WO2015046658A1

WO2015046658A1 - Apparatus and method for measuring reproducibility of tongue diagnosis device

Info

Publication number: WO2015046658A1
Application number: PCT/KR2013/008844
Authority: WO
Inventors: 정창진; 김근호; 전영주
Original assignee: 한국 한의학 연구원
Priority date: 2013-09-24
Filing date: 2013-10-04
Publication date: 2015-04-02
Also published as: CN105764408B; CN105764408A; KR101523843B1; KR20150033807A

Abstract

An apparatus for measuring the reproducibility of a tongue diagnosis device is provided. The apparatus may comprise: a calculating unit which calculates a first parameter from each of a first image and a second image which are photographed by the tongue diagnosis device and a measuring unit which, with respect to the first image and the second image, calculates intra-class correlation coefficients of the first parameter and measures reproducibility of the tongue diagnosis.

Description

Device and Method for Measuring Reproducibility

The present invention relates to an apparatus and a method for measuring tongue reproducibility, and more particularly, to an apparatus and method for quantitatively determining the color and shape reproducibility of a tongue image provided by the tongue is provided.

Seoljin is to diagnose the health of the patient through the tongue. Recently, a snow blower is developed and distributed to assist such a snow blow.

The tongue is a device for taking an image (photograph) of the patient's tongue to derive a diagnosis result according to a predetermined algorithm, and / or to provide to the medical personnel.

By the way, the color or shape of the tongue affects the results of the tongue, the color and shape can be taken differently depending on the position or posture of the patient's tongue. For example, tongue color and geometry may vary due to tongue flexion and shadows.

Since the reproducibility of the image taken by Seoljingi is an important factor in the reliability of Seoljingi, it is necessary to evaluate such reproducibility.

According to one side, the seoljingi reproducibility measuring device, comprising: a calculator for calculating a first parameter from each of the first image and the second image photographed by the seoljingi; And a measurement unit for measuring the reproducibility of the snow picker by calculating a sudden internal correlation coefficient of the first parameter with respect to the first image and the second image.

According to an embodiment, the reproducibility may include at least one of color reproducibility and shape reproducibility of the seoljingi measured using the first image and the second image.

According to another embodiment, the reproducibility is the color reproducibility, and the apparatus may further include a color converter configured to convert color values of the first image and the second image into color values according to a predetermined color space. .

According to another embodiment, the color value according to the predetermined color space may include at least one of a chromaticity value and a brightness value according to the Commission Internationale de l'Eclairage (CIE) color space. .

In example embodiments, the first parameter is calculated for the first image and the second image, and may be at least one of an average of the chromaticity values and an average of the brightness values.

According to another embodiment, the reproducibility is the shape reproducibility, and the first parameter may be a value associated with an object width in a predetermined unit space for the first image and the second image.

According to another embodiment, the reproducibility is the shape reproducibility, the apparatus may further include a feature point extraction unit for extracting at least one feature point from the first image and the second image.

According to an embodiment, the at least one feature point may include at least one of a tongue root point and a tongue tip of a tongue, which are objects included in the first image and the second image. Can be.

According to another embodiment, the first parameter may be any one of angles formed by the at least one feature point.

The display apparatus may further include an image divider configured to divide the first image and the second image into a predetermined number of regions, wherein the first parameter includes the divided first image and the divided second image. Comparisons may be made between regions corresponding to each other between images.

According to an embodiment, the first image and the second image may be images of a tongue, which is an object, to correspond to an image guide grid provided in advance.

According to another aspect, a seoljingi reproducibility measuring method comprising: calculating a first parameter from each of the first image and the second image taken by the seoljingi; And for the first image and the second image, calculating a rapid internal correlation coefficient of the first parameter to measure the reproducibility of the snow picker.

According to an embodiment, the reproducibility may include at least one of color reproducibility and shape reproducibility of the snow picker measured using the first image and the second image.

