion, and linear (linear) components of each predetermined angle from each of the extracted linear texture images Extract the intensities respectively. Then, using the extracted linear (linear) component intensities of the predetermined angles, wrinkle state information of the skin of the analysis target portion is generated.

JP, 2010-119431, A JP, 2015-62569, A

  The above-described proposed method of Patent Document 1 extracts wrinkle information by obtaining a three-dimensional shape of a wrinkle portion specified from a certain region of a captured image by using a replica. Therefore, the above-mentioned patent document 1 does not disclose the specific method which pinpoints one wrinkles area directly from a photography picture.

  In this respect, Patent Document 2 described above extracts various linear components that appear on the skin of the analysis target region by extracting a linear texture image for each of a plurality of predetermined angles by image processing on the skin luminance image of the analysis target region. It is presented that the feature quantity of (linear component) can be acquired. Further, Patent Document 2 presents a technical idea that the directional strength of the obtained linear component indicates the strength of a wrinkle feeling provided by a groove group represented as the linear component.

  The present invention adds a further idea obtained from a new idea to the method presented in Patent Document 2 described above. That is, the present invention provides a technique for scoring the wrinkle state so that the viewpoint of the visual evaluation of the wrinkle by a professional evaluator is reflected based on the skin image.

  In each aspect of the present invention, the following configurations are adopted in order to solve the problems described above.

  The first aspect relates to a method of analyzing wrinkle state. The wrinkle state analysis method according to the first aspect includes one or more predetermined items corresponding to the analysis target region from an image acquisition step of acquiring a skin luminance image of the analysis target region and a skin luminance image acquired in the image acquisition step. A line detection step of extracting one or more linear texture images of an angle; and intensity extraction of extracting linear component intensities of the one or more predetermined angles from the one or more linear texture images extracted in the line detection step And a relational expression between the linear component intensity of the one or more predetermined angles and the visual score of wrinkles on the face image, obtained by regression analysis for a plurality of sample face images, and the intensity extraction step. Calculating the estimated visual score of the wrinkles of the skin of the analysis target site using the extracted linear component strength.

  The second aspect relates to a wrinkle condition analyzer. According to a second aspect of the present invention, there is provided a wrinkle condition analysis apparatus comprising: an image acquisition unit for acquiring a skin luminance image of an analysis target region; and one or more predetermined items corresponding to the analysis target region from the skin luminance image acquired by the image acquisition unit. Line detection means for extracting one or more linear texture images of angles, and intensity extraction for extracting linear component intensities of the one or more predetermined angles from the one or more linear texture images extracted by the line detection means A relational expression between the linear component intensity of the one or more predetermined angles and the visual score of wrinkles on the face image, obtained by regression analysis for a plurality of sample face images, and the intensity extraction means Calculating means for calculating an estimated visual score of wrinkles of the skin of the analysis target portion using the extracted linear component strength.

  Another aspect of the present invention is a program that causes at least one computer to execute the wrinkle state analysis method according to the first aspect, and is a computer readable recording medium having such a program recorded thereon. This recording medium includes non-transitory tangible medium.

  According to each of the above aspects, the wrinkle state can be scored based on the skin image so that the viewpoint of the visual evaluation of the wrinkle by the professional evaluator is reflected.

It is a figure which shows notionally the hardware structural example of the wrinkles condition analysis apparatus in 1st embodiment. It is a flowchart which shows the operation example of the wrinkles condition analysis apparatus in 1st embodiment. It is a figure which shows notionally the process structural example of the wrinkles condition analysis apparatus in 1st embodiment. It is a flowchart which shows the operation example of the wrinkles condition analysis apparatus in 2nd embodiment. It is a figure which shows the 1st output example of presumed visual score. It is a figure which shows the 2nd output example of presumed visual score. It is a figure which shows notionally the process structural example of the wrinkles condition analysis apparatus in 2nd embodiment. It is a flowchart which shows the operation example of the wrinkles condition analysis apparatus in 3rd embodiment. It is a figure which shows the example of the position of an analysis object site | part. It is a figure which shows notionally the process structural example of the wrinkles condition analysis apparatus in 3rd embodiment. It is a graph which shows correlation with the combination of the angle of linear component intensity, and a binarization threshold, and a visual score. It is a graph which shows the relationship between the added angle and the degree-of-freedom adjusted determination coefficient in regression analysis which added one angle to angle "135 degree". It is a graph which shows the relationship between the added angle and the degree-of-freedom adjusted determination coefficient in regression analysis which added one angle to angles "135 degree" and "85 degree." It is a graph showing the relationship between presumed visual score S computed by simple regression formula (1), and visual score obtained by sensory evaluation. It is a graph showing the relationship between presumed visual score S computed by multiple regression formula (2), and visual score obtained by sensory evaluation. It is a figure which shows the skin brightness image of the analysis object site | part of sample provider # 1 and # 2. It is a table | surface which compares the linear component intensity | strength and estimated visual score which are obtained from the skin brightness image of sample provider # 1 and # 2. It is a figure which shows the example which puts in order and outputs the linear texture image of 135 degree and 85 degree about sample provider # 1 and # 2. It is a figure which shows the example of an output of the superposition image of a 135-degree and 85 degree linear texture image about sample provider # 1 and # 2.

  Hereinafter, embodiments of the present invention will be described. In addition, each embodiment listed below is each illustration, and this invention is not limited to the structure of the following each embodiment.

First Embodiment
[Hardware configuration]
FIG. 1: is a figure which shows notionally the hardware structural example of the wrinkles condition analysis apparatus (it is also hereafter described only as an analyzer) in 1st embodiment. The analysis device 10 in the first embodiment is a so-called computer, and includes a CPU (Central Processing Unit) 1, a memory 2, an input / output interface (I / F) 3, a communication unit 4 and the like.

The CPU 1 includes an application specific integrated circuit (ASIC), a DSP (Digital Signal Processor), a GPU (Graphics Processing Unit) and the like in addition to a general CPU.
The memory 2 is a random access memory (RAM), a read only memory (ROM), or an auxiliary storage device (such as a hard disk).

The input / output I / F 3 can be connected to user interface devices such as the output device 5 and the input device 6. The output device 5 is a display device, a projection device (projector), a printing device (printer), a speaker or the like. The display device is a device such as an LCD (Liquid Crystal Display) or a CRT (Cathode Ray Tube) display for displaying a screen corresponding to drawing data processed by the CPU 1 or the like. The input device 6 is a device such as a keyboard, a mouse or the like that receives an input of a user operation, a microphone (microphone), an imaging device (camera, video) or the like. The display device and the input device 6 may be integrated and realized as a touch panel.
The communication unit 4 communicates with other computers, exchanges signals with other devices, and the like. An imaging apparatus (not shown), a portable recording medium, and the like can also be connected to the communication unit 4.

  The analysis device 10 may include hardware elements not shown in FIG. 1, and the number of each hardware element is not limited. For example, the analyzer 10 may have a plurality of CPUs 1 or may be connected to a plurality of output devices 5. The hardware configuration of the analysis device 10 is not limited to the content shown in FIG.

[Operation example / wrinkle state analysis method]
FIG. 2 is a flow chart showing an operation example of the wrinkle state analysis device 10 in the first embodiment. Hereinafter, the wrinkle state analysis method in the first embodiment will be described with reference to FIG. The wrinkle state analysis method in the first embodiment is executed by at least one computer such as the analysis device 10. For example, the wrinkle state analysis method is realized by the CPU 1 executing a program stored in the memory 2.

  The wrinkle state analysis method executed by the analyzer 10 includes an image acquisition step (S21), a line detection step (S22), an intensity extraction step (S23), and a calculation step (S24) as shown in FIG. . Hereinafter, each of these steps will be described in detail.

