KR20180109676A - 2D skin image analysis system and analysis method using thereof - Google Patents

Abstract

The present invention provides a system and a method for analyzing a two-dimensional skin image, which can accurately measure and analyze skin feature parts without expensive special equipment. According to an embodiment of the present invention, the system for analyzing a two-dimensional skin image comprises: an image measuring unit including a light source irradiating light to a skin in a direction of an upper part of the skin and an image measuring part measuring a two-dimensional skin image; and an image processing unit including an image extracting part generating an extraction image by extracting a preset-color from the measured image and an image binarizing part binarizing the extracted image.

Description

[0001] The present invention relates to a skin image analysis system,

The present invention relates to a two-dimensional skin image analysis system and method, and more particularly, to a two-dimensional skin image analysis system and an analysis method capable of accurately measuring and analyzing skin characteristics.

Skin pores and wrinkles are major features of aging. Accordingly, various methods have been attempted to evaluate skin characteristics such as pores and wrinkles.

Conventionally, 3D image and 2D image were used to evaluate pores.

In the case of using 3D image, the depth of the pore can be measured, but the shape, distribution and area of the pore can not be calculated, and the measurement can not be performed without expensive special equipment. In addition, since it is difficult to distinguish the roughness of the pores from the skin roughness, and the pore deviation varies depending on the focus, it is necessary to closely adhere the equipment to the subject's face in order to adjust the focus accurately. However, there is a problem that an error occurs because the pores or wrinkles of the subject are pressed and deformed while the equipment is closely attached.

In the case of a method using a 2D image as in Patent Document 1, the fact that it is darker than other areas due to the blackhead of the pore region is used. When measured by this method, skin pigmentation outside the pore, shadow caused by facial bending, The structure of the pores is included in the result value, which causes the error, and it is difficult to analyze the pores accurately. Also, in the case of a 2D image, there is a problem that a pore deviation occurs depending on the focus, and when the equipment is brought into contact with the skin of the subject, the shape of the pore or wrinkle is deformed and an error occurs.

1 is a photograph showing a pore analysis method using a 2D face image according to the prior art. Referring to FIG. 1 (a), a two-dimensional face image is measured and ROI (A ₁ ) is set. Referring to FIG. 1 (b), the image of the region of interest A ₁ is converted to gray scale. Referring to FIG. 1 (c), color information is removed from the image converted to gray scale and only the shaded area is left. In this case, as shown in the lower right, there is a problem that the image is lost due to the bending of the face.

That is, in the conventional 3D image analysis, the depth of the pore can be measured, but the shape and the distribution area can not be calculated, and it is difficult to measure the pore with expensive bulky equipment. In the case of 2D image analysis, it is difficult to accurately analyze the results because the results include shadows due to facial bending. In addition, both of the 3D and 2D images have an error due to the focus, so that they are brought into close contact with the face. In this case, the shape of the pore or wrinkle is deformed to cause an error.

JP1995-231883A

SUMMARY OF THE INVENTION The present invention provides a two-dimensional skin image analysis system and an analysis method capable of measuring and analyzing accurate skin features without expensive special equipment.

In addition, the present invention provides a two-dimensional skin image analysis system and analysis method capable of analyzing pore features by minimizing errors caused by facial bending, fine wrinkles, and the like.

The present invention also provides a two-dimensional skin image analysis system and method for analyzing pore features in various angles by analyzing the angle, number, distribution, stretching length, etc. of the pores.

The present invention also provides a two-dimensional skin image analysis system and an analysis method capable of minimizing errors due to focus through focus correction and analyzing skin characteristics without bringing the measuring device into close contact with the face.

SUMMARY OF THE INVENTION The present invention has been made to solve the above-mentioned problems, and it is an object of the present invention to provide an image measuring apparatus including an image measuring unit including a light source for irradiating light to the skin in an upper direction of the skin, and an image measuring unit for measuring a two- And an image processing unit including an image extracting unit for extracting predetermined colors from the measured image to generate an extracted image, and an image binarizing unit for binarizing the extracted image.

The image measuring unit is disposed to face the subject skin, and the light source may be disposed in an upper direction with respect to an axis connecting the skin and the image measuring unit.

The target skin is the face skin, and the light source may be disposed within a range of 0 to 90 degrees to the left or right about the axis of the head of the head.

The target skin is the face skin, and the light source can be disposed in the range of 0 to 90 degrees in the frontal direction about the pivotal axis of the head.

The image processing unit may further include a pre-processing unit for applying a filter to the measured image and preprocessing the filter.

