KR101992403B1 - Skin moisture estimating method using image - Google Patents

Abstract

A method for measuring skin moisture content using an image includes the steps of: detecting a skin area in an image by a computer device; extracting color data and texture data of the skin area by the computer device; And inputting the color data and the texture data to a regression analysis function, which is previously prepared using the relationship between each skin and the moisture content of the skin, to determine skin moisture.

Description

{SKIN MOISTURE ESTIMATING METHOD USING IMAGE}

The technique described below relates to a technique for measuring the moisture of the skin using an image.

BACKGROUND ART [0002] Recently, as interest in skin beauty has increased, devices for diagnosing a user's skin condition through cosmetic-care products have been attracting attention. Meanwhile, a service for managing the skin condition data by a smart phone is also provided.

Korean Patent Publication No. 10-2015-0033938

Conventional techniques for measuring or managing skin conditions basically require a separate device to measure skin condition. The technique described below is intended to provide a method of measuring the degree of moisture of a skin using an image.

A method for measuring skin moisture content using an image includes the steps of a computer device detecting a skin region of a subject in an image, the computer device extracting color data and texture data of the skin region, And determining the first skin moisture content by inputting at least one of the color data and the texture data into a first regression analysis function provided in advance using a relation between at least one of the skin texture data and the skin moisture.

The technique described below can easily measure the moisture content of the skin using only images captured by a camera or a smart device.

FIG. 1 shows an example of a configuration of an apparatus for measuring skin moisture using an image.
2 is an example of a flowchart of a method for measuring skin moisture using an image.
FIG. 3 is an example of a procedure for measuring skin moisture according to the method of FIG.
FIG. 4 shows an example of a process of preparing a regression analysis function.
FIG. 5 shows an example of a procedure for preparing an improved regression analysis function using the calculated skin moisture.
6 is an example of a process for calculating improved skin moisture.

The following description is intended to illustrate and describe specific embodiments in the drawings, since various changes may be made and the embodiments may have various embodiments. However, it should be understood that the following description does not limit the specific embodiments, but includes all changes, equivalents, and alternatives falling within the spirit and scope of the following description.

The terms first, second, A, B, etc., may be used to describe various components, but the components are not limited by the terms, but may be used to distinguish one component from another . For example, without departing from the scope of the following description, the first component may be referred to as a second component, and similarly, the second component may also be referred to as a first component. And / or < / RTI > includes any combination of a plurality of related listed items or any of a plurality of related listed items.

As used herein, the singular " include "should be understood to include a plurality of representations unless the context clearly dictates otherwise, and the terms" comprises & , Parts or combinations thereof, and does not preclude the presence or addition of one or more other features, integers, steps, components, components, or combinations thereof.

Before describing the drawings in detail, it is to be clarified that the division of constituent parts in this specification is merely a division by main functions of each constituent part. That is, two or more constituent parts to be described below may be combined into one constituent part, or one constituent part may be divided into two or more functions according to functions that are more subdivided. In addition, each of the constituent units described below may additionally perform some or all of the functions of other constituent units in addition to the main functions of the constituent units themselves, and that some of the main functions, And may be carried out in a dedicated manner.

Also, in performing a method or an operation method, each of the processes constituting the method may take place differently from the stated order unless clearly specified in the context. That is, each process may occur in the same order as described, may be performed substantially concurrently, or may be performed in the opposite order.

FIG. 1 shows an example of a configuration of an apparatus for measuring skin moisture using an image. FIG. 1 illustrates an example of detecting a face in an image including a user's face. Skin moisture refers to the moisture content of the skin.

1 (a) is an example of measuring skin moisture using a smart device 50 such as a smart phone. The user takes a face with the camera built in the smart device 50. The smart device 50 detects the face area from the source image and extracts the color data of the preset area. The smart device 50 measures skin moisture content based on the color data.

1 (a), the smart device 50 includes a camera 51, a storage device 52, a computing device 53, and an output device 54. The camera 51 acquires the source image. The arithmetic unit 53 extracts the color data of the skin region included in the source image and performs an operation of measuring the skin moisture from the color data. The storage device 52 may temporarily store the source image. The storage device 52 may also store a regression analysis function used to measure skin moisture. The output device 54 can output the measured skin moisture.