  In the image acquisition step (S21), the analysis device 10 acquires a skin luminance image of a region to be analyzed. The site to be analyzed is not limited as long as it is a site where wrinkles can occur in a part of human skin. "Wrinkles" may be classified into multiple types depending on the cause of occurrence, such as aging, dryness, and reduction of dermal function. For example, wrinkles called "small wrinkles" are wrinkles caused by the dryness of the epidermis, and are known to be repairable by improvement of the dryness by skin care. In addition, it is known that wrinkles caused by a decrease in dermal function are deeper in ditch than "small wrinkles" and repair is difficult only by improving the dryness of the epidermis. The site to be analyzed may be determined depending on which type of wrinkle condition is to be analyzed among such types. For example, in the case of analyzing the condition of small wrinkles, a predetermined range in which small wrinkles are likely to occur, such as cheeks, eyes, mouth, neck, etc., is selected as an analysis target site. Moreover, when analyzing the condition of the wrinkles which arises by aging, the predetermined range of eye circumference, a forehead, a neck muscle, for example is chosen as an analysis object site | part.

  The skin luminance image is an image in which an analysis target site of skin is captured, and is an image having light and shade information for each pixel. The skin luminance image may be a grayscale image obtained by grayscaleting a color image captured by a general camera. Also, the skin luminance image may be acquired as an image file such as a JPEG (Joint Photographic Experts Group) format, a BMP (Bitmap image) format, a TIFF (Tagged Image File Format) format, or a GIF (Graphic Interchange Format) format. , May be acquired as data in which light and shade information of each pixel is listed. Further, since it is preferable that the pixel value has a linear relationship with the luminance, it is preferable that γ correction is not performed in the skin luminance image used here. When γ correction is applied to an image captured by a camera, it is preferable to convert pixel values into a linear relationship with luminance by inverse γ correction. The present embodiment does not limit the data format of the skin luminance image. The analysis device 10 can also acquire the skin luminance image from a portable recording medium, another device, or the like via the communication unit 4.

  In the line detection step (S22), the analysis apparatus 10 extracts one or more linear texture images at one or more predetermined angles corresponding to the region to be analyzed from the skin luminance image acquired in the image acquisition step (S21). Do. The linear texture image for one predetermined angle is an image representing only linear components extending in the direction of the predetermined angle in the skin luminance image. Here, the linear component represented by the linear texture image may, strictly speaking, include not only a component present in a predetermined angular direction but also a component present in a range from a predetermined angle to an allowable angle. The range of allowable angles depends on the linear texture image extraction method.

  The linear component represented by the linear texture image is a linear pattern reflected in the skin luminance image, and almost corresponds to a linear groove (dent) formed on the skin surface of the analysis target site. Therefore, according to the line detection step (S22), various linear components that appear on the skin of the analysis target site, including grooves that are recognized as wrinkles and grooves that are difficult to be recognized as wrinkles (such as shallow skin grooves) It can be extracted as a linear texture image.

  As described in detail in the section of the Examples, the present inventors target the plurality of sample face images and relate the result of the visual evaluation of the condition of the wrinkles by the expert evaluator to the linear component strength at each angle. Was regressed. The result of the visual evaluation of the condition of wrinkles by this expert evaluator was numerically expressed as a visual score. That is, the visual score is a value obtained by digitizing the condition of wrinkles. For example, the visual score is determined to a value indicating the level of the degree of wrinkles to be visually recognized (not at all = 1, slightly at = 2, at = 3 and very at = 4). The condition of wrinkles represented by a visual score is not limited to such an example, and may vary depending on the criteria of visual evaluation. Specifically, focusing on one type of wrinkles among the plurality of types described above, the condition of the wrinkles may be represented by a visual score. For example, the state of "wrinkles" (herein referred to as "dermal wrinkles") caused by the deterioration of the dermis state may be represented by a visual score. In this case, the expert evaluator distinguishes "dermis Ziwa" and other types of wrinkles such as "small Ziwa" as much as possible, and the condition (number, length, depth, etc.) of "dermis Ziwa" Determine the level as a visual score.

  The present inventors perform regression analysis on the relationship between the visual score and the linear component intensity at each angle with respect to a plurality of sample face images to obtain visual correlation with the visual score for a certain analysis target site. The angle of the high linear component was found. Furthermore, the present inventors have found that the visual score of the wrinkles at the analysis target site can be sufficiently explained by using the linear component intensity at a high angle of correlation with the visual score in a limited manner. Thereby, in the present embodiment, a limited number of predetermined angles that can sufficiently explain the visual score of the wrinkles of the analysis target site are determined in advance corresponding to the analysis target site, and are stored in the memory 2. For example, the analyzer 10 extracts one or two linear texture images for one or two predetermined angles. As a result, the processing time can be shortened while maintaining the accuracy of scoring of the wrinkle state, as compared to the method of extracting the linear texture image at a large number of predetermined angles.

  However, the number of predetermined angles to be extracted in the line detection step (S22) may be set to three or more. For example, angles obtained by dividing the range of 0 degrees to 360 degrees by equal angle intervals (for example, 10 degrees) or a large number of angles in the descending order of correlation with the visual score may be used as the predetermined angles. The analyzer 10 can also input the one or more predetermined angles by the user using the input device 6, and acquire the one or more predetermined angles as the input data.

  Various well-known methods can be used for the extraction method of a linear texture image. For example, edge detection operators such as Prewitt operator, Sobel operator, etc., line detection operators such as Vander Brug operator, Paton operator, Kasvand operator etc, Wavelet, Steerable, Gabor filter, etc. can be used as the extraction method. The present embodiment does not limit the specific extraction method of the linear texture image. An embodiment using a Gabor filter will be described later as this extraction method.

  In the intensity extraction step (S23), the analyzer 10 extracts linear component intensities at one or more predetermined angles from the one or more linear texture images extracted in the line detection step (S22). The linear component strength at one predetermined angle indicates the feature amount (linear component amount) of the linear component extending in the direction of the predetermined angle. Various well-known texture analysis methods can be used for the linear component strength extraction method. In the present embodiment, the extraction method of the linear component strength is not limited as long as the feature quantity of the linear component extending in the direction of each predetermined angle can be obtained.

  For example, the analysis device 10 can calculate the variance value or the standard deviation value from the density histogram of the linear texture image, and can use the variance value or the standard deviation value as the linear component strength. A linear texture image showing a large dispersion value is an image with high contrast of light and dark, and it is considered that a strong convex component (bright component) and a strong concave component (dark component) are mixed in an image with high contrast of light and dark Be This mixed state can be said to be a state in which the linear component amount of the image is large. On the other hand, it can be considered that the mixed state in the linear texture image is a state in which a large number of distinct uneven shapes exist on the skin surface. Therefore, it can be said that the dispersion value obtained from the density histogram of the linear texture image indicates the feature amount of the linear groove formed in the skin surface and extending in the predetermined angular direction, that is, the linear component strength.

  Besides the concentration histogram method (GLHM), a concentration level difference method (GLDM), a spatial concentration level dependence method (SGLDM), or the like may be used as the extraction method. In addition, the analysis device 10 binarizes the linear texture image using a predetermined binarization threshold, and calculates the area of one value in the acquired binarized image as the linear component intensity. You may In this case, in the line detection step (S22), the analyzer 10 may execute up to the binarization process, and the binarized image after the binarization process may also be referred to as a linear texture image. The area of one value corresponds, for example, to the number of white or black pixels. In addition, the analysis device 10 may calculate the ratio of the area of one value to the area of the other value, or the ratio of the area of one value to the total area as the linear component intensity. The predetermined binarization threshold is set in advance by the imaging magnification of the analysis target site shown in the skin luminance image, the imaging environment (brightness etc.) of the analysis target site, and the like, and is stored in the memory 2. In the present embodiment, it is desirable that the predetermined binarization threshold be set to a value that can extract linear component strength that has a high correlation with the visual score described above. The specific method of determining the desired binarization threshold will be described in detail in the embodiment section.