The filter may be a high pass filter.

The predetermined color may be blue.

And a skin analysis unit for analyzing skin features in the binarized image.

The skin analysis unit may analyze at least one of a pore drawing length, a pore area, a pore distribution, a pore angle, and a number of pores.

Wherein the image measuring unit comprises an integral image measuring device including a light source, the image measuring unit, a fixing unit fixing the position of the subject to the image measuring unit, and a housing including the light source, the image measuring unit, Lt; / RTI >

According to another aspect of the present invention, there is provided a method for analyzing a two-dimensional skin image, the method comprising: an image measuring step of measuring a two-dimensional skin image by irradiating light to the skin in an upper direction of the skin; An image extracting step of extracting predetermined colors from the measured image to generate an extracted image; And an image binarizing step of binarizing the extracted image.

In the image extracting step, a blue color image may be extracted by extracting a blue color image.

In the image extracting step, the binarized image may be generated by increasing the contrast ratio in the blue extracted image.

And analyzing the skin feature in the binarized image.

And analyzing the pores in the binarized image to calculate pore feature data composed of at least one of a pore elongation length, a pore area, a pore distribution, a pore angle, and a number of pores in the image analysis step.

The image analysis step may include collecting and storing pore image data or pore feature data binarized by race or age; And estimating the race or age range of the subject by comparing the binarized image or the pore characteristic data of the measured skin with the binarized pore image or the pore characteristic data by the race or age.

Wherein the image analysis step comprises the steps of: collecting and storing binaural pore image or pore characteristic data according to use time or usage of the test cosmetic; And calculating the degree of influence of the pores of the test cosmetic based on the change of the modified pore image or the pore characteristic data according to the use time or use amount of the test cosmetic.

According to an embodiment of the present invention, it is possible to provide a two-dimensional skin image analysis system and analysis method capable of measuring and analyzing accurate skin features without expensive special equipment.

In addition, it is possible to provide a two-dimensional skin image analysis system and analysis method capable of analyzing pore features by minimizing errors caused by facial bending, fine wrinkles, and the like.

It is also possible to provide a two-dimensional skin image analysis system and analysis method capable of analyzing pore features in various angles by analyzing the angle, number, distribution, stretching length, etc. of pores.

In addition, it is possible to provide a two-dimensional skin image analysis system and an analysis method capable of minimizing errors due to focus through focus correction and analyzing skin characteristics without being brought into close contact with a face.

And, it can be used for collecting and storing the pore characteristic data by race or age, building a database, and estimating the race or age range of the subject based on the pore characteristic data measured therefrom.

It may also be used to analyze the effect of the product on the pores through the pore image and the quantitative pore feature data based thereon. That is, it can be used to judge the efficacy of the pore-related product through the change of the pore characteristic data of the subject using the product.

FIG. 1 is a photograph showing pore images by a conventional pore analysis method.
FIG. 2 is a schematic view of a two-dimensional skin image analyzing apparatus according to an embodiment of the present invention.
3 is a side view schematically showing the arrangement of an image measurement unit according to an embodiment of the present invention.
4 is a front view schematically showing an arrangement of an image measurement unit according to an embodiment of the present invention.
5 is a flowchart schematically illustrating a method of analyzing a two-dimensional skin image according to an embodiment of the present invention.
6 is a flowchart schematically showing a method of analyzing a two-dimensional skin image according to another embodiment of the present invention.
7 is a photograph showing pore images by a two-dimensional skin image analyzer according to an embodiment of the present invention.
FIG. 8 shows pore images of the respective ages and measured pore images according to an embodiment of the present invention.
FIG. 9 is a graph showing the pore area distribution according to the prior art and the embodiment of the present invention.
FIG. 10 is a magnified view of the image-processed images of FIG. 8 by age.
11 is a graph showing the average pore elongation rate of subjects by age.
Fig. 12 shows measured pore images of subjects in their 50s and 60s.

These embodiments are capable of various modifications and various embodiments, and specific embodiments will be described in detail with reference to the drawings. It is to be understood, however, that it is not intended to limit the scope of the specific embodiments but includes all transformations, equivalents, and alternatives falling within the spirit and scope of the disclosure disclosed. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS In the following description of the embodiments of the present invention,

In the embodiment, 'module' or 'sub' performs at least one function or operation, and may be implemented in hardware or software, or a combination of hardware and software. In addition, a plurality of 'modules' or a plurality of 'parts' may be integrated into at least one module except for 'module' or 'module' which need to be implemented by specific hardware, and implemented by at least one processor (not shown) .

