KR102225426B1 - Method and device for estimating amount of tongue coating and system thereof - Google Patents

Abstract

The present disclosure relates to a method and apparatus for estimating the amount of tongue tongue, and a system thereof, wherein the method of estimating the amount of tongue tongue includes obtaining image data captured using an ultraviolet light source, and extracting a tongue region from the image data. And determining an amount of tongue tongue based on the ultraviolet fluorescence state of the tongue region, and determining an ultraviolet fluorescence state of the tongue region.

Description

Method and apparatus for estimating the amount of snow formation, and the system thereof {METHOD AND DEVICE FOR ESTIMATING AMOUNT OF TONGUE COATING AND SYSTEM THEREOF}

The present disclosure relates to a method and apparatus for estimating the amount of tongue tongue, and to a system thereof, and specifically, to determine the ultraviolet fluorescence state of the tongue area based on image data of the tongue irradiated with an ultraviolet light source, and the ultraviolet fluorescence state of the tongue area. It relates to a method and apparatus for estimating the amount of snow formation, and a system thereof.

Seoltae is a material that covers the back of the tongue in a moss shape, and is generally called "white tae". There is a difference in the amount of snow flakes for each person, some people have a lot of snow flakes, and some people have a small amount of snow flakes. Seoltae is a complex material consisting of dead and fallen oral epithelial cells, microbes in the oral cavity including bacteria, blood components bleeding from periodontal tissues, white blood cells, and food waste. Since tongues continue to be made in living tissues and are continuously removed by oral activity and secreted saliva, tongues tend to continue to maintain a certain amount per person, decreasing and then elongating.

In traditional East Asian medicine, including oriental medicine, the amount of seoltae has been used as an important observational index when judging the overall health status of a patient. On the other hand, seoltae is the biggest cause of true bad breath (breath). Therefore, the amount of snowflake is also used as an important index in evaluating the condition of bad breath.

Until now, various methods have been suggested to evaluate the amount of snow formation, but the methods have not been sufficiently reliable and accurate. The methods that have been used to evaluate the amount of snow formation so far have been published in 2018, 「Kim SR, Nam D. Reliability, Accuracy, and Use Frequency of Evaluation Methods for Amount of Tongue Coating. Chin J Integr Med. 2018:1-8.

Against this background, the present disclosure intends to propose an objective method and apparatus for measuring snow content with sufficient reliability and accuracy.

The present disclosure conceived in the above-described task, in one aspect, relates to a method of estimating the amount of tongue, the method of estimating the amount of tongue, the step of obtaining image data captured using an ultraviolet light source And extracting the tongue region from the image data, determining an ultraviolet fluorescence state of the tongue region, and determining an amount of tongue based on the ultraviolet fluorescence state of the tongue region.

In another aspect, the present disclosure relates to an apparatus for estimating the amount of tongue, wherein the device for estimating the amount of tongue is an image data acquisition unit that acquires image data captured using an ultraviolet light source, and a tongue region from the image data. And a region extracting unit for extracting,, a fluorescence state determination unit for determining an ultraviolet fluorescence state of the tongue region, and a tongue content determination unit for determining an amount of tongue tongue based on the ultraviolet fluorescence state of the tongue region.

In yet another aspect, the present disclosure relates to a system for estimating the amount of tongue, the system for estimating the amount of tongue, an imaging device for imaging the back of the tongue using an ultraviolet light source, and an image captured by the imaging device. And a tongue diagnosis apparatus for acquiring data, extracting a tongue region from image data, determining an ultraviolet fluorescence state of the tongue region, and determining an amount of tongue tongue based on the ultraviolet fluorescence state of the tongue region.

As described above, according to the present disclosure, it is possible to provide an objective method of measuring the amount of tongue tongue with sufficient reliability and accuracy without subjective judgment of the observer when determining the amount of tongue tongue.