  In the calculation step (S24), the analysis device 10 compares the linear component intensity of the one or more predetermined angles and the visual score of the wrinkles on the face image, which is obtained by regression analysis on a plurality of sample face images. The estimated visual score of the wrinkle of the skin of the analysis target part is calculated using the relational expression and the linear component strength extracted in the strength extraction step (S23). The predetermined angle corresponding to the linear component strength that forms the relational expression is the same as one or more predetermined angles corresponding to the analysis target site, which are targets in the line detection step (S22). In the present embodiment, a simple regression equation in which the linear component intensity of the first predetermined angle having the highest correlation with the visual score described above is used as an explanatory variable and the visual score is an objective variable according to the above-described regression analysis, or the first A multiple regression equation in which linear component intensities at two predetermined angles including a predetermined angle are used as explanatory variables and a visual score is used as an objective variable is generated and held in advance, and is used as the above-mentioned relational expression. A specific example of the relational expression will be described later as an example.

  The analyzer 10 calculates the estimated visual score by substituting the linear component intensities extracted in the intensity extracting step (S23) into the relational expression generated and held in advance. The estimated visual score to be calculated is a wrinkle state that is estimated to be obtained as an evaluation result when the expert evaluator visually evaluates the wrinkle state of the analysis target portion shown in the skin luminance image acquired in (S21). Means a score of. As a result, the analysis device 10 can calculate a score that approximates the result of the actual visual evaluation, without actually causing the expert evaluator to visually evaluate the condition of the subject's analysis target wrinkles.

  The analysis device 10 stores the calculated estimated visual score in the memory 2. For example, the analysis device 10 acquires identification information of the subject, associates the identification information, and stores the calculated estimated visual score. In addition, the analysis device 10 may store the estimated visual score on the portable recording medium via the communication unit 4 or may provide it to another computer.

[Processing configuration]
FIG. 3: is a figure which shows notionally the process structural example of the wrinkles condition analysis apparatus 10 in 1st embodiment. The analysis device 10 in the first embodiment includes an image acquisition unit 11, a line detection unit 12, an intensity extraction unit 13, a calculation unit 14, and the like. Each of these processing modules is realized, for example, by executing a program stored in the memory 2 by the CPU 1. Also, the program may be installed from, for example, a portable recording medium such as a CD (Compact Disc) or a memory card, or from another computer on a network via the input / output I / F 3 and stored in the memory 2 Good.

  The analyzer 10 can execute the above-described wrinkle state analysis method by operating each processing module illustrated in FIG. 3. That is, the analyzer 10 operates as shown in FIG. In this case, the image acquisition unit 11 executes the above-described image acquisition step (S21), the line detection unit 12 executes the above-described line detection step (S22), and the intensity extraction unit 13 performs the above-described intensity extraction step. The calculation unit 14 executes (S23), and executes the above-described calculation step (S24).

  The analysis device 10 may hold in advance the skin luminance image of the region to be analyzed in the analysis device 10 itself, or may generate it in the analysis device 10 itself, or from another computer, a portable recording medium, etc. You may acquire via input-output I / F3.

[Operation and Effect in First Embodiment]
As described above, in the first embodiment, one or more linear texture images at one or more predetermined angles corresponding to the analysis target site are extracted from the skin luminance image of the analysis target site, and one or more linear shapes are extracted. From the texture image, linear component intensities at one or more predetermined angles are extracted. On the other hand, a relational expression between linear component intensities at one or more predetermined angles and a visual score indicating the result of visual evaluation of wrinkles by a professional evaluator is defined in advance by regression analysis for a plurality of sample face images. There is. Then, by applying the linear component intensities at one or more predetermined angles calculated as described above to the relational expression, an estimated visual score of wrinkles of the skin of the analysis target portion is calculated.

  Thereby, according to the first embodiment, regarding the wrinkle state of the skin of the analysis target site, the visual evaluation of the actual visual evaluation is performed based on the skin luminance image of the analysis target site without actually making the professional evaluator visually evaluate it. A score can be obtained that approximates the result. As a result, it is possible to reduce the time and burden of the expert evaluator and to reduce the cost of analyzing the wrinkle state. Moreover, according to the present embodiment, it is possible to stably and quantitatively evaluate the visual impression of the wrinkle state.

  Furthermore, according to the first embodiment, by using the angle of the linear component strength that is highly correlated with the visual score, the linear component strength of a small number of angles can be used as a result of actual visual evaluation by a professional evaluator. An approximate estimated visual score can be calculated. Thereby, according to the first embodiment, the calculation speed of the estimated visual score can be improved while maintaining the accuracy as compared with the method of calculating the linear texture image and the linear component intensity with respect to a large number of predetermined angles. it can.

  Furthermore, according to the first embodiment, the state of wrinkles represented by the estimated visual score to be calculated can be limited to the state of certain types of wrinkles such as "small wrinkles" and "dermal wrinkles". In this case, the visual evaluation by the expert evaluator is performed focusing on the condition of the target type of wrinkles, and the visual score obtained as the evaluation result is used for regression analysis. This makes it possible to calculate an estimated visual score that represents the state of the desired type of wrinkles.

Second Embodiment
The second embodiment effectively outputs the result of the wrinkle state analysis in the first embodiment. Hereinafter, the analysis device 10 and the wrinkle state analysis method in the second embodiment will be described focusing on contents different from the first embodiment. Hereinafter, the description of the same content as that of the first embodiment is appropriately omitted. The hardware configuration of the analyzer 10 in the second embodiment is the same as that of the first embodiment shown in FIG.

[Operation example (wrinkle state analysis method)]
Hereinafter, the wrinkle state analysis method according to the second embodiment will be described with reference to FIG. FIG. 4 is a flow chart showing an operation example of the analysis device 10 in the second embodiment. In FIG. 4, the same steps as those in FIG. 2 are denoted by the same reference numerals.

  The wrinkle state analysis method in the second embodiment executed by the analysis apparatus 10 further includes the step (S41) of acquiring age information and the output step (S42) in addition to the method of the first embodiment shown in FIG. Including. Hereinafter, each process is explained in full detail focusing on the process of contents different from the first embodiment.

  In the step (S41), the analysis apparatus 10 acquires age information of the subject appearing in the skin luminance image acquired in the step (S21). The age information to be acquired may indicate a specific age, or may indicate an age such as 30's or 40's, or an age range such as 30 to 35 and 35 to 40. May be indicated. The method of acquiring age information by the analysis device 10 is not limited. For example, the analysis device 10 displays a screen for causing the subject or another user to input the age information on the display device of the output device 5, and acquires the age information by an input operation using the input device 6 on the screen. be able to. In addition, the analysis device 10 may acquire age information by recognizing a voice obtained from a microphone. The analysis apparatus 10 can also estimate the age from a face image obtained by imaging the face of the subject and acquire the estimated age as age information. The step (S41) may be performed in any order before the execution of the step (S42).

  In step (S42), the analyzer 10 outputs the estimated visual score calculated in step (S24). In the present embodiment, the analysis device 10 identifies a representative visual score corresponding to the age information acquired in the step (S41), and determines the identified representative visual score and the estimated visual score calculated in the step (S24). Output side by side. In this case, the analyzer 10 holds in advance a representative visual score for each age, each age, or each age range. The analysis device 10 can specify a representative visual score corresponding to the age, the year, or the age range indicated by the acquired age information from among the plurality of representative visual scores to be held. The representative visual score indicates a standard (typical) wrinkle condition of the skin of a person of that age, age, or age range. For example, the representative visual score is set to the average value of the visual score or the estimated visual score obtained for the skin of the person in the age, age, or age range.