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. Referring to the accompanying drawings, the same or corresponding elements are denoted by the same reference numerals, and a duplicate description thereof will be omitted.

FIG. 2 is a schematic view of a two-dimensional skin image analyzing apparatus according to an embodiment of the present invention.

2, a two-dimensional skin image analysis system according to an embodiment of the present invention includes an image measurement unit 1 for measuring a two-dimensional skin image and an image processing unit 3 for processing a measured image do.

The image measuring unit 1 includes a light source 11 for irradiating light to the skin in the upper direction of the skin, and an image measuring unit 13 for measuring the two-dimensional skin image.

In the present specification, the skin feature refers to a portion in which irregularities are formed on another common skin surface including pores, wrinkles, scars, and the like and has a height difference. According to one embodiment, the skin features may be pores in the face.

The light source 11 is configured to guide shadows to the features of the skin. Are arranged to induce undistorted shadows on the skin features. For example, the pores have irregularities, which can cause shadows due to light.

The image measuring unit 13 is a device for measuring a skin image, and various image measuring devices such as a camera that can be used in the art can be applied thereto.

FIG. 3 is a side view schematically showing the arrangement of an image measurement unit according to an embodiment of the present invention, and FIG. 4 is a front view schematically showing an arrangement of an image measurement unit according to an embodiment of the present invention.

3, the image measuring unit 13 is disposed to face the subject skin (i.e., the subject X), and the light source 11 connects the skin and the image measuring unit 13 As shown in Fig.

When the light source 11 is irradiated on the front surface, it is difficult to distinguish features such as pores even if a two-dimensional image is measured, since shadows are hardly generated in the characteristic portions of the skin. Therefore, the light source 11 can be irradiated to one side with respect to the subject X. [

Further, when the light source 11 is irradiated from one side, the shadow of the characteristic portion may be inclined or distorted. According to one embodiment, the image measuring unit 13 is arranged to face the subject X, and the light source 11 is disposed in the upper direction (the X direction) with respect to the axis connecting the image measuring unit 13 and the subject X That is, in the direction opposite to the paper surface or in the direction toward the subject's (X) crown) to irradiate the light X.

More specifically, the skin may be placed into a face to be subjected when the skin, the light source 11 around the top of the head of the head axis (X ₁₎ in the front direction 0 ° to a range of 90 °. In order to measure the face skin, since the shadow is distorted by other parts of the face when it exceeds 90 degrees, it can be arranged to have a value of 90 degrees or less.

3, the light source 11 be disposed at a first angle (α) which is previously set in the direction of the front direction toward the nose around the top of the head axis (X ₁₎ of the head of the subject (X) have. Figure 3 is an arrangement for guiding undistorted shadows, particularly at the pore region, wherein the first angle [alpha] is approximately 45 [deg.].

When the skin to be treated is facial skin, the light source 11 may be arranged in a range of 0 to 90 degrees to the left or right side around the axis X ₂ of the head of the head.

Particularly, when applied to facial skin, since the nose is the highest in the characteristic of the contour of the face, the nose may be excessively biased to the left or right around the nose. Or, the shadow of the feature such as the pore may be inclined, and the length component such as the stretching length may be distorted and can be measured incorrectly. Therefore, the light source 11 may be arranged in the range of less than 90 ° to the right or left around the top of the head axis (X ₂₎ of the face.

More specifically, referring to Figure 4, the light source 11 has a second angular predetermined left or right direction toward the right or left ear around the top of the head axis (X ₂₎ of the head of the subject (X) ( beta]. FIG. 4 shows an embodiment in which the light source 11a has a second angle? Of about 0 DEG, and the light source 11b is a light source having a predetermined angle of 0 deg. As shown in Fig. However, it should be understood that the present invention is not limited thereto and may be disposed on the left side. Also, the light source 11 may be arranged to have a predetermined first angle? And a second angle? Both set to the front direction component and the left / right direction. That is, in the case of the embodiment for measuring the pore region, the first angle? Is approximately 45 ° and the second angle? Is approximately 0 ° so as to optimize the shadow of the pore region.

With this arrangement, it is possible to derive shadows having similar shapes and shapes to the features, while minimizing the shadows that may be caused by the skin, or specifically by other structures that may form on the face.

Herein, the system and method for measuring two-dimensional skin images will be described mainly on the face skin, particularly on the pores, but the present invention is not limited thereto. The system and method may be other parts other than the face, Of course, can be used to analyze the features of the device.