1 and 2 are diagrams showing the configuration of a system for estimating the amount of tongue tongue according to an embodiment of the present disclosure.
3 is a view showing a light source included in the system for estimating the amount of tongue according to an embodiment of the present disclosure.
4 is a diagram showing the configuration of an apparatus for estimating the amount of tongue debris according to an embodiment of the present disclosure.
5 is image data of a tongue captured using a visible light source.
6 is image data of a tongue imaged using a near-ultraviolet light source according to an embodiment of the present disclosure.
7 to 9 are diagrams illustrating a process of extracting a tongue region from image data of the tongue according to an embodiment of the present disclosure.
10 is a diagram illustrating color information of a tongue region extracted according to an embodiment of the present disclosure.
11 is a scatter diagram between the amount of mCV and tongue according to an embodiment of the present disclosure.
12 is a graph showing average autofluorescence spectra acquired at different locations on the oral mucosa.
13 is a flowchart illustrating a method of estimating the amount of tongue tongue according to an embodiment of the present disclosure.

Hereinafter, some embodiments of the present disclosure will be described in detail through exemplary drawings. In describing the constituent elements of the present disclosure, terms such as first, second, A, B, (a), and (b) may be used. These terms are for distinguishing the constituent element from other constituent elements, and the nature, order, or order of the constituent element is not limited by the term. When a component is described as being "connected", "coupled" or "connected" to another component, the component may be directly connected or connected to that other component, but another component between each component It will be understood that elements may be “connected”, “coupled” or “connected”.

The present disclosure discloses a method and apparatus for estimating the amount of tongue tongue, and a system for the same.

There are four methods for evaluating the amount of tongue: ① Intuitive method by observing the tongue by the doctor with the naked eye, ② By observing the tongue with the naked eye according to the defined criteria. The method of scoring (specificative method), ③ The method of directly scraping the tongue with a scraper and then weighing the tongue (weighting tongue coating method), ④ Taking a picture of the tongue and analyzing the picture of the tongue. (computerized method).

Among these methods, two methods of observing the tongue with the naked eye are the ones that depend on the subjectivity or experience of the evaluator, so the biggest drawback is that the accuracy and reliability are low. The method of measuring the weight of the tongue is the most direct method, but it can cause nausea in the patient during the process of scratching the tongue, and in severe cases, the tongue may bleed. In addition, there may be a large difference in the result value depending on the degree and range of scratching the tongue, so high proficiency of the evaluator is required. Recently, as a method of analyzing tongue pictures has been proposed, studies on this method have been actively conducted.

In the conventional tongue photo analysis method, a photo of the tongue taken under visible light illumination was used (a method, system and recording medium of tongue analysis through quantification of evaluation indexes of the tongue image. Patent Registration No. 10-1551814). This method focuses on the fact that the tongue is red, but the tongue is not red, and the tongue is white or light yellowish brown. Specifically, the tongue body area that shows a certain degree of red color in the tongue photograph is defined as the tongue body area, and the area that does not show red color is defined as the tongue coating area. This is a method of calculating the ratio of the area to the snow area. This method is an objective analysis method based on image technology, and it can show a high degree of agreement between the visual evaluation method and the results. However, the correlation with the method of measuring tongue weight is low (Pearson correlation coefficient r = 0.44, Kim J, Han G, Ko SJ, et al. Tongue diagnosis system for quantitative assessment of tongue coating in patients with functional dyspepsia: a clinical trial.J Ethnopharmacol. 2014;155(1):709-713.), the downside is that it does not accurately reflect the actual amount of tongue.

In order to overcome these drawbacks, the present disclosure proposes a method different from the conventional method using visible light illumination. Since seoltae is a combination of a large amount of microorganisms and blood metabolites, it has the property of fluorescing when exposed to near ultraviolet rays. Microorganisms in seoltae absorb near ultraviolet rays and then mainly emit green fluorescence, and blood metabolites (phorphyrin) emit red fluorescence. Therefore, by using this fluorescence phenomenon, the amount of tongue can be estimated and evaluated. When there are many tongues, the intensity of fluorescence increases, and when there are few tongues, the intensity of fluorescence decreases.

Therefore, the present disclosure is to investigate the correlation between the thickness of the tongue and ultraviolet fluorescence, and propose a method and apparatus for evaluating the amount of tongue using a computerized tongue image acquisition system (CTIS). . That is, the present disclosure proposes a method and an apparatus for estimating the amount of tongue by using the ultraviolet autofluorescence phenomenon occurring in the tongue.