  Further, the analysis device 10 specifies a representative linear texture image corresponding to the age information acquired in the step (S41), and the representative linear texture image and the linear texture image extracted in the step (S22) Alternatively, it may be arranged and output at predetermined angles corresponding to the analysis target site. In this case, the analysis device 10 holds in advance representative linear texture images for each of one or more predetermined angles for each age, each age, or each age range. The analysis device 10 can specify a representative linear texture image corresponding to the age, the year, or the age range indicated by the acquired age information from among the plurality of representative linear texture images to be held. The representative linear texture image is, for example, a visual score or estimation close to the representative visual score among those extracted in advance from the skin luminance image of the analysis target part of a person in the corresponding age range by the same method as step (S22) It is possible to use a linear texture image of the person who scored visually.

  FIG. 5 is a diagram showing a first output example of the estimated visual score. In the example of FIG. 5, the analysis device 10 includes an image RN including the analysis target region of the subject, a linear texture image YT of a predetermined angle PA extracted from the skin luminance image of the analysis target region of the subject, and The representative linear texture images AT of the angle PA are arranged and displayed on the display device. Furthermore, the analysis device 10 displays the calculated estimated visual score “your wrinkle index: 4” and the average visual score of the same age as the subject “average wrinkle index: 3 of the same age” on the display. The subject who sees this output can grasp the wrinkle state of his / her skin with a specific numerical value (estimated visual score) and can easily compare with the average of the subject and the same age. In addition, the subject can recognize the distribution, the amount, etc. of the linear texture extending in the direction of the predetermined angle PA by looking at his / her linear texture image, and compare with the linear texture of the same age. Can. As shown in the example of FIG. 5, the analyzer 10 further compares the result of comparison between the estimated visual score and the representative visual score with a text (text: "Your skin has more wrinkles compared to the average of the same age," etc. It can also be displayed in).

  In the example of FIG. 5, the linear texture images are output side by side only for the predetermined angle PA, but the analysis device 10 outputs the linear texture image of the same age as the subject's linear texture image for each of a plurality of predetermined angles. Can be displayed side by side. In this way, the state of the linear texture in each angular direction can be confirmed.

  FIG. 6 is a diagram illustrating a second output example of the estimated visual score. As shown in FIG. 6, the analyzer 10 can also display an image obtained by superimposing the plurality of linear texture images extracted in the step (S22) on the display. In the example of FIG. 6, an image ST in which a linear texture image of a predetermined angle PA1 and a linear texture image of a predetermined angle PA2 are superimposed is displayed. The displayed image ST represents a superposition of linear textures extending in the directions of angles PA1 and PA2 that are highly correlated with the visual score of the wrinkle state, and excludes linear textures extending in other angular directions. It can be said that the image emphasizes the appearance features of the wrinkled state. Therefore, the subject who sees the displayed superimposed image can easily grasp the appearance of his / her wrinkle state. Further, the analyzer 10 can output not only a plurality of linear texture images but also an image in which linear components are represented in different colors for each linear texture image. In this way, the state of the linear texture in each angular direction can be more easily grasped.

  The linear texture image and the representative linear texture image output in the step (S42) may be images extracted by any extraction method from the skin luminance image in the line detection step (S22), It may be an image obtained by further processing by binarization processing or the like. When outputting a superimposed image of linear texture images at a plurality of angles, the images after extraction may be superimposed, or the image after extraction and the image after processing may be superimposed. In other words, the method of extracting the superimposed linear texture image may be different. For example, a linear texture image at another angle obtained by performing a binarization process after applying the Gabor filter is superimposed on the linear texture image at a certain angle obtained by applying the Gabor filter. May be output.

  The above-mentioned output by the analysis device 10 may be display on a display device or printing on a printing device. In addition, the analysis device 10 can also output, from the speaker, a voice for reading out the estimated visual score or the representative visual score of the subject. The method of output by the analyzer 10 is not limited.

[Processing configuration]
FIG. 7: is a figure which shows notionally the process structural example of the wrinkles condition analysis apparatus 10 in 2nd embodiment. The analyzer 10 according to the second embodiment further includes an information acquisition unit 16 and an output processing unit 17 in addition to the processing configuration of the first embodiment. The respective processing modules are also realized, for example, by executing a program stored in the memory 2 by the CPU 1.

  The analyzer 10 can execute the above-described wrinkle state analysis method by operating each processing module illustrated in FIG. 7. That is, the analyzer 10 operates as shown in FIG. In this case, the information acquisition unit 16 executes a step (S41) of acquiring age information, and the output processing unit 17 executes the above-mentioned output step (S42).

[Operation and Effect in Second Embodiment]
In the second embodiment, the representative visual score corresponding to the subject's age information and the estimated visual score calculated for the subject are output side by side. This allows the subject to grasp the wrinkle condition of his / her skin with a specific numerical value (estimated visual score), and to position the subject's wrinkle condition relative to the standard wrinkle condition of the same age. It can be easily grasped.

  In the second embodiment, a representative linear texture image corresponding to the subject's age information and a linear texture image extracted from the subject's skin luminance image are arranged and output at predetermined angles corresponding to the analysis target region. Be done. As a result, the subject can recognize the wrinkle state (linear component state) of his own skin in each predetermined angular direction in the image, and can also compare it with the standard wrinkle state of the same age.

  In the second embodiment, an image in which a plurality of linear texture images representing linear textures of a plurality of predetermined angles are superimposed is output. Since each linear texture image represents a linear component of an angle that exhibits high correlation with the visual score of the wrinkle state, this superimposed image emphasizes the linear component that strongly affects the appearance of the wrinkle state. Therefore, the output of the superimposed image allows the subject to easily grasp the impression of the appearance of the wrinkle state of the subject. Further, by representing the linear components in different colors for each linear texture image in the superimposed image, the state of the linear texture in each angular direction can be further easily grasped.

  As described above, according to the second embodiment, since the subject's wrinkle state can be effectively output, it is possible to perform the counseling on the wrinkle state or the counseling on the skin care product or the cosmetic for improving the wrinkle state. Two embodiments can be utilized.

Third Embodiment
Hereinafter, the analysis device 10 and the wrinkle state analysis method in the third embodiment will be described focusing on contents different from the above-described embodiments. In the third embodiment, a specific method of acquiring a skin luminance image that can increase the analysis accuracy of the wrinkle state is newly added. Hereinafter, the description of the same content as the first and second embodiments is appropriately omitted. The hardware configuration of the analysis device 10 in the third embodiment is the same as the first embodiment shown in FIG.

[Operation example (wrinkle state analysis method)]
Hereinafter, the wrinkle state analysis method according to the third embodiment will be described with reference to FIG. FIG. 8 is a flowchart showing an operation example of the analysis device 10 in the third embodiment. In FIG. 8, the same steps as in FIG. 2 are denoted by the same reference numerals.
The wrinkle state analysis method in the third embodiment executed by the analyzer 10 further includes an image processing step (S81) and a normalization step (S82) in addition to the steps of the first embodiment or the second embodiment. However, FIG. 8 shows a wrinkle state analysis method in which the steps (S81) and (S82) unique to the third embodiment are added to the steps of the first embodiment. Hereinafter, each process is explained in full detail focusing on the process of contents different from the first embodiment.

  In the image processing step (S81), the analyzer 10 projects a S-polarized light on the skin of the subject and captures a surface reflected light image from each polarized image obtained by imaging the S-polarized light and the P-polarized light. Specifically, the analysis apparatus 10 projects a S-polarized light and captures an S-polarized light (S-S polarized image) and a S-polarized projected image and a P-polarized captured light image ( Take the difference with the SP polarization image). The S-S polarization image is an image in which the surface reflection light component of the skin of the subject is strong and the internal reflection light component is small, and the SP polarization image is an image in which the internal reflection light component of the skin of the subject is strong. Therefore, by obtaining the difference between the SS polarized light image and the SP polarized light image, it is possible to acquire a surface reflected light image from which components other than the surface reflected light component (internally reflected light) have been removed. Here, the direction of the s-polarization can be set arbitrarily. On the other hand, the direction of P polarization needs to be orthogonal to the direction of S polarization. For example, S-polarization can be set in the vertical direction, and P-polarization can be set in the left-right direction. Similarly to the skin luminance image in the first embodiment, it is preferable that the pixel values have a linear relationship with the luminance as in the case of the skin luminance image in the first embodiment, so that γ correction is preferably not performed. The analyzer 10 can acquire each polarization image from an imaging device, a portable recording medium, another device, etc. via the input / output I / F 3.