The angle can be adjusted so that the light source irradiates light to the target site in the upper direction according to the structural characteristics of each site.

According to an embodiment of the present invention, the image measuring unit 1 includes a light source 11, an image measuring unit 13, a fixing unit capable of fixing the position of the subject, A measurement section 13 and a housing including a fixing section (not shown) therein. It is possible to fix the face of the subject including the fixing portion and to control the light source to eliminate the error. For example, the image measuring apparatus may be VISIA-CR ^® in Canfield four (Fairfield, NJ, USA). However, it is needless to say that the present invention is not necessarily limited to this, and the light source 11, the image measuring unit 13, and the fixing unit may be constituted by a detachable image measuring apparatus formed to be assembled and disassembled.

According to one embodiment, when the pore region is measured using VISIA-CR ^® , only the upper light source in the standard 1 mode or the 2 mode has aperture values of F5.6 + 1 to F5.6 + 9, F8.0 + 0 To F8.0 + 9, F11.0 + 0 to F11.0 + 9, and the left, right, and bottom light sources can be turned on and off. Preferably, when the light source in the range of F11.0 + 0 to F11.0 + 9 is turned on, the sharpest pore image can be obtained.

Referring again to FIG. 2, the image processing unit 3 removes shadows due to skin color elements and skin curvature through image processing, and generates an image that enhances the feature.

More specifically, the image processing unit 3 includes an image extracting unit 31 for extracting a predetermined color from the measured image to generate an extracted image, and an image binarizing unit 33 for binarizing the extracted image do.

The image extracting unit 31 removes shadows due to skin color elements and skin bending. Specifically, the portion due to pigmentation can be removed from the two-dimensional skin image, and shadows due to skin curvature can be removed.

Particularly, when applied to the measurement of the pores of the face, it is possible to remove shadows caused by skin pigmentation such as stains or spots formed on the face and skin bending such as wrinkles on the palate.

The image extracting unit 31 extracts a predetermined color from the measured two-dimensional skin image so as to extract only the image of the feature of the skin to generate an extracted image. For example, when measured to analyze facial pores, a blue extracted image may be generated by extracting blue from a two-dimensional skin image. In this case, the difference in shade of the pores can be maximized through the blue extract image.

The present invention is not necessarily limited to this, and when a red color image is generated by extracting a red color from a two-dimensional skin image, the difference in shade of sebum formed on the skin can be maximized. That is, the present invention can be applied to analyzing the sebum distribution and area of the skin using a red extract image.

In addition, when green is extracted from a two-dimensional skin image to generate a green extract image, the difference in shading of the white head formed on the skin can be maximally extracted. That is, the present invention can be applied to analyzing the distribution and area of the whitehead of the skin using a green extract image.

Utilizing various color extraction images, it is possible to maximize the shade image of a desired skin feature. That is, it is possible to separate only the desired features by analyzing the skin bending or pigmentation regions in the two-dimensional skin image.

The image binarization unit 33 binarizes the extracted image and analyzes the feature based on the binarized data. In addition, in the image binarization unit 33, the contrast of the feature may be adjusted within a predetermined value range to remove the bending of the face and the wrinkles, and only the pores may be displayed.

According to one embodiment, when analyzing the pores of a face, the control ratio may be set to a value before the pigmented region appears. Accordingly, it is possible to remove the pigmentation site and generate a binarized image showing only the pores.

According to an embodiment of the present invention, the image processing unit 3 may further include a preprocessing unit (not shown) for applying a filter to the measured image and preprocessing the filter. The pre-processor may be used for focus correction.

The pre-processing unit may correct the focus by applying a filter to the image measured by the image measuring unit 13 before the color extracting unit 31 extracts the color. More specifically, in the case of a face image, the projecting nose portion is focused. However, in order to observe the pores of both cheeks, focus correction should be performed. Thus, a filter can be applied to the measured skin image, so that the desired portion can be focused.

According to one embodiment, the filter may be a high-pass filter and may focus on both cheeks of the face to enhance the sharpness of the image ultimately formed.

According to an embodiment of the present invention, the skin analysis unit 5 (also referred to as an " image analysis unit ") for analyzing skin features in the binarized image may further comprise. The skin analysis unit 5 can calculate the distribution, the number, the area, and the like of the feature through the derived binaural skin image.