1 (b) is an example of measuring the skin moisture by using a device such as a PC. The user shoots the face with the camera 81 connected to the computer 85. The computer 85 detects the face area in the source image and extracts the color data of the preset area. The computer 85 measures skin moisture content based on the color data.

1C is an example in which the server 95 located at a remote location measures the skin moisture using an image acquired by the user terminal 91. FIG. The user takes a face with a camera built in the user terminal 91. The user terminal 91 transfers the photographed source image to the server 95 via the network. In this case, the user terminal 91 includes a communication module for data transmission. The server 95 detects the face area from the source image and extracts the color data of the predetermined area set in advance. The server 95 measures the skin moisture content based on the color data. The server 95 can transmit the measured skin moisture content to the user terminal 91.

In some cases, the user terminal 91 may detect the skin region from the source image and transmit it to the server 95. In this case, the server 95 extracts color data for the skin region and measures skin moisture using the color data. Alternatively, the user terminal 91 may detect the skin region in the source region and extract the color data in the skin region. The user terminal 91 can transmit only the color data of the skin region to the server 95. [ The server 95 can measure the skin moisture using the color data.

Figure 2 is an example of a flowchart for a method (100) for measuring skin moisture using an image.

First, the camera acquires the source image (110). The source image includes a skin area of the user. The computer device detects the skin region in the source image captured by the camera (120). The algorithm by which the computer device detects the skin area can utilize various techniques known in the art.

The computer device extracts color and texture data for the skin region (130). The computer device can extract color and texture data for the entire extracted skin area. The computer device may also extract color and texture data for a specific skin region from the acquired image. The computer device may continue to extract color data in successive images (consecutive frames).

Various values can be used for the color data. For example, (1) the color data may use at least one of an R value, a G value, and a B value based on the RGB color scheme. The color data may use an average value for at least one of R value, G value, and B value. (2) The computer device can convert the RGB color scheme to a different color scheme. For example, computer politics can convert the RGB color scheme to various color schemes such as YUV, HSV, YCbCr, YCgCo, and the like. The computer device can extract color data of at least one of chrominance components or luminance components of a specific color system. In this case, the color data may use one of the components that are less influenced by the surrounding environment (illumination, etc.). For example, in the case of YCbCr, at least one of Cb and Cr can be used. In the case of YCgCo, at least one of Cg and Co may be used. Further, one of the two chrominance components, which is more robust to the variation of the illuminance, can be used. For example, in the case of YCgCo, only Cg can be used. In this case, the computer device can extract the average value of the Cg color data of the skin region as color data. (3) Further, the color data may be a value obtained by combining weights applied to at least one color component in various color systems such as RGB, YUV, HSV, YCbCr, YCgCo, and the like. In the case of combining color components, the color data may be a value obtained by adding different weighted values depending on the color system and the type of color component.

Various kinds of texture data are used in image. Various scales such as contrast, dissimilarity, homogeneity, directionality, and entropy are studied for the texture of images.

The computer device applies the extracted color data and / or texture data to a regression analysis function provided in advance to calculate the skin moisture (140). The computer device can calculate at least one of the color data and the texture data to the regression analysis function to calculate the moisture content of the skin.

FIG. 3 is an example of a process for measuring skin moisture according to the method 100 of FIG.

The user shoots a face image of a person using a smart device or a general camera (a process). The computer apparatus detects a face region displayed in a square in the source image including the face image (step b). The computer device detects the skin area in the face area (step c). Fig. 3 shows an example in which the computer apparatus detects a specific skin area A set in advance in the face area. Figure 3 shows an example in which a computer device detects a " ball " area.

If your computer device uses a color scheme other than RGB, you must perform a color scheme conversion. For example, if you use the YCgCo color scheme, the computer device converts the RGB color scheme of the skin region to the YCgCo color scheme.

The computer device extracts color data and texture data based on the skin area A (step d). For example, the computer device can extract color data from the average value of Co chrominance components in the YCgCo color system. Further, the computer device can extract the contrast value of the skin area A as texture data. The contrast value can be expressed as a flat (average) brightness value of the corresponding region.

The computer device applies color data and / or texture data to a regression analysis function (e process). The regression analysis function is stored in the regression analysis DB. The process of constructing the regression analysis DB will be described later. The computer device determines the result calculated from the regression analysis function as the final skin moisture (f process).

The computer device can calculate a single result using the weighted average of the color data and the texture data in the course of calculating the skin moisture.