  Furthermore, the analyzer 10 further uses a PS polarization image obtained by projecting P polarization and imaging S polarization and a PP polarization image obtained by projecting P polarization and imaging P polarization. The surface reflected light image may be acquired. Thereby, it is possible to acquire a surface reflected light image in which all polarization components are correctly considered. However, in the case of using a PS polarization image and a PP polarization image, there are problems that the imaging time becomes long, the subject is easily shifted between the images, and more imaging facilities are required. is there. Therefore, according to such a problem and the effect of suppressing noise, it is desirable to use only the combination of the SS polarization image and the SP polarization image as described above.

  In the normalization step (S82), the analysis apparatus 10 extracts a normalized skin image of a region to be analyzed from the surface reflected light image obtained in (S81). Specifically, the analysis device 10 detects the analysis target site from the surface reflection light image, and based on the detected image area of the analysis target site, a normalized image of the analysis target site (skin image) Extract In the case where the resolution, size, and orientation of the analysis target portion in the respective polarization images acquired in (S81) are irregular, adjustment of the resolution and size of the image and the orientation of the analysis target portion appearing in the image are performed as normalization processing. Adjustments may be made.

FIG. 9 is a diagram showing an example of the position of the analysis target site. In the example of FIG. 9, an area surrounded by white lines, that is, a square area at the lower orbit is detected as an analysis target site.
There is no limitation on the method of detecting the analysis target site. For example, the analyzer 10 can automatically detect the eye and nose area in the surface reflected light image, and can automatically detect the analysis target site from the relative positional relationship between the eye and nose area. As another example, the user may operate the input device 6 to specify the area of the analysis target region in the surface reflected light image, and cause the analysis apparatus 10 to generate an image corresponding to the area. . In addition, a region fixed in advance in the surface reflected light image may be taken as an analysis target site.

  In the image acquisition step (S21), the analysis device 10 acquires the skin luminance image by deleting color information from the skin image obtained in (S82). As a method of deleting color information, an average value or a weighted average value of RGB values, or a method using only one of RGB values as a representative value of each pixel can be taken. Similar to the method of the first embodiment, (S22) and subsequent steps are executed based on this skin luminance image.

[Processing configuration]
FIG. 10: is a figure which shows notionally the process structural example of the analyzer 10 in 3rd embodiment. The analyzer 10 in the third embodiment further includes an image processing unit 18 and a standardization unit 19 in addition to the processing configuration in the first embodiment or the second embodiment. However, FIG. 10 shows a processing configuration in which the image processing unit 18 and the standardization unit 19 unique to the third embodiment are added to the processing configuration of the first embodiment. The image processing unit 18 and the standardization unit 19 are also realized by executing a program stored in the memory 2 by the CPU 1 as in the case of other processing modules.

  The analyzer 10 can execute the above-mentioned wrinkle state analysis method by operating each processing module shown in FIG. That is, the analyzer 10 operates as shown in FIG. In this case, the image processing unit 18 executes the above-mentioned image processing step (S81), and the normalization unit 19 executes the above-mentioned normalization step (S82). The other processing modules are the same as in the first embodiment.

  The analyzer 10 can acquire each polarization image from another computer, a portable recording medium, or the like via the input / output I / F 3. The analyzer 10 may further include an imaging device (not shown in FIG. 1) connected to the input / output I / F 3. In this case, the analyzer 10 can also acquire each polarized image from the imaging device.

  In the third embodiment described above, the normalization step (S82) and the normalization unit 19 are provided, but the polarization image is generated in a standardized state, and only the analysis target portion is copied in the polarization image. If it is, the standardization process (S82) and the standardization unit 19 can be omitted.

[Operation and Effect in Third Embodiment]
In the third embodiment, a surface reflection light image is acquired from a polarization image, and a normalized skin image of a region to be analyzed is acquired from the surface reflection light image. Then, the color information is deleted from the skin image to acquire the skin luminance image of the analysis target site, and based on the acquired skin luminance image, the estimated visual score is calculated as in the first embodiment. Be done.

  The surface reflected light image represents a component (concave / convex component) derived from the shape of the skin surface excluding color unevenness components such as bears, stains, buckwheat etc. Therefore, according to the third embodiment, the linear texture image extracted from the skin luminance image is further prevented from including linear components (noise components) derived from other than the shape of the skin surface of the analysis target portion. Can. As a result, the linear component intensity at each predetermined angle can be extracted in a state where noise components other than the shape (mainly grooves) of the skin surface are excluded, so that the wrinkle state can be analyzed with higher accuracy. .

  Examples are given below, and the above-described embodiments will be described more specifically. The embodiments described above are not limited at all by the following examples.

  The present inventors conducted sensory evaluation on a plurality of sample face images, and obtained a visual score of the wrinkle state for each subject's skin appearing in each sample face image. In the sensory evaluation, three expert evaluators evaluated the condition of wrinkles on the skin of each sample provider by looking at 210 sample face images (photographs) in which all the faces of 210 sample providers were captured. . In the present embodiment, the portion of the cheek (lower orbit) as the analysis target portion in the entire face represented by the sample face image is focused on, and the "small wrinkles" depending on the dry state of the epidermis are mainly The condition of the wrinkles was evaluated. Moreover, in this sensory evaluation, in order to unify the evaluation criteria of each professional evaluator, all face images of four persons representing four stages of the state of "small wrinkles" were provided as comparison targets. The visual score for all face images with very few wrinkles was 1 point, the visual score for all face images with very wrinkles was 4 points, and the visual scores for all the two face images between them were set to 2 points and 3 points . Each expert evaluator compares the four full face images with each sample face image, and for each sample face image, one point, 1.5 points, two points, 2.5 points, three points One of the 3.5 points and 4 points was allocated. As a result, a score for three persons is given to each sample face image, and the average of the scores for three persons is determined as the visual score of each sample face image.

  The present inventors perform regression analysis on 210 skin luminance images including the analysis target sites of the 210 sample providers described above to obtain linear component intensities at one predetermined angle, or two or more of them. It was examined whether the visual score could be estimated with high accuracy by linear combination of linear component intensities at a predetermined angle. In this examination, a site focused on sensory evaluation (lower left eye socket, see FIG. 9) is a site to be analyzed, and a skin luminance image of this site to be analyzed (size = 550 × 550 pixels, resolution on the site of interest = 18) Pixels / mm were respectively extracted ((S81), (S82) and (S21) in FIG. 8), and linear texture images of a predetermined angle were respectively extracted from the plurality of extracted skin luminance images (FIG. 8) (S22)). Furthermore, the extracted linear texture image was binarized with a predetermined binarization threshold, and the number of white pixels in the obtained binarized image was calculated as the linear component intensity (see FIG. S23).

A Gabor filter corresponding to a predetermined angle θ was used to extract the linear texture image. In general, the Gabor filter is expressed by the following equation. For the other parameters λ, φ, σ, and γ that determine the shape of the Gabor filter, appropriate values are set according to the shooting environment of the sample face image (λ = 10, φ = 0, σ = 4, γ = 1). The details of the Gabor filter are known as described in Patent Document 2.

  Then, the present inventors change the combination of the binarization threshold for obtaining the linear component strength and the target angle θ, and change the correlation coefficient between the linear component strength of the angle θ and the visual score. The combinations of angles and threshold values which can be calculated sequentially and can obtain linear component intensities highly correlated with the visual score were searched. In the present embodiment, Gabor filters corresponding to 36 predetermined angles from 0 degrees to 175 degrees set at an angle width of 5 degrees were sequentially used. Note that this angle notation is a notation in the case where the vertical reverse direction is 0 degree, the vertical direction is 180 degrees, and the angle increases clockwise toward the face.