According to one embodiment, the skin analysis unit 5 may calculate at least one of a pore drawing length, a pore area, a pore distribution, a pore angle, and a number of pores. For example, if the binaural skin image is a monochrome image in which the pores are expressed in white, the total area of the pores can be calculated by summing the areas of the white portions, and the length of the longest diameter in each of the pores is divided into the shortest length, (elongation) can be calculated, and the pore angle and pore distribution can be analyzed. That is, it can solve the disadvantage that the change of the pore can not be shown intuitively, and the pore characteristic can be expressed by the numerical value, and objectivity can be secured in the analysis.

Further, according to the present invention, it is possible to collect and store the pore characteristic data (for example, stretching length, pore area, pore distribution, pore angle, number, etc.) The skin analysis unit 5 can also be used to analyze the effect of the product on the pores through the pore image and the quantitative pore characteristic data based thereon have. That is, it can be used to judge the efficacy of the pore-related product through the change of the pore characteristic data of the subject using the product.

The image processing unit 3 and the image analysis unit 5 may be configured as processing software or hardware, or a combination of software and hardware. According to one embodiment, the image processing unit 3 and the image analysis unit (5), or to exchange data directly or indirectly.

The image processing unit 3 may be, for example, Image-Pro Premier 9.2 from Media Cybernetics, Inc. (Silver Spring, MD, USA), and the pore region in the skin image measured through the image processing unit 3, And a high-pass filter can be applied to perform the preprocessing operation. The high pass filter can be specified in the range of intensity and path value in the range of 1 to 100. After the filter is applied, only blue is extracted to generate a blue extracted image, and in the extracted image excluding the skin color, a threshold of 0 to 130 ) So that only the pore area is left as white, and the remaining part is removed, so that the image can be binarized.

5 is a flowchart schematically illustrating a method of analyzing a two-dimensional skin image according to an embodiment of the present invention.

The two-dimensional skin image analysis method may be performed using the skin image analysis system described above, and the content of the skin image analysis system described above may also be applied to the analysis method.

A method for analyzing a two-dimensional skin image according to an embodiment of the present invention includes an image measuring step (S1) for measuring a two-dimensional skin image by irradiating light to the skin in an upper direction of the skin; An image extracting step (S2) of extracting predetermined colors from the measured image to generate an extracted image; And an image binarization step (S3) of binarizing the extracted image.

According to one embodiment, the method may further include an image analysis step (S4) of analyzing the skin feature in the binarized image.

6 is a flowchart schematically showing a method of analyzing a two-dimensional skin image according to another embodiment of the present invention.

According to an embodiment of the present invention, in particular, the pores of the facial skin can be measured in the following manner.

A two-dimensional skin image analyzing method for analyzing a pore feature according to an embodiment of the present invention includes an image measuring step (S11) of measuring a face image by irradiating light to the skin in an upper direction of the face; A face image preprocessing step (S13) of performing preprocessing for focus correction by applying a high pass filter to the measured face image; An extracted image generating step (S15) of extracting only blue from the preprocessed image to generate a blue extracted image; A binarized image generation step (S17) of generating a binarized image by raising a contrast ratio to extract only a pore feature part from the extracted image; And a skin feature analysis step (or an image analysis step) S19 for analyzing the feature of the pore based on the binarized image.

And analyzing the pores in the binarized image to calculate pore feature data composed of at least one of a pore elongation length, a pore area, a pore distribution, a pore angle, and a number of pores in the image analysis step.

For this purpose, only the pore region of the skin can be highlighted using the blue extract image, and the pigment deposit area or the skin bend area can be removed. Accordingly, it is possible to provide a two-dimensional skin image analysis method that can accurately analyze only the pore features.

According to an embodiment of the present invention, it is possible to provide a two-dimensional skin image analysis system and an analysis method capable of accurately measuring a two-dimensional skin image by inducing an undistorted shadow of a skin feature, particularly a pore region.

Furthermore, in the image analysis step, it is possible to grasp the characteristic of pore by race or age based on the binarized pore image or the pore characteristic data, and to estimate the age or race of the subject's pore.

Specifically, the image analysis step may include collecting and storing pore image data or pore feature data binarized by race or age, and storing the binarized image or pore feature data of the measured skin and the binarized or non- And comparing the pore image or the pore characteristic data to estimate the race or age range of the subject.

According to one embodiment of the present invention, the pore characteristics can be grasped accurately and quantitatively, so that the pore characteristics of each race or age can be accurately grasped and the age of the pores of the subject can be grasped based on the characteristics. For example, it is possible to more easily grasp the state of the pores of the subject by giving the subject the age of his / her pore.