According to another embodiment, the reproducibility is the color reproducibility, and the method may further include converting color values of the first image and the second image into color values according to a predetermined color space.

According to another embodiment, the reproducibility is the shape reproducibility, and the method may further include extracting at least one feature point from the first image and the second image.

According to another embodiment, the method may further include dividing the first image and the second image into a predetermined number of regions, and wherein the first parameter is between the divided first image and the divided second image. Can be compared for regions corresponding to each other.

According to yet another aspect, there is provided a computer-readable recording medium having recorded thereon a program for performing the method.

1 is a block diagram showing the configuration of a snow duster reproducibility measuring apparatus according to an embodiment.

2 is a flowchart illustrating a flow of a method of measuring snow reproducibility according to an embodiment.

3 illustrates an example of dividing a tongue image into six equal parts to measure color reproducibility according to an exemplary embodiment.

4 is in accordance with another embodiment. Exemplary drawing in which the tongue image is divided into ten horizontal sections to measure color reproducibility.

5 is an exemplary diagram including a boundary portion of a tongue image to measure shape reproducibility, according to an exemplary embodiment.

6 is an exemplary diagram of measuring a side angle of a tongue image to measure shape reproducibility according to another embodiment.

FIG. 7 is an exemplary view of measuring a side angle of a tongue image to measure shape reproducibility according to another embodiment. FIG.

8 is a diagram illustrating an example screen for presenting a guideline for capturing a tongue image, according to an exemplary embodiment.

9 is a graph illustrating a change in the number of rapid internal correlations according to whether a guideline is provided according to an embodiment.

Hereinafter, some embodiments will be described in detail with reference to the accompanying drawings. However, it is not limited or limited by these embodiments. Like reference numerals in the drawings denote like elements.

The terminology used in the following description has been selected as widely used as possible in the present invention in consideration of the functions in the present invention, but may vary according to the intention or custom of the person skilled in the art, the emergence of new technologies and the like.

In addition, in certain cases, there are terms arbitrarily selected by the applicant for the sake of understanding and / or convenience of description, and in this case, detailed meanings thereof will be described in the corresponding description. Therefore, the terms used in the following description should be understood based on the meanings of the terms and the contents throughout the specification, rather than simply the names of the terms.

The seoljingi reproducibility measuring apparatus 100 may include a calculation unit 110, a measurement unit 120, an image divider 130, a color converter 140 and a feature point extractor 150.

The seoljingi reproducibility measuring apparatus 100 may evaluate the reproducibility by analyzing the image photographed by the seoljingi with respect to the color or shape. The captured image may be an image of the tongue of the same patient. At least two captured images may be analyzed for color or shape. In order to check whether an image is reproduced close to the real object, a certain index value for the same part may be compared.

The device for measuring snow reproducibility 100 may be a device for measuring at least one of color reproducibility and shape reproducibility.

Color reproducibility can be determined based on the color value. Color reproducibility can be determined by whether or not a plurality of tongue image color values (color values) taken of the same patient's tongue are not fluidly changed and are within a predetermined error range. Color reproducibility may be determined by calculating color values of the entire tongue image. In addition, color reproducibility may be determined for each region by dividing the tongue image into regions and calculating color values for each region.

For example, the tongue image of the tongue of the first patient may have a first image to a third image. The first to third images may be divided into six equal parts. A part divided into six equal parts may be designated as the first to sixth areas. Color reproducibility may be determined by calculating a correlation coefficient by calculating color values of the first area of the first image, the first area of the second image, and the first area of the third image.

The shape reproducibility can be determined by whether or not a plurality of tongue image ratio values obtained by photographing the tongues of the same patient are not fluidly changed and are within a predetermined error range. The ratio value is a value obtained by calculating the proportion of the tongue in the region including the tongue boundary. Tongue images can be segmented around the tongue boundary. The more regions including the divided tongue boundaries, the higher the accuracy of shape reproducibility measurement.