  FIG. 11 is a graph showing the correlation between the visual score and the combination of the linear component intensity angle and the binarization threshold. In FIG. 11, the horizontal axis indicates the angle, the vertical axis indicates the correlation coefficient, and the binarization threshold is distinguished by the line type. From the result of FIG. 11, the combination of the binarization threshold value "95" and the angle "135 degrees" at which the absolute value of the correlation coefficient is maximum is detected. A linear component strength can be obtained which exhibits an absolute value of about 0.7). In the present embodiment, the combination of the binarization threshold and the angle at which the absolute value of the correlation coefficient is maximum is thus detected, but a combination in which the absolute value of the correlation coefficient indicates the periphery of the maximum value is used. It is also good. For example, the binarization threshold may be set in the range of 63 or more and 127 or less, and the angle may be set in the range of 130 degrees or more and 140 degrees or less. In addition, although the optimum value of the binarization threshold in the present embodiment is 95, when the shooting conditions such as the brightness of the illumination, the shutter speed, and the aperture change, the brightness of the linear texture image also changes. Since the optimal value of the digitization threshold also changes, the binarization threshold changes in accordance with the imaging conditions. The reason why the correlation coefficient is negative in FIG. 11 is that the linear component intensity is represented by the number of white pixels, that is, the size of the portion other than the groove. Further, as described above, since the angle in steps of 5 degrees is used, in FIG. 11, data for the step size is linearly interpolated.

  Thereby, it was verified that the visual score can be estimated with high accuracy by the linear component intensity of one angle "135 degrees" in the environment of the present embodiment. Furthermore, the present inventors examined whether it is possible to estimate the visual score with higher accuracy by further adding the linear component strength at other angles.

  FIG. 12 is a graph showing the relationship between the added angle and the degree of freedom adjusted determination coefficient in the regression analysis in which one more angle is added to the angle “135 degrees”. According to FIG. 12, the degree of freedom adjusted determination coefficient is maximized at the angle "85 degrees". Moreover, the degree of freedom adjusted determination coefficient increased by adding the linear component intensity of the angle “85 degrees” compared with the case where only the linear component intensity of the angle “135 degrees” is used (from 0.4502 to 0) To .4607). Thereby, it was confirmed that the estimation accuracy of the visual score is improved by adding the linear component intensity of the angle "85 degrees" to the linear component intensity of the angle "135 degrees".

  FIG. 13 is a graph showing the relationship between the added angle and the degree of freedom adjusted determination coefficient in regression analysis in which one angle is further added to the angles “135 degrees” and “85 degrees”. According to FIG. 13, both degrees of freedom adjusted determination coefficients are lower than in the case of using linear component intensities of angles “135 degrees” and “85 degrees” (0.4607). Thereby, it was confirmed that the visual score can be estimated with sufficient accuracy without using the linear component intensity of an angle larger than that by using the linear component intensities of the angles “135 degrees” and “85 degrees”. .

From the above, a simple regression equation (1) in which the linear component intensity at the angle "135 degrees" is an explanatory variable and the visual score is an objective variable, and the two linear component intensities at the angles "135 degree" and "85 degrees" The multiple regression equation (2) was obtained with the explanatory variable and the visual score as the objective variable.
S = -0.00002543 x ₁₃₅ + 8.652 (1)
S = -0.00003068 X ₁₃₅ + 0.000009301 X ₈₅ + 7.484 (2)

FIG. 14 is a graph showing the relationship between the estimated visual score S calculated by the simple regression equation (1) and the visual score obtained by sensory evaluation. FIG. 15 is a graph showing the relationship between the estimated visual score S calculated by the multiple regression equation (2) and the visual score obtained by sensory evaluation. In FIG. 14 and FIG. 15, the horizontal axis indicates the estimated visual score S, and the vertical axis indicates the visual score. According to FIGS. 14 and 15, it was confirmed that there is a correlation between the estimated visual score obtained from the regression equation and the visual score obtained from the sensory evaluation. Moreover, it was confirmed by the determination coefficient (R ² ) shown in FIG. 14 and FIG. 15 that a visual score with higher accuracy is estimated from the multiple regression equation (2) than for the single regression equation (1).

  In Example 1 described above, the number of white pixels in the binarized image is used as the linear component intensity. An example in which the ratio of the number of black pixels to the total number of pixels is used as the linear component intensity will be described below as a second embodiment. However, the linear component intensity of the present invention may be the number of black pixels or the ratio of the number of white pixels to the total number of pixels.

The following regression equations (3) and (4) were obtained in Example 2 by using the same method and environment as Example 1 except for the calculation method of linear component strength. And according to each regression (3) and (4), it was confirmed that a visual score can be estimated by the precision substantially the same as Example 1.
S = 7.693 · X ₁₃₅ +0.959 (3)
_{S = 9.281 · X 135 -2.814 ·} X 85 +1.017 (4)

In Example 2, the legitimacy of the wrinkle state analysis method in each of the above-described embodiments is further applied to the analysis target sites of two sample providers # 1 and # 2 who receive the same visual score in sensory evaluation. It was verified. In this verification, regression equations (3) and (4) were used.
FIG. 16 is a view showing a skin luminance image of the analysis target site of sample providers # 1 and # 2. Although there are more irregularities on the skin surface at the analysis target site of sample provider # 2, compared to sample provider # 1, according to the sensory evaluation by a professional evaluator, the state of "small wrinkles" is Both gave the same visual score.

  FIG. 17 is a table comparing linear component intensities and estimated visual scores obtained from skin luminance images of sample providers # 1 and # 2. As shown in FIG. 17, the difference between the estimated visual score calculated from two images of the same visual score (2.5) and the actual visual score (2.5) is when using only 135 degrees ( It becomes smaller when using two angles of 135 degrees and 85 degrees (-0.04) compared to -0.18), and according to the wrinkle state analysis method in each embodiment described above, sensory evaluation It was verified that an estimated visual score similar to the visual score could be obtained.

  FIG. 18 is a diagram showing an example in which 135 degree and 85 degree linear texture images for sample providers # 1 and # 2 are arranged and output. In FIG. 18, the binarized image is output as a linear texture image. From the output of FIG. 18, it is observed that sample provider # 2 has higher linear component intensity at both angles than sample provider # 1. On the other hand, both the visual score and the estimated visual score are the same or approximate. That is, it is estimated that the information close to the visually recognized wrinkle state is extracted by canceling the other linear component of 85 degrees, the linear component of 135 degrees having high correlation with the visual score. This is linked to the fact that in the multiple regression equations (2) and (4), the sign of the coefficient of 85 degrees is inverted with the coefficient of 135 degrees.

  FIG. 19 is a diagram showing an output example of superimposed images of the 135 degree and 85 degree linear texture images for sample providers # 1 and # 2. The upper two images are 135 degree linear texture images extracted from the skin intensity image by Gabor filter application. The lower two images are 85-degree linear texture images (Gabor filter and binarization processing) obtained from the 135-degree linear texture image extracted from the skin luminance image by Gabor filter application ( Is an image in which a binarized image is superimposed.

  In each of the above-mentioned examples, the portion of the cheek (lower orbit) as a site to be analyzed was used, and the visual score mainly reflected the state of "small wrinkles" depending on the dry state of the epidermis. Therefore, it can be said that the estimated visual score obtained in each of the above-described embodiments is an index value indicating the visual impression of the state of "small wrinkles". As described above, “Wrinkle” may be classified into multiple types depending on the cause of occurrence, such as aging, dryness, reduction of dermal function, etc. Therefore, in the sensory evaluation of a professional evaluator, other types of wrinkles It is also possible to calculate the estimated visual score which shows the impression of the appearance of the state of the type of wrinkles other than "small wrinkles" by evaluating in the center. For example, if a visual score mainly reflecting the state of "dermal wrinkles" caused by a decrease in dermal function is obtained by sensory evaluation, calculation of an estimated visual score indicating an impression of the appearance of the state of "dermal wrinkles" is also possible It is possible.