1 and 2 are diagrams showing the configuration of a system for estimating the amount of tongue tongue according to an embodiment of the present disclosure.

Referring to FIG. 1, the system 100 for estimating the amount of tongue tongue according to the present disclosure acquires an imaging device 110 for imaging the back of the tongue using an ultraviolet light source, and image data captured by the imaging device. And a tongue diagnosis apparatus 120 that extracts the tongue region from the image data, determines an ultraviolet fluorescence state of the tongue region, and determines an amount of tongue tongue based on the ultraviolet fluorescence state of the tongue region.

The system 100 for estimating the amount of tongue tongue of FIG. 1 may further include components illustrated in FIG. 2. Referring to FIG. 2, the system for estimating the amount of tongue is a face contact part 210, a light path 220, a diffusion plate 230, a light source part 240, a light source control part 250, an image pickup part 260, and It includes an obsolete part 270 and an output part 280.

The face contact unit 210 is a device that provides an environment in which the tongue to be imaged can be imaged by being irradiated by the light source unit 240 of the system of the present disclosure in an environment where external light is shielded, and the light path 220 and the diffusion plate Reference numeral 230 is a device that uniformly irradiates the light irradiated from the light source unit 240 onto a subject (tongue) to be imaged. The light source unit 240 may include one or more light sources. For example, the light source unit 240 may include one or more near-ultraviolet light sources and/or one or more visible light sources. In one example, one or more light sources may be arranged surrounding the subject so as to irradiate toward the subject to be imaged.

3 is a diagram illustrating a light source unit included in a system for estimating an amount of snow condition according to an embodiment of the present disclosure. Referring to FIG. 3, the light source unit 240 includes one or more near-ultraviolet light sources and one or more visible light sources, for example, one or more near-ultraviolet and/or visible light LED lamps to irradiate the tongue (snow quality) to be imaged. Snow quality) can be arranged in a concentric circle.

The light source control unit 250 may control overall operations of the light source unit 240, such as light intensity of the light source unit 240, the number of irradiated lights, and on/off.

The imaging device 110 of FIG. 1 or the imaging unit 260 of FIG. 2 includes one or more image sensors, and may capture an image of a tongue using the image sensor. The image sensor may mean a device that converts light (image information) received through a camera lens into an electrical digital signal. For example, the image sensor may mean a charge coupled device (CCD) image sensor that directly transmits an electronic signal. Alternatively, the image sensor may mean a CMOS (Complementary Metal Oxide Semiconductor) image sensor that converts a signal into a voltage form and transmits it.

Since the image information captured from the image sensor is composed of image data, it may mean image data captured from the image sensor. Hereinafter, in the present disclosure, image information captured from an image sensor means image data captured from an image sensor. The image data captured by the image sensor may be generated in, for example, one of a raw format of AVI, MPEG-4, H.264, DivX, and JPEG, and a processor or a device in the imaging device 110 Can be processed by the processor within.

The tongue diaphragm 120 of FIG. 1 or the tongue diaphragm 270 of FIG. 2 acquires image data captured by the imaging device, extracts the tongue area from the image data, determines the ultraviolet fluorescence state of the tongue area, and The amount of tongue can be determined based on the ultraviolet fluorescence state of the region. The tongue diagnosis device 120 of FIG. 1 or the tongue diagnosis unit 270 of FIG. 2 may correspond to the device for estimating the amount of tongue tongue according to the present disclosure. For a detailed description of the tongue diaphragm 120 of FIG. 1 and the tongue diaphragm 270 of FIG. 2, the description of the device for estimating the amount of tongue tongue is referred to below.

The output unit 280 is a device for estimating the amount of tongue tongue and outputting the estimated amount of tongue tongue by the tongue diagnosis unit 270. The preliminary output unit 280 includes, for example, a monitor, a display unit, or a device through which the user can see the data processed by the tongue diagnosis unit 270 with the naked eye.

4 is a diagram showing the configuration of an apparatus for estimating the amount of tongue debris according to an embodiment of the present disclosure.