Shape reproducibility can be determined by whether the plurality of lateral tongue image angle values photographing the tongue of the same patient are not fluidly changed and are within a predetermined error range. The angle value is a value obtained by calculating an angle between the reference line and the feature point on the side of the tongue. The description of the part measuring the angle will be described in detail with reference to FIGS. 6 and 7.

The calculation unit 110 may calculate a parameter from each of the first image and the second image photographed by the seoljingi.

The parameter may be for a color value of the tongue image. An intra class correlation for the color value may be a criterion for determining the color reproducibility of the snow picker.

The parameter may be a ratio value occupied by the tongue of an area including a boundary portion of the tongue image. An intra class correlation with respect to the ratio value may be a criterion for determining shape reproducibility of the snow picker.

The parameter may be a value obtained by measuring a lateral angle in the tongue image. An intra class correlation with respect to the angle value may be a criterion for determining shape reproducibility of the snow picker.

The measurement unit 120 may calculate an intra class correlation of the parameter with respect to the first image and the second image to measure the reproducibility of the snow picker. The closer the emergency correlation coefficient is to 1, the better the reproducibility of the seoljingi can be evaluated.

The image divider 130 may divide the first image and the second image into a predetermined number of regions. When divided into the regions, parameters of regions corresponding to each other may be compared between the divided first image and the divided second image.

The method of dividing by the image divider 130 may correspond to at least one of dividing the first image and the second image horizontally, vertically, and grid. The image divider 130 may divide the region evenly or may divide the region evenly.

The image splitter 130 may segment the tongue image to determine shape reproducibility. The segmented tongue image may have a region including a tongue boundary portion. A ratio value occupied by the tongue in the region including the tongue boundary portion may be calculated. The ratio value can be used as a parameter value.

The color converter 140 may convert color values of the first image and the second image into color values according to a predetermined color space. The color value according to the predetermined color space may include at least one of a chromaticity value and a brightness value according to the Commission Internationale de l'Eclairage (CIE) color space.

At least one of the average of the chromaticity values and the average of the brightness values may correspond to the parameter. The parameter may be calculated for the first image and the second image.

The feature point extractor 150 may extract at least one feature point from the first image and the second image. The feature point may correspond to at least one of a tongue point and tongue point of the tongue which are objects included in the first image and the second image.

An angle value formed by the feature point may be used as a parameter. The rapid internal correlation coefficient for the angle value is calculated, and the rapid internal correlation coefficient may be a reference for determining the form reproducibility of the snow picker.

In operation 201, parameters to be measured may be determined from each of the first image and the second image photographed by the seoljingi. The reproducibility of the seoljingi may include at least one of color reproducibility and shape reproducibility of the seoljingi measured using the first image and the second image. When determining color reproducibility, the parameter may relate to color values. In determining shape reproducibility, the parameter may be a ratio value or lateral tongue angle value occupied by the tongue in the region including the tongue boundary.

In operation 202, when the snow picker reproducibility measurement relates to color reproducibility, color values of the first image and the second image may be converted into color values according to a predetermined color space. The color value according to the predetermined color space may correspond to at least one of chromaticity and lightness values according to the CIE color space. The area divider may divide the first image and the second image into a predetermined number of regions. The calculator 110 may calculate a parameter for at least one of chromaticity and brightness values for each region. The average value for the parameter can be calculated.

In operation 203, when the snow picker reproducibility measurement relates to shape reproducibility, the parameter may be a value associated with an object width in a predetermined unit space for the first image and the second image. The area divider may divide the first image and the second image into a predetermined number of regions. The parameter may be a ratio value occupied by the tongue in the region including the tongue boundary. The calculation unit 110 may calculate the ratio value and obtain an average value of the ratio value for a plurality of images.