Further, based on the binarized pore image or pore feature data, the degree of pore influence (e.g., pore shrinkage degree, pore age change, etc.) of the product can be calculated.

Specifically, the image analysis step may include: collecting and storing the binarized pore image or the pore feature data according to the use time or usage amount of the test cosmetic, and extracting the binarized pore image or the pore And calculating an influence degree of the pores of the test cosmetic based on the change of the characteristic data.

Accordingly, it can be used to analyze the effect of the pore-related product on the pore through the binarized pore image and the quantitative pore characteristic data based thereon. For example, through the change of the pore characteristic data of the subject using the product, information such as how much the pore size is reduced to the subject, how the pore distribution is reduced, and the pore elongation length is reduced is quantitatively You can check it with images. Various embodiments of the present invention can be used to evaluate the pore impact of cosmetic products.

As a result, through the various embodiments of the present invention described above, it is possible to extract and analyze only a desired feature regardless of skin color, pigment deposition area, or skin curvature by using a color extraction image by extracting predetermined colors from a skin image Dimensional skin image analysis system and an analysis method capable of providing a two-dimensional skin image.

Also, it is possible to provide a two-dimensional skin image analysis system and an analysis method that can provide a clear image through focus correction and provide characteristics of a feature part with an accurate numerical value.

According to an embodiment of the present invention, since the two-dimensional skin image is used, it is possible to freely adjust the area of the region of interest to analyze the feature portion. That is, it is possible to provide a two-dimensional skin image analysis system and analysis method capable of quickly and easily measuring a wide range of pores.

The equipment using the 3D image is expensive and complicated equipment, but it is possible to measure and analyze the characteristics of the pores by cheap and simple method through the 2D skin image analysis system, and to evaluate easily and intuitively through the image Dimensional skin image analysis system and analysis method capable of providing an objective basis for the skin image analysis.

In order to evaluate pore features, analysis was performed through a two-dimensional skin image analysis system according to an embodiment of the present invention. The photographs of FIG. 7 are photographs derived by this two-dimensional skin image analysis system.

Was used VISIA-CR ^® by image measurement unit (1), the light source was turned off only the upper light source direction F11.0 + 8 at 1 Standard mode balance of the light source. The ISO value was set to 100, the aperture value was set to F16, the daylight was set to the white balance at a resolution of 5616 × 3744, and the pore portion of one cheek was observed at the front of the subject And the region of interest (ROI) A ₂ was set (see Fig. 7 (a)).

As shown in FIG. 7 (b), a highpass filter is set to a strength of 5 and a pass value of 10 to a region of interest (A ₂ ) of the photographed image to perform a preprocessing operation.

Then, as shown in FIG. 7 (c), only blue is extracted and a blue extracted image is generated. At this time, the pore regions are clearly emphasized, while the pigmentation sites are also microscopically visible.

Thereafter, as shown in (d) of FIG. 7, the contrast ratio was increased to the value before the pigmentation site appeared, thereby generating a binarized image. Referring to FIG. 7 (d), it can be seen that the pigment deposits P ₁₁ and P ₁₂ shown in FIG. 7 (b) have been removed. The skin condensation areas (P ₉ , P ₁₀ ) were also removed from the final binarized image, indicating that only the pore area was converted to a black and white image.

Subject

In the age group of 20 (27.36 ± 1.36 years, 11), 30 (34.64 ± 2.45 years, 33), 40 (44.87 ± 3.22 years, 45), 50 (52.60 ± 2.54 years, 20) 61.00 ± 1.42 years old, 7 persons). The characteristics of the pores were measured. To prevent environmental influences, subjects were allowed to rest in a laboratory maintained at 40 ± 2% relative humidity for 20 minutes at a temperature of 20 ± 2 ° C. Optical images were then measured.

Image measurement

First, light was irradiated from all directions of the subject's face according to the conventional technique as described in FIG. 1, and the pore area of the pore area was measured in pixel units after conversion to gray scale using an image analysis program.

And, according to one embodiment of the invention, face images have been measured with respect to the front face 1 in the Standard mode by using the VISIA-CR ^®. Some subjects were adjusted so that the light was illuminated only at the top and all of the light in the other direction was lost, as a portion of the subject's face could be lost due to bending of the face.