Referring to FIG. 4, the apparatus 400 for estimating the amount of tongue may include an image data acquisition unit 410 for obtaining image data captured using an ultraviolet light source, and an area extraction unit for extracting a tongue region from the image data ( 420), a fluorescence state determination unit 430 for determining an ultraviolet fluorescence state of the tongue region, and a tongue content determination unit 440 for determining an amount of tongue tongue based on the ultraviolet fluorescence state of the tongue region.

Specifically, the image data acquisition unit 410 of the apparatus 400 for estimating the amount of snow condition acquires image data captured using an ultraviolet light source.

In an embodiment, the image data may be image data obtained by photographing a tongue (snow quality) using an ultraviolet light source in an environment where external light is shielded.

In an embodiment, the image data may be image data of the tongue imaged using one or more near-ultraviolet light sources that irradiate the tongue. As an example, one or more near-ultraviolet light sources, such as one or more near-ultraviolet LED lamps, may be arranged surrounding the tongue (snow quality) to irradiate toward the tongue (snow quality) to be imaged. For example, one or more light sources may be arranged in a concentric circle around a tongue (snow quality) to be imaged.

After obtaining the image data from the imaging device, the apparatus 400 for estimating the amount of tongue can analyze the tongue based on the image data acquired under near ultraviolet rays. Specifically, the region extracting unit 420 of the apparatus 400 for estimating the amount of tongue tongue extracts the tongue region from the image data. Further, the fluorescence state determination unit 430 determines an ultraviolet fluorescence state of the tongue region based on image data acquired under near ultraviolet rays, and the tongue content determination unit 440 determines the amount of tongue tongue based on the ultraviolet fluorescence state of the tongue region. Decide.

First, the region extracting unit 420 extracts a tongue region from the acquired image data.

In an embodiment, the region extracting unit 420 may divide the tongue region and the background region from the image data, and extract the tongue region. Here, the tongue region refers to a region to which the tongue including tongue tongue belongs, and the background region refers to a region that does not include the tongue.

In a general tongue diagnosis method, image data of the tongue captured using a visible light source is used, like the image data shown in FIG. 5. 5 shows an image of the tongue taken under visible light illumination, such as white LED illumination (LWH5000, Luxpia, Korea). Here, the white LED illumination has a diameter of 5 mm and a double peak wavelength of 470 nm and 580 nm. Based on the image as shown in FIG. 5, a method of calculating the proportion of the tongue area occupied by the tongue area is mainly used. However, this method does not accurately reflect the actual amount of snow formation.

The present disclosure proposes a method of using near-ultraviolet illumination instead of conventional visible light illumination in order to overcome these drawbacks. 6 is an image data of a tongue imaged using a near-ultraviolet light source, for example, near-ultraviolet LED lighting (T5F36, Seoul Optodevice, Korea) according to an embodiment of the present disclosure. Here, near-ultraviolet LED lighting has a direct view of 5mm and a peak wavelength of 365nm.

Tongue is a combination of bacteria, epithelial cells peeling from the oral mucosa, blood metabolites such as porphyrins, white blood cells in the periodontal sac, and other nutrients. Therefore, when near-ultraviolet rays are irradiated on the tongue, the tongue area (the area containing the tongue in the tongue (snow quality) area) has a characteristic of fluorescing. The fluorescence of these tongues is caused by the presence of bacteria and porphyrins. Depending on the type of oral bacteria, more red or green fluorescence may be expressed. Green fluorescence intensity is stronger than that of red fluorescence in S. oralis, S. salivarius, S. mutans, F. nucleatum, and S. sobrinus, and red fluorescence intensity is P. intermedia, A. naeslundi, A. Israelii, L. fermentans, L. rhamnosus and L. casei appear more strongly in the same species.

If staphylococcus and streptococci make up up to 90% of the microbes in the tongue, this bacterial fluorescence is related to metabolites such as AAA + NA and fryptophan, so the porphyrin produced by the degradation of Hgb by the microbes is about 365. Red fluorescence is generated on the back side of the tongue under the ultraviolet rays of nm.