  In this way, different regression equations are prepared in advance for each type of wrinkle, and the estimated visual score representing the wrinkle condition of each type is calculated by switching the regression equation according to the type of wrinkle to be analyzed. It is also possible to take For example, when counseling skin care products that repair the dryness of the epidermis, an estimated visual score indicating the impression of appearance of "small wrinkles" is calculated, and when counseling skin care products that improve the condition of the dermis, "estimated visual resistance of" dermal wrinkles " It is conceivable to calculate the score.

  In each of the above-mentioned examples, the left cheek (lower orbit) was taken as the analysis target site. This is because "small wrinkles" depending on the dry state of the epidermis are the main analysis targets, and the lower part of the orbit is apt to dry easily and a difference is likely to occur between people. Therefore, the right cheek (lower orbit) may be the analysis target site. In this case, for example, 225 degrees is used instead of 135 degrees, and 275 degrees is used instead of 85 degrees. Similarly to the above, this angle notation is a notation represented so that the vertical reverse direction is 0 degree, the vertical direction is 180 degrees, and increases clockwise toward the face. Further, since 225 degrees and 275 degrees are angles when the face is considered to be symmetrical, in reality, the respective angles may be slightly shifted. As can be seen from the equation (1) of the Gabor filter, the shape of the filter is the same even if the angle θ deviates by 180 degrees, so the same effect can be obtained by using 45 degrees instead of 225 degrees, for example. Is obtained.

  In addition, estimated visual scores may be calculated for each of the left and right cheeks. In this case, in the line detection step (S22), the analyzer 10 specifies one or more predetermined angles corresponding to the analysis target site among the plurality of usage angle information predetermined for the plurality of analysis target sites. Do. That is, the analyzer 10 specifies 135 degrees, or 135 degrees and 85 degrees when the cheek on the left side is to be analyzed, and 225 degrees or 225 degrees when the cheek on the right side is to be analyzed. And 275 degrees. In addition, one analysis target site may be selected from a plurality of different analysis target sites such as the eyes, cheeks, mouth, neck, eyes and forehead. Also in this case, since the direction (angle) that affects the visual impression of the wrinkle state differs for each part, the usage angle information may be determined in advance for each analysis target part. For example, in the case where the forehead is the analysis target site, one or more predetermined angles including the horizontal angle are specified, and when the neck muscle is the analysis target site, the one or more predetermined angles including the vertical angle The predetermined angle is identified. Then, in the calculation step (S24), the analysis apparatus 10 identifies a regression equation corresponding to the analysis target site from among a plurality of regression formulas predetermined for the plurality of analysis target sites, and the identified regression An estimated visual score is calculated using a formula.

  Note that although the plurality of steps (processes) are described in order in the plurality of flowcharts used in the above description, the execution order of the steps performed in each embodiment is not limited to the described order. In each embodiment, the order of the illustrated steps can be changed within the scope of the content. In addition, each step may include contents implemented by a person. For example, the skin luminance image acquired in (S21) may be read by the analysis device 10 from a file selected by a human operation on the analysis device 10. In addition, in (S 82), when the analysis target site is cut out from the acquired skin luminance image, the position of the analysis target site may be designated by a human operation on the analyzer 10. Moreover, the above-mentioned each embodiment can be combined within the range in which the contents do not contradict each other.

  Some or all of the contents described above can also be specified as follows. However, the above content is not limited to the following description.

<1> An image acquisition step of acquiring a skin luminance image of a region to be analyzed;
A line detection step of extracting one or more linear texture images at one or more predetermined angles corresponding to the analysis target part from the skin luminance image acquired in the image acquisition step;
An intensity extraction step of extracting linear component intensities of the one or more predetermined angles from the one or more linear texture images extracted in the line detection step;
A relational expression between linear component intensities of the one or more predetermined angles and visual scores of wrinkles on the face image obtained by regression analysis for a plurality of sample face images, and extracted in the intensity extraction step A calculation step of calculating an estimated visual score of wrinkles of the skin at the analysis target site using the linear component strength;
Wrinkle state analysis method including:

<2> The single relational expression that the linear component intensity of the first predetermined angle having the highest correlation with the visual score is an explanatory variable and the visual score is an objective variable, or the first predetermined angle thereof It is a multiple regression equation in which linear component intensities at two predetermined angles including the above are used as an explanatory variable and the visual score as a target variable.
The wrinkle state analysis method as described in <1>.
<3> An information acquiring step of acquiring age information of the subject of the skin for which the estimated visual score is calculated in the calculating step;
An output step of arranging and outputting a representative visual score corresponding to the age information acquired in the information acquisition step and the estimated visual score calculated in the calculation step;
The wrinkle state analysis method according to <1> or <2>, further comprising
<4> An information acquiring step of acquiring age information of the subject of the skin for which the estimated visual score is calculated in the calculating step;
An output that arranges and outputs the representative linear texture image corresponding to the age information acquired in the information acquisition step and the linear texture image extracted in the line detection step at predetermined angles corresponding to the analysis target portion Process,
The wrinkle state analysis method according to any one of <1> to <3>, further comprising
<5> An output step of outputting an image in which a plurality of linear texture images extracted in the line detection step are superimposed and linear components are represented in different colors for each image.
The wrinkle state analysis method according to any one of <1> to <4>, further comprising
<6> The intensity extraction process is a binary process obtained by binarizing the one or more linear texture images extracted in the line detection process using a predetermined binarization threshold value. Extracting the linear component intensity of the one or more predetermined angles using an area of one value of the
The wrinkle state analysis method as described in any one of <1> to <5>.
<7> The line detection step applies the one or more linear texture images to the skin luminance image by applying a Gabor filter corresponding to the one or more predetermined angles corresponding to the analysis target portion. Extract,
The wrinkle state analysis method as described in any one of <1> to <6>.
<8> An image processing step of acquiring a surface reflected light image from each polarized image obtained by projecting S polarized light onto the skin of a subject and imaging S polarized light and P polarized light;
A normalization step of extracting a normalized skin image of the analysis target site from the surface reflection light image;
Further include
The image acquisition step acquires the skin luminance image by deleting color information from the skin image.
The wrinkle state analysis method as described in any one of <1> to <7>.
<9> The analysis target site is any one of cheek, eye, mouth, and neck muscle, which is prone to small wrinkles.
The wrinkle state analysis method as described in any one of <1> to <8>.
<10> The line detection step includes identifying the one or more predetermined angles corresponding to the analysis target site among a plurality of usage angle information predetermined for a plurality of analysis target sites,
In the calculation step, the analysis target is selected from among a plurality of relational expressions between linear component intensities at one or more predetermined angles and visual scores of wrinkles on a face image, which are predetermined for the plurality of analysis target portions. Including identifying the relationship corresponding to the site,
The wrinkle state analysis method as described in any one of <1> to <9>.
<11> The analysis target site is a left cheek or a right cheek,
In the case where each of the one or more predetermined angles is 0 degrees in the reverse vertical direction, 180 degrees in the vertical direction, and increases clockwise toward the face,
When the analysis target site is the left cheek, the one or more predetermined angles corresponding to the analysis target site are 135 degrees, or 135 degrees and 85 degrees,
When the analysis target site is the right cheek, the one or more predetermined angles corresponding to the analysis target site are 225 degrees, or 225 degrees and 275 degrees.
The wrinkle state analysis method as described in any one of <1> to <10>.
<12> An image acquisition unit for acquiring a skin luminance image of an analysis target site,
Line detection means for extracting one or more linear texture images at one or more predetermined angles corresponding to the analysis target part from the skin luminance image acquired by the image acquisition means;
Intensity extraction means for extracting linear component intensities at the one or more predetermined angles from the one or more linear texture images extracted by the line detection means;
A relational expression between linear component intensities of the one or more predetermined angles and visual scores of wrinkles on the face image obtained by regression analysis for a plurality of sample face images, and extracted by the intensity extraction means Calculation means for calculating an estimated visual score of wrinkles of the skin of the analysis target site using the linear component strength;
Wrinkle condition analyzer comprising:
<13> The relational expression is a single regression equation in which the linear component intensity of the first predetermined angle having the highest correlation with the visual score is an explanatory variable and the visual score is an objective variable, or the first predetermined angle thereof It is a multiple regression equation in which linear component intensities at two predetermined angles including the above are used as an explanatory variable and the visual score as a target variable.
The wrinkle state analyzer according to <12>.
<14> Information acquiring means for acquiring age information of the subject of the skin for which the estimated visual score has been calculated;
Output processing means for arranging and outputting a representative visual score corresponding to the age information acquired by the information acquisition means and the estimated visual score calculated by the calculation means;
The wrinkle state analyzer according to <12> or <13>, further comprising:
<15> Information acquiring means for acquiring age information of the subject of the skin for which the estimated visual score has been calculated;
An output that arranges and outputs a representative linear texture image corresponding to the age information acquired by the information acquisition means and a linear texture image extracted by the line detection means at predetermined angles corresponding to the analysis target part Processing means,
The wrinkle state analyzer according to any one of <12> to <14>, further comprising:
<16> Output processing means for outputting an image in which a plurality of linear texture images extracted by the line detection means are superimposed, and in which linear components are represented in different colors for each image.
The wrinkle state analyzer according to any one of <12> to <15>, further comprising:
<17> An image processing means for acquiring a surface reflected light image from each polarized image obtained by projecting S polarized light onto the skin of a subject and imaging S polarized light and P polarized light,
Normalization means for extracting a normalized skin image of the analysis target site from the surface reflection light image;
And further
The image acquisition unit acquires the skin luminance image by deleting color information from the skin image.
The wrinkle state analyzer according to any one of <12> to <16>.
<18> The line detection means specifies the one or more predetermined angles corresponding to the analysis target site from among a plurality of usage angle information predetermined for a plurality of analysis target sites,
The calculation unit is configured to calculate the analysis target from among a plurality of relational expressions between linear component intensities at one or more predetermined angles and visual scores of wrinkles on a face image, which are predetermined for the plurality of analysis target portions. Identify the relational expression corresponding to the site,
The wrinkle state analyzer according to any one of <12> to <17>.
<19> A program causing at least one computer to execute the wrinkle state analysis method according to any one of <1> to <11>.