In step 204, when the snow duster reproducibility measurement relates to shape reproducibility, at least one feature point may be extracted from the first image and the second image, and an angle value measured from the extracted feature point may be used as a parameter. have. The feature point may include at least one of a tongue point and tongue point of the tongue which are objects included in the first image and the second image. The calculation unit 110 may calculate an angle using at least one of the tongue root and the tongue of the tongue as vertices. An average value of the angle values may be obtained for a plurality of images.

In step 205, the extractor may calculate the rapid internal correlation coefficient using the average value of the parameter value and the parameter value. The extractor may measure the reproducibility of the snow picker by calculating the rapid internal correlation coefficient.

The region dividing unit may divide the tongue image into six equal parts as shown in FIG. 3. The color converter 140 may convert the first to sixth areas into color values. The color value may correspond to at least one of a chromaticity value and a brightness value according to the CIE color space.

The calculation unit 110 may calculate at least one of a chromaticity value and a brightness value as a parameter. The calculator 110 may calculate an average value of at least one of chromaticity values and brightness values of the first region with respect to the plurality of tongue images. The average value may be used to determine the color reproducibility of the first region. The measurement unit 120 may use the average value in the process of calculating the rapid internal correlation coefficient. The measurement unit 120 may determine the color reproducibility of the snow picker for the first region using the rapid internal correlation coefficient as an index.

In the same manner, the calculation unit 110 may calculate at least one of the chromaticity values and the brightness values as parameters, for the second to sixth regions, and calculate the average value, respectively. The measurement unit 120 may use an average value for each area in the process of calculating the rapid internal correlation coefficient for each area. The measurement unit 120 may determine the color reproducibility of the snow picker for the second area to the sixth area using the rapid internal correlation coefficient as an index.

The calculator 110 may calculate the color values of the first to tenth areas as parameters from the first image and the second image. The color value may correspond to at least one of a chroma value and a brightness value.

The measurement unit 120 may calculate the rapid internal correlation coefficient for the color value with respect to the first image and the second image, and measure the color reproducibility of the snow picker.

As illustrated in FIG. 5, the area divider may divide a tongue image. The calculation unit 110 may calculate the ratio of the tongue in the area including the boundary of the tongue as a parameter value in order to measure the shape reproducibility of the tongue isolator. The parameter may be a value associated with the object width in a unit space predetermined for the first image and the second image. The calculation unit 110 may calculate the ratio value of the first to fourth areas. The calculator 110 may calculate an average of ratio values for each region. The measurement unit 120 may calculate the rapid internal correlation coefficient using the average value and the ratio value, and measure the shape reproducibility of the seoljingi.

Calculation unit 110 can calculate the angle of the tongue root (P _root) and, following the end of the tongue (P _tip) line 620 and a vertical axis 610 passing through the tongue root. The angle value can be used as a parameter. The average value of each parameter value for a plurality of images can be obtained.

The measurement unit 120 may calculate the rapid internal correlation coefficient using the average value of the angle value and the angle value. The measurement unit 120 may calculate the rapid internal correlation coefficient to measure the shape reproducibility of the snow picker.

The calculator 110 divides the tongue root P _root and the _tip P into four quarters and calculates a point where the five

lines

710, 720, 730, 740, and 750 meet the tongue boundaries. The angle may be measured using the point where the center line 710 meets the tongue boundary among the five lines. The angle between the meeting point and the center line 710 may be calculated by calculating a point where the second line 720 above the center line meets the tongue boundary. By calculating a point where the tongue line meets the third line 730 below the center line, an angle between the meeting point and the center line 710 may be calculated. The calculation unit 110 can obtain a parameter using the angle value as a parameter. The average value of each parameter value for a plurality of images can be obtained.

When the tongue picker photographs the patient's tongue, the flexion and shadow of the tongue may vary according to the patient's tongue posture. If the flexion and shadow of the tongue is different, the color and geometric information about the tongue may be different.