Therefore, by using this fluorescence phenomenon, the amount of tongue can be estimated and evaluated. When there are many tongues, the intensity of fluorescence increases, and when there are few tongues, the intensity of fluorescence decreases.

In an embodiment, the region extracting unit 420 may extract the tongue region using the outline of the tongue. Specifically, a tongue region may be selected from image data through drag of a mouse, and color information on the tongue region may be analyzed. Here, the area of the tongue is an area of interest in which the user wants to analyze color information.

In this regard, it will be described with reference to FIGS. 7 to 10. 7 to 10 are views for explaining a method of extracting a tongue region from image data of the tongue and analyzing the tongue region according to an embodiment of the present disclosure.

Referring to FIG. 7, the region extracting unit 420 may generate a layer on the acquired image data and display M nodes on the generated layer. Where M is a natural number greater than 1. In addition, the tongue region can be extracted or selected using M nodes. The M nodes can be connected to each other to form a closed figure.

In an embodiment, the region extracting unit 420 may extract or select a tongue region from image data using a drag-and-drop operation. Referring to FIG. 8, by dragging-and-dropping M nodes displayed on the image data as shown in FIG. 7, the positions of the M nodes are adjusted to be located on the outline of the tongue area, and according to the positions of the M nodes. The tongue area can be determined. In addition, the apparatus 400 for estimating the amount of tongue tongue may analyze color information on the tongue area.

An image captured under near ultraviolet rays is a combination image of RGB channels. Accordingly, the image excluding the background region can be divided into three separate channels, that is, red (R), green (G), and blue (B). Here, a channel is a gray scale image made with only one of the basic colors. As known to those of ordinary skill in the art, the RGB color model is a method of expressing colors consisting of the three primary colors of light, red (R), green (G), and blue (B).

In an embodiment, the region extracting unit 420 may erase the remaining regions except for the extracted tongue region, that is, the background region black. The region extracting unit 420 may extract a tongue region obtained by separating the background from the obtained image.

In an embodiment, the region extracting unit 420 may extract the tongue region from the extracted tongue region by using a difference in a* value of the CIE-LAB color model. The CIE-Lab color model is a color system re-established in 1976 by an international standard color measurement organization called CIE. In Lab color, L stands for luminosity, a combination of green to red, and b combination of yellow. It means the complementary color of blue.

In an embodiment, the region extracting unit 420 may distinguish between a fluorescence state of the tongue region and a fluorescence state of the tongue region. It has the lowest fluorescence intensity at the lateral border of the tongue than other parts of the oral cavity. Although the tongue (snow quality) is covered over the entire back, the tongue is mostly distributed in the center or root of the tongue, and less in the tip or lateral border of the tongue. Accordingly, it is possible to distinguish between the fluorescence state of the tongue region in which a large amount of tongue tongue is distributed and the fluorescence state of the tongue region in which the tongue tongue is less distributed. Here, an area in which a lot of tongue tongue is distributed can be regarded as a tongue area, and an area where there is a small amount of tongue tongue can be regarded as a tongue area. Whether the tongue is more or less distributed can be determined based on the value of the fluorescence state.

As described above, the image captured under near ultraviolet rays is a combination image of RGB channels, and the image excluding the background area is divided into three separate channels, namely, red (R), green (G), and blue (B). I can. The mean color value (mCV) of each color channel may be calculated as an average gray scale value of pixels in the tongue area. The brightness channel of the HSL color model can also be separated from the selected tongue region, and the mCV of the brightness channel can be calculated according to the following brightness equation:

In Equation 1, max(R, G, B) and min(R, G, B) represent the maximum and minimum values in parentheses, respectively. R, G and B represent the values of R, B and B of each pixel in the region of the tongue.

Considering that the back of the tongue emits green and red fluorescence under near ultraviolet rays, and the blue image sensor records reflected near ultraviolet rays as well as fluorescence, the brightness of the mCV of the brightness channel is modified to be an indicator of ultraviolet fluorescence of the tongue. Remove the blue value from the value definition.

Thus, the definition of modified lightness is expressed as follows:

The mCV of the corrected brightness value may be calculated by Equation 2 above. Here, the corrected brightness value may be expressed as an ultraviolet fluorescence brightness value.