Regression analysis is an analytical method that measures fit between two variables for continuous variables. Regression analysis calculates a function (formula) that calculates a specific value using predetermined sample data in advance. The regression function is expressed as an equation representing a regression line or a regression curve. The computer device extracts color data and texture data using images and simultaneously measures skin moisture for the same user using a skin moisture measuring device. This process is repeated to generate a plurality of data, and the computer device generates a regression analysis function that calculates skin moisture from color data and texture data based on the generated plurality of data.

FIG. 4 shows an example of a process of preparing a regression analysis function. The process of preparing samples for color data and texture data will be described. The user shoots a face image of a person using a smart device or a general camera (a process). The computer apparatus detects a face region displayed in a square in the source image including the face image (step b). The computer device detects the skin area in the face area (step c). The computer device extracts color and texture data from the skin region (d). The extracted color data and texture data are stored in the color and texture data DB. FIG. 4 shows an example of detecting a part of the face area A as a sample. Unlike FIG. 4, the entire face region may be detected to extract color data and texture data. A computer device typically provides a plurality of samples for color and texture data.

A sample for the color data and texture data is prepared, and at the same time, a moisture meter measures the skin moisture for the same user (step e). Fig. 4 shows an example in which the moisture content is measured by a moisture meter at B, which is the same point as the A area. Moisture meter refers to a commercially available measuring instrument. The skin moisture measured by the moisture meter is stored in the skin moisture DB. When the computer device extracts the first color data and texture data, it simultaneously measures the first moisture content with the moisture meter. The computer device identifies the color data / texture data and the moisture measured by the moisture meter so that they can match each other. For example, the computer device may store the color data / texture data generated at the same time and the moisture measured by the moisture meter in the same table or in the same order in different tables.

The computer device generates a regression analysis function using the skin moisture measured at the same time as any one of the color data and the texture data (step f), and stores the generated regression analysis function in the regression analysis DB. The computer device can generate a regression analysis function using a plurality of sample data. As described above, the regression analysis function means a regression line or a regression curve.

The computer device can derive a regression linear equation using the color and texture data DB and the skin moisture DB for the same area. The regression linear equation is shown in Equation 1 below.

Where x is the value of the color or texture data in the specified color scheme. a and b are constants obtained by regression analysis. y represents the calculated skin moisture value. The results of applying the actual data may vary with the values of the constants a and b depending on the data used.

The regression curve is a curve obtained by representing a set of points on a correlation chart as a curve rather than a straight line. Regression curves show the relationship between two variables. The computer device can derive a regression curve equation using the color and texture data DB and the skin moisture DB. The regression curve equation is shown in Equation (4) below.

Where x is the value of the color or texture data in the specified color scheme. a, b, and c are constants obtained by regression analysis. y represents the calculated skin moisture value. The result of applying the actual data may vary in constant a, b or c depending on the data used.

As described above, the computer device may use at least one of color data and texture data. A regression analysis function should be provided according to the input data. For example, a regression analysis function may be needed for (1) a regression analysis function for color data, (2) a regression analysis function for texture data, and (3) a combination of color and texture data. Furthermore, when color data and texture data are used, a regression analysis function may be prepared by assigning different weights to each data. (4) or a first regression analysis function for the color data and a second regression analysis function for the texture data are separately generated, and the first value and the texture data, to which the color data is applied to the first regression analysis function, The final skin moisture content may be determined by assigning different weights to the second value applied to the skin.

On the other hand, the computer device may generate a regression analysis function considering various variables. For example, it is possible to generate different regression analysis functions depending on the type of skin area (forehead, ball, jaw, etc.), hardware specifications of the camera, In this case, the user would have to go through a process of entering variables into the computer device.