Image processing

The measured images were processed using Image-Pro Plus 9.2. The region of interest (ROI) was designated as 700 x 700 pixels on the right cheek, and a high pass filter was applied to the region of interest (ROI) and converted to a grayscale image. Finally, the threshold was applied to remove the skin pigmentation out of the skin, excluding the pores of the face. In the image after image processing, the pores appeared white. The total area of the pores was measured by calculating the sum of the areas of the white areas. The pore elongation was calculated as the ratio of the short diameter to the long diameter in the elliptical pores.

The pore images according to an embodiment of the present invention can be calculated by image processing to calculate the number of pixels and the pore area can be calculated, and it is possible to analyze the distribution, direction and shape of the pores using the visual image itself I could.

Statistical analysis

Results from SPSS Inc. (Chicago, IL, USA) were analyzed. For normal distribution data, one-way ANOVA was used, and for non-normal distribution data, only Bay-Whitney U was used. Following the Kruskal-Wallis test, multiple comparisons were performed with Bonferroni's correction to compare age differences. Statistical significance was assumed to be P <0.05.

Changes in shape and area of pores by age

FIG. 8 is a graph showing the relationship between the age-based pore images A, B, C, D and E measured according to an embodiment of the present invention and the pore images F, G, H , I, J).

Referring to FIG. 8, it was found that the pores of the twenties were mainly located around the central portion of the face around the nose (A, F). However, the pores of the subjects in their thirties were found around the nose and around the cheeks (B, G). The pores of the subjects in their forties were more prominent than those in their thirties, and they were found to have U-shaped pores (C, H). It was found that the pores previously formed in the U shape changed obliquely and some pores were combined. The pores of the 50 subjects showed clear directionality, but the area of the pores represented by the number of pixels was smaller than those of the forties (D, I). The pores of the subjects in their 60s were mostly disappeared, while the pores around the nose remained wrinkled (E, J).

FIG. 9 is a graph showing the pore area distribution by age group measured according to the prior art (a) and the above-described embodiment (b) of the present invention.

9 (a) and 9 (b), according to the prior art and the embodiment of the present invention, the pore area increases from 20 to 40, and then decreases from 50 .

However, referring to FIG. 9 (a), according to the conventional art, when the pore area is about 3000 to 6000 pixels in all ages, The average was similar for the 40s, 50s, and 60s. It was difficult to analyze the distribution, orientation and shape of pores, and only pore area and number of pores could be confirmed.

Referring to FIG. 9B, according to an embodiment of the present invention, the pore area is distributed in a range of approximately 5000 pixels to 15000 pixels, Respectively. In other words, the difference between the ages was clearly distinguished. 9A, it can be seen that the deviation of the graph of FIG. 9B is greatly reduced, and the deviation value does not change largely over the ages, thereby increasing the measurement accuracy and reliability of the data In FIG. 9 (b), the pore area of the subjects in their twenties is 5604.45 pixels, and the area of the pores of the subjects in their thirties is about 80.97% more than that of the subjects in their twenties. . On the other hand, it was found that the pore area of the subjects in their forties was the largest in all ages, and it was about 176.49% larger than those in their 20s. The subjects in the 40s or older were able to confirm that the pore area gradually decreased to 60s.

Changes in elongation of pores by age

FIG. 10 is a magnified view of the image-processed images of FIG. 8 by age.

Referring to FIG. 10, in the case of the twenty subjects, the pores show a circular shape (A), and it can be seen that the pores remain up to thirty (B). However, while the pores in the 40s have ellipses and orientations (C), in the 50s, several pores are combined and have distinct directions (D). These features were more evident in the subjects in their 60s (E) and their pores could be seen as wrinkles.

11 is a bar graph (a) showing the average pore elongation rate (ratio of the long diameter / short diameter of the elliptical pores) to the subjects by age and a line graph (b) showing the average and distribution thereof.

Referring to FIG. 11 (a), the elongation rate of the pores of the twenties was about 2.7, and no statistically significant change was observed until the thirties. However, for the subjects in their 40s, the pores had a long elliptical shape, the elongation was increased by about 8.25%, and until the age of 50, there was no statistically significant change compared to the elongation of the pores in their forties. In the subjects in their 60s, rapid pore elongation was found, and it was found that the elongation rate of the pores was increased by about 16.3% as compared to the subjects in their 20s.

Referring to FIG. 11 (b), it can be seen that the length of the pores gradually increases over a lifetime, and that the pore elongation has a positive correlation (r2 = 0.424, p <0.001) with age.

FIG. 12 shows the measured pore images of subjects in their 50s and 60s, and confirmed the direction of the pore drawing. As the age went on, it was confirmed that several pores were combined in the subjects in their 50s and 60s, and skin around the pores formed skin condensates such as wrinkles along the nose lip line.