The tongue may suggest guidelines for the patient to maintain a constant tongue position when photographing the tongue. The guide line can be presented from the front or side. If the patient does not meet the guidelines and does not maintain a constant tongue posture, the tongue may give feedback information to the patient.

According to one embodiment, the feedback information may be a message for inducing the positioning of the tongue accurately in the suggested guide line. The message may be provided in an auditory or visual form including voice. From the message the patient can correctly position the tongue in the tongue of the tongue. If the guideline is lattice shaped, the patient may be positioned to fit the edge of the tongue to fit inside the edge of the lattice shaped guideline.

On the other hand, the grid-shaped guide line is only one embodiment, the shape and / or shape of the guide line in any other shape and / or shape that can guide the patient to position the tongue accurately and reproducibly May be provided.

According to one embodiment, the guideline may be presented at front 810 or side 820. If the guideline is presented in front, the patient may be positioned about the tongue shape in the grid guideline 811 for color reproducibility. The patient may allow the boundary of the tongue to be located inside the guide line 811 while looking at the guide line 811. If the guideline is presented laterally, the patient may position the tongue at the lattice guide line 821 with the tongue root and tongue tip for form reproducibility. The patient may look at the guide line 821 so that the boundary of the tongue is positioned inside the guide line 821.

According to one embodiment, in addition to inducing the patient to accurately position the tongue in a predetermined area of the guide grid, it is also possible to automatically photograph the tongue-collected image at the moment the correct position is secured.

According to one embodiment, when the guideline is not presented to the tongue isolator, when the front guideline is presented only to the tongue, and when the front and side guideline is presented to the tongue is divided into three groups to observe the change in the emergency correlation coefficient Can be.

As shown in FIG. 9, when no guideline was presented to the snow picker, the sudden correlation coefficient was calculated to be low in most areas. In the case of presenting both front and side guideline in the snow washer, the rapid internal correlation coefficient was higher than in the case of only the front guideline.

The apparatus described above may be implemented as a hardware component, a software component, and / or a combination of hardware components and software components. For example, the devices and components described in the embodiments may be, for example, processors, controllers, arithmetic logic units (ALUs), digital signal processors, microcomputers, field programmable arrays (FPAs), It may be implemented using one or more general purpose or special purpose computers, such as a programmable logic unit (PLU), microprocessor, or any other device capable of executing and responding to instructions. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. The processing device may also access, store, manipulate, process, and generate data in response to the execution of the software. For convenience of explanation, one processing device may be described as being used, but one of ordinary skill in the art will appreciate that the processing device includes a plurality of processing elements and / or a plurality of types of processing elements. It can be seen that it may include. For example, the processing device may include a plurality of processors or one processor and one controller. In addition, other processing configurations are possible, such as parallel processors.

The software may include a computer program, code, instructions, or a combination of one or more of the above, and configure the processing device to operate as desired, or process it independently or collectively. You can command the device. Software and / or data may be any type of machine, component, physical device, virtual equipment, computer storage medium or device in order to be interpreted by or to provide instructions or data to the processing device. Or may be permanently or temporarily embodied in a signal wave to be transmitted. The software may be distributed over networked computer systems so that they may be stored or executed in a distributed manner. Software and data may be stored on one or more computer readable recording media.

The method according to the embodiment may be embodied in the form of program instructions that can be executed by various computer means and recorded in a computer readable medium. The computer readable medium may include program instructions, data files, data structures, etc. alone or in combination. The program instructions recorded on the media may be those specially designed and constructed for the purposes of the embodiments, or they may be of the kind well-known and available to those having skill in the computer software arts. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tape, optical media such as CD-ROMs, DVDs, and magnetic disks, such as floppy disks. Magneto-optical media, and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine code generated by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like. The hardware device described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

Although the embodiments have been described by the limited embodiments and the drawings as described above, various modifications and variations are possible to those skilled in the art from the above description. For example, the described techniques may be performed in a different order than the described method, and / or components of the described systems, structures, devices, circuits, etc. may be combined or combined in a different form than the described method, or other components. Or even if replaced or substituted by equivalents, an appropriate result can be achieved.