1 CPU
2 Memory 5 Output Device 6 Input Device 10 Wrinkle Condition Analyzer (Analyzer)
11 image acquisition unit 12 line detection unit 13 intensity extraction unit 14 calculation unit 16 information acquisition unit 17 output processing unit 18 image processing unit 19 standardization unit

Claims (13)

An image acquisition step of acquiring a skin luminance image of a region to be analyzed;
A line detection step of extracting one or more linear texture images at one or more predetermined angles corresponding to the analysis target part from the skin luminance image acquired in the image acquisition step;
An intensity extraction step of extracting linear component intensities of the one or more predetermined angles from the one or more linear texture images extracted in the line detection step;
A relational expression between linear component intensities of the one or more predetermined angles and visual scores of wrinkles on the face image obtained by regression analysis for a plurality of sample face images, and extracted in the intensity extraction step A calculation step of calculating an estimated visual score of wrinkles of the skin at the analysis target site using the linear component strength;
Wrinkle state analysis method including: The relational equation is a single regression equation in which the linear component intensity of the first predetermined angle having the highest correlation with the visual score is the explanatory variable and the visual score is the objective variable, or two including the first predetermined angle thereof It is a multiple regression equation in which the linear component intensity at a predetermined angle is an explanatory variable and the visual score is an objective variable.
The method for analyzing wrinkles according to claim 1. An information acquisition step of acquiring age information of the subject of the skin for which the estimated visual score is calculated in the calculation step;
An output step of arranging and outputting a representative visual score corresponding to the age information acquired in the information acquisition step and the estimated visual score calculated in the calculation step;
The wrinkle state analysis method according to claim 1 or 2, further comprising An information acquisition step of acquiring age information of the subject of the skin for which the estimated visual score is calculated in the calculation step;
An output that arranges and outputs the representative linear texture image corresponding to the age information acquired in the information acquisition step and the linear texture image extracted in the line detection step at predetermined angles corresponding to the analysis target portion Process,
The wrinkle state analysis method according to any one of claims 1 to 3, further comprising An output step of outputting an image in which a plurality of linear texture images extracted in the line detection step are superimposed and linear components are represented in different colors for each image;
The wrinkle state analysis method according to any one of claims 1 to 4, further comprising In the intensity extraction step, the one or more linear texture images extracted in the line detection step are binarized using a predetermined binarization threshold value, and a binarized image obtained by the binarization processing Extract the linear component intensities at the one or more predetermined angles using an area of one value,
The wrinkle state analysis method according to any one of claims 1 to 5. The line detection step extracts the one or more linear texture images by applying a Gabor filter corresponding to the one or more predetermined angles corresponding to the analysis target portion to the skin luminance image.
The wrinkle state analysis method according to any one of claims 1 to 6. An image processing step of acquiring a surface reflected light image from each polarized image obtained by projecting S polarized light onto the skin of a subject and imaging S polarized light and P polarized light;
A normalization step of extracting a normalized skin image of the analysis target site from the surface reflection light image;
Further include
The image acquisition step acquires the skin luminance image by deleting color information from the skin image.
The wrinkle state analysis method according to any one of claims 1 to 7. The site to be analyzed is any one of cheeks, around eyes, around mouth, and neck muscles, which are susceptible to small wrinkles.
The wrinkle state analysis method according to any one of claims 1 to 8. The line detection step includes identifying the one or more predetermined angles corresponding to the analysis target site from among a plurality of usage angle information predetermined for a plurality of analysis target sites,
In the calculation step, the analysis target is selected from among a plurality of relational expressions between linear component intensities at one or more predetermined angles and visual scores of wrinkles on a face image, which are predetermined for the plurality of analysis target portions. Including identifying the relationship corresponding to the site,
The wrinkle state analysis method according to any one of claims 1 to 9. The analysis target site is a left cheek or a right cheek,
In the case where each of the one or more predetermined angles is 0 degrees vertically upward , 180 degrees vertically downward , and increases clockwise toward the face,
When the analysis target site is the left cheek, the one or more predetermined angles corresponding to the analysis target site are 135 degrees, or 135 degrees and 85 degrees,
When the analysis target site is the right cheek, the one or more predetermined angles corresponding to the analysis target site are 225 degrees, or 225 degrees and 275 degrees.
The wrinkle state analysis method according to any one of claims 1 to 10. An image acquisition unit that acquires a skin luminance image of the analysis target portion;
Line detection means for extracting one or more linear texture images at one or more predetermined angles corresponding to the analysis target part from the skin luminance image acquired by the image acquisition means;
Intensity extraction means for extracting linear component intensities at the one or more predetermined angles from the one or more linear texture images extracted by the line detection means;
A relational expression between linear component intensities of the one or more predetermined angles and visual scores of wrinkles on the face image obtained by regression analysis for a plurality of sample face images, and extracted by the intensity extraction means Calculation means for calculating an estimated visual score of wrinkles of the skin of the analysis target site using the linear component strength;
Wrinkle condition analyzer comprising:   A program causing at least one computer to execute the wrinkle state analysis method according to any one of claims 1 to 11.

Images