That is, from the age of 50 and older, the pores around the wrinkles appear to be wrinkled, and the range (the range between the arrows a1 and a2, the range between the arrows a3 and a4) becomes wider and sharper in the 60s.

According to the prior art, it is difficult to precisely measure and grasp the characteristics of pores due to the influence of skin pigment and skin curvature. However, according to one embodiment of the present invention, by using the light irradiated from the upper direction, the influence on the remaining parts other than the pore can be minimized, and the shading ratio of the pores in the image can be strengthened. Accordingly, the size and size of the pores can be clearly measured, and the pore characteristics according to age can be accurately measured.

Specifically, the size and number of the pores are different from each other, and the pore pattern according to the age is different. However, it can not be clearly analyzed without accurate measurement of the pore characteristics. According to the present invention, Data can be provided so that characteristics of pores by age or race can be analyzed clearly.

Accordingly, according to the present invention, it is possible to data of pore characteristics by age group such as elongation percentage of pores, pore area, pore direction, pore distribution, etc., and to estimate the age of the subject's pores by measuring pore characteristics of the subject. In addition, the present invention may be applied to the evaluation of the efficacy of a product by grasping a change in a pore characteristic of a subject according to a product.

1: Image measurement unit
3: Image processing unit
5: Image analysis unit
11: Light source
13: image measuring unit
31: image extracting unit
33:

Claims (17)

An image measuring unit including a light source for irradiating light to the skin in an upper direction of the skin and an image measuring unit for measuring a two-dimensional skin image; And
An image extracting unit for extracting a predetermined color from the measured image to generate an extracted image; and an image processing unit including an image binarizing unit for binarizing the extracted image.
The method according to claim 1,
Wherein the image measuring unit is arranged to face the subject skin,
Wherein the light source is disposed in an upper direction with respect to an axis connecting the skin and the image measuring unit.
The method according to claim 1,
The target skin is the facial skin,
Wherein the light source is disposed in a range of 0 to 90 degrees to the left or right of the axis of the head of the head.
The method according to claim 1,
The target skin is the facial skin,
Wherein the light source is disposed in a range of 0 to 90 degrees in the frontal direction about the pivotal axis of the head.
The method according to claim 1,
Wherein the image processing unit comprises:
Further comprising a pre-processing unit for applying a filter to the measured image and pre-processing the filtered image.
6. The method of claim 5,
Wherein the filter is a high pass filter.
The method according to claim 1,
Wherein the predetermined color is blue.
The method according to claim 1,
Further comprising a skin analysis unit for analyzing skin features in the binarized image.
9. The method of claim 8,
Wherein the skin analysis unit analyzes at least one of a pore drawing length, a pore area, a pore distribution, a pore angle, and a number of pores.
The method according to claim 1,
The image measurement unit includes:
An image measuring unit, a fixing unit fixing the position of the subject to the image measuring unit, and a housing including the light source, the image measuring unit and the fixing unit. Dimensional skin image analysis system.
An image measuring step of measuring a two-dimensional skin image by irradiating light to the skin in an upper direction of the skin;
An image extracting step of extracting predetermined colors from the measured image to generate an extracted image; And
And binarizing the extracted image. The method of claim 1,
12. The method of claim 11,
Wherein in the image extracting step, a blue color is extracted and a blue extracted image is generated.
13. The method of claim 12,
Wherein the binarized image is generated by increasing the contrast ratio in the blue extracted image in the image extracting step.
12. The method of claim 11,
Further comprising an image analysis step of analyzing skin features in the binarized image.
15. The method of claim 14,
And analyzing the pores in the binarized image to calculate pore feature data composed of at least one of a pore elongation length, a pore area, a pore distribution, a pore angle, and a number of pores in the binarized image Dimensional skin image analysis method.
16. The method of claim 15,
Wherein the image analysis step comprises:
Collecting and storing the pore image or pore feature data binarized by race or age; And
Further comprising the step of estimating the race or age range of the subject by comparing the binarized image or the pore characteristic data of the measured skin with the binaural image or the pore characteristic data differentiated by race or age, Analysis method.
16. The method of claim 15,
Wherein the image analysis step comprises:
Collecting and storing the binarized pore image or the pore characteristic data according to the use time or usage amount of the test cosmetics; And
Further comprising the step of calculating the degree of influence of the pores of the test cosmetic based on the change of the binarized pore image or the pore characteristic data according to the use time or usage amount of the test cosmetic.

Images