FIG. 5 shows an example of a procedure for preparing an improved regression analysis function using the calculated skin moisture. The user shoots a face image of a person using a smart device or a general camera (a process). The computer apparatus detects a face region displayed in a square in the source image including the face image (step b). The computer device detects the skin area in the face area (step c). Fig. 5 shows an example in which the computer device detects a specific skin area A set in advance in the face area. Figure 5 shows an example in which a computer device detects a " ball " region. The computer device extracts color data and texture data based on the skin area A (step d). The computer device applies color data and / or texture data to a regression analysis function (e process). The computer device calculates skin moisture from the regression analysis function (step f). An improved regression analysis function is generated using the calculated skin moisture content and a skin moisture DB measured through a moisture meter (step g), and the generated regression analysis function is stored in an improved regression analysis DB. 5 is an example of a process of preparing an improved regression analysis function using the calculated skin moisture. The user shoots a face image of a person using a smart device or a general camera (a process). The computer apparatus detects a face region displayed in a square in the source image including the face image (step b). The computer device detects the skin area in the face area (step c). Fig. 5 shows an example in which the computer device detects a specific skin area A set in advance in the face area. Figure 5 shows an example in which a computer device detects a " ball " region. The computer device extracts color data and texture data based on the skin area A (step d). The computer device applies color data and / or texture data to a regression analysis function (e process). The computer device calculates skin moisture from the regression analysis function (step f). An improved regression analysis function is generated using the calculated skin moisture content and a skin moisture DB measured through a moisture meter (step g), and the generated regression analysis function is stored in an improved regression analysis DB. As described above, the regression analysis function means a regression line or a regression curve. The ear analysis function means a regression line or a regression curve.

6 is an example of a process for calculating improved skin moisture. The user shoots a face image of a person using a smart device or a general camera (a process). The computer apparatus detects a face region displayed in a square in the source image including the face image (step b). The computer device detects the skin area in the face area (step c). Fig. 6 shows an example in which the computer apparatus detects a specific skin area A preset in the face area. Figure 5 shows an example in which a computer device detects a " ball " region. The computer device extracts color data and texture data based on the skin area A (step d). The computer device applies color data and / or texture data to a regression analysis function (e process). The computer device calculates skin moisture from the regression analysis function (step f). The computer predicted skin moisture is applied to an improved regression analysis function (g process). The computer device determines the final skin moisture content by calculating an improved skin moisture content in an improved regression analysis function (step i).

The computer device can calculate a single result using the weighted average of the color data and the texture data in the course of calculating the skin moisture.

The computer device can derive a regression line equation and a regression curve equation using the calculated skin moisture and skin moisture DB. The regression linear equation is as shown in Equation 1,

Where x is the value of the calculated skin moisture. a and b are constants obtained by regression analysis. y represents an improved skin moisture value. The results of applying the actual data may vary with the values of the constants a and b depending on the data used.

Regression curves can also be used to derive a regression curve equation using the calculated skin moisture and skin moisture DB. The regression curve equation is as shown in equation (2)

Where x is the value of the calculated skin moisture. a, b, and c are constants obtained by regression analysis. y represents an improved skin moisture value. The result of applying the actual data may vary in constant a, b or c depending on the data used.

The present embodiment and drawings attached hereto are only a part of the technical idea included in the above-described technology, and it is easy for a person skilled in the art to easily understand the technical idea included in the description of the above- It will be appreciated that variations that may be deduced and specific embodiments are included within the scope of the foregoing description.

50: Smart devices
51: Camera
52: Storage device
53:
54: Output device
81: Camera
85: Computer
91: User terminal
95: Server

Claims (10)

Detecting a skin region of the subject from a source image of the subject;
The computer device extracting color data and texture data of the skin region,
Here, the color data is at least one chrominance component of Cb and Cr in the YCbCr color system, at least one chrominance component of H or S in the HSV color system, or a Co chrominance component in the YCgCo chrominance system,
The texture data is data on contrast, data on dissimilarity, data on homogeneity, data on orientation or data on entropy;
Determining the first skin moisture content by inputting the color data and the texture data into a first regression analysis function provided beforehand by using the relationship between the color data and the texture data and the skin moisture content;
The computer device generates an improved second regression analysis function in the first regression analysis function using the first person's skin moisture content and the skin moisture of the subject measured by the moisture meter at the time of shooting the source image of the subject step; And
Wherein the computer device applies the first skin moisture gradient to the second regression analysis function to determine a final second skin moisture gradient,
The first regression analysis function is generated differently according to the kind of the skin region, the hardware specification of the camera for acquiring the source image of the subject, and the type of the smart device equipped with the camera,
Wherein the first skin moisture content is determined by applying a weighted value to each of the color data and the texture data to the first regression analysis function. delete The method according to claim 1,
Wherein the computer device changes an RGB color of the skin region to another color system and extracts an average value of at least one of a luminance component and a chrominance component of the different color system as the color data. delete delete delete The method according to claim 1,
Wherein the skin region is a specific point of interest set in advance in a user's face region. delete delete delete

Images