Therefore, the scope of the present invention should not be limited to the described embodiments, but should be determined not only by the claims below but also by the equivalents of the claims.

Claims

In the snow duster reproducibility measuring device,

A calculator configured to calculate a first parameter from each of the first image and the second image photographed by the seoljingi; And

A measurement unit for measuring the reproducibility of the snow isolator by calculating the rapid internal correlation coefficient of the first parameter for the first image and the second image

Device comprising a.
The method of claim 1,

The reproducibility,

And at least one of color reproducibility and shape reproducibility of the seoljingi measured using the first image and the second image.
The method of claim 2,

The reproducibility is the color reproducibility,

The device,

A color converter configured to convert color values of the first image and the second image into color values according to a predetermined color space

Device further comprising.
The method of claim 3,

The color value according to the predetermined color space includes at least one of a chromaticity value and a brightness value according to a Commission Internationale de l'Eclairage (CIE) color space.
The method of claim 4, wherein

The first parameter is,

The device is calculated for the first image and the second image, and is at least one of an average of the chromaticity values and an average of the brightness values.
The method of claim 2,

The reproducibility is the shape reproducibility,

The first parameter is,

And a value associated with an object width in a predetermined unit space for the first image and the second image.
The method of claim 2,

The reproducibility is the shape reproducibility,

The device,

Feature point extraction unit for extracting at least one feature point from the first image and the second image

Device further comprising.
The method of claim 7, wherein

The at least one feature point is,

And at least one of a tongue root point and a tongue tip of a tongue, which are objects included in the first image and the second image.
The method of claim 8,

And the first parameter is any one of the angles formed by the at least one feature point.
The method of claim 1,

An image divider dividing the first image and the second image into a predetermined number of regions

More,

And the first parameter is compared with respect to a region corresponding to each other between the divided first image and the divided second image.
The method of claim 1,

And the first image and the second image are images of a tongue which is an object so as to correspond to an image guide grid provided in advance.
In the method of measuring snow reproducibility,

Calculating a first parameter from each of the first image and the second image photographed by the snow picker; And

Measuring a reproducibility of the snow picker by calculating a rapid internal correlation coefficient of the first parameter with respect to the first image and the second image;

How to include.
The method of claim 12,

And the reproducibility comprises at least one of color reproducibility and shape reproducibility of the snow catcher measured using the first image and the second image.
The method of claim 13,

The reproducibility is the color reproducibility,

The method,

Converting color values of the first image and the second image into color values according to a predetermined color space;

How to include more.
The method of claim 14,

The color value according to the predetermined color space includes at least one of a chromaticity value and a brightness value according to a Commission Internationale de l'Eclairage (CIE) color space.
The method of claim 15,

The first parameter is,

And calculated for the first image and the second image, the method being at least one of an average of the chromaticity values and an average of the brightness values.
The method of claim 13,

The reproducibility is the shape reproducibility,

The first parameter is,

And a value associated with an object width in a predetermined unit space for the first image and the second image.
The method of claim 13,

The reproducibility is the shape reproducibility,

The method,

Extracting at least one feature point from the first image and the second image

How to include more.
The method of claim 18,

The at least one feature point is,

And at least one of a tongue root point and a tongue tip of a tongue, which are objects included in the first image and the second image.
The method of claim 19,

The first parameter is any one of the angles formed by the at least one feature point.
The method of claim 12,

Dividing the first image and the second image into a predetermined number of regions

More,

And the first parameter is compared with respect to a region corresponding to each other between the divided first image and the divided second image.
The method of claim 12,

And the first image and the second image are images of a tongue which is an object so as to correspond to an image guide grid provided in advance.
A computer-readable recording medium having recorded thereon a program for performing the method of claim 12.