10 is a diagram illustrating color information of a tongue region extracted according to an embodiment of the present disclosure. The extracted red (R), green (G), and blue (B) channels of the tongue region may be calculated as average gray scale values of pixels in the tongue region as shown in FIG. 10. In addition, the corrected brightness value L of the extracted tongue region may be calculated by an average of the red (R) and green (G) channels as shown in FIG. 10 and the above-described method.

The mCV of the G, B, brightness values, and the corrected brightness values have a larger value for the tongue image with a large amount of tongue tongue than for the tongue image with a small amount of tongue tongue. On the other hand, in the red (R) channel, there is no significant difference between the image of the tongue with a small amount of tongue and the image of the tongue with a large amount of tongue, but there is a big difference between the image of the tongue with less amount of tongue and the image of the tongue without tongue. . That is, the R channel is more sensitive when the tongue is less, and the other channel is more sensitive when the tongue is wide. Therefore, the apparatus 400 for estimating the amount of snow flakes estimates the amount of snow flakes by assigning a weight to the R channel when discriminating when there is little or no snow flakes. You can estimate the amount of snow formation.

And the relationship between the mCV of the modified brightness value and the amount of snow can be described by a log-transformed linear regression model and a logistic curve modeled by a nonlinear regression model. I can.

Here, the log-transformed linear regression model is expressed by the following equation:

And the nonlinear regression model is expressed by the following equation:

In the two equations, K represents the maximum possible WWTC value, β ₀ and β ₁ represent the intercept and regression coefficients in logarithmic-transformed linear regression, respectively, and ε is an arbitrary error value. Here, WWTC (wet weight of tongue coating) indicates the weight of tongue.

To measure the fit of each model, the mean squared error (MSE) is applied according to the following formula:

와

는 각각 추정된 모델에 기초한 관찰 WWTC와 예측 WWTC를 나타낸다. n과 p는 각각 모델에서 추정된 샘플 사이즈와 파라미터의 수를 나타낸다. 비선형 회귀는 대수 변환된 회귀보다 작은 MSE를 가진다. 즉, 수정된 명도 값의 mCV에 대하여 WWTC는 다음의 수식에 의해 추정될 수 있다:here

Wow

Represents the observed WWTC and the predicted WWTC based on the estimated model, respectively. n and p represent the estimated sample size and number of parameters in the model, respectively. Nonlinear regression has a smaller MSE than logarithmic transformed regression. That is, for mCV of the corrected brightness value, the WWTC can be estimated by the following equation:

It should be noted that the constant value in the specific estimation equation may change depending on the application environment and state, and the estimation equation may be expressed differently in various functional forms.

11 is a scatter diagram between the amount of mCV and tongue according to an embodiment of the present disclosure. 11 shows the amount of tongue tongue according to mCV of the corrected brightness value in each regression model. 12 is a graph showing average autofluorescence spectra acquired at different locations on the oral mucosa. Referring to FIG. 12, the graph of FIG. 12 is an autofluorescence spectrum of a hard palate, a cheek mucosa, a vermilion border of the lip, and a dorsal side of the tongue. Shows. Here, the horizontal axis of the fluorescence spectrum represents the range of wavelengths detected by each of R, G, and B of the image sensor. Looking at the measured autofluorescence spectrum 810 for the back of the tongue, it can be seen that peaks are at about 500-520 nm (green) and about 700 nm (red). That is, the wavelength of the first peak is about 520 nm (green), and the wavelength of the second peak is about 636 nm (red). Therefore, the apparatus for estimating the amount of tongue can estimate the amount of tongue by using information on the red and green pixels in the tongue area.

In one embodiment, the apparatus 400 for estimating the amount of snow flakes, in order to ensure reliability in estimating the amount of snow flakes, after a predetermined period of time, the image data acquisition unit 410 and the region extraction unit 420 ), the amount of snow tongue may be determined by performing the operation of the fluorescence state determination unit 430 and the snow tongue amount determination unit 440. For example, the image data acquisition unit 410 re-acquires the image data captured by using the ultraviolet light source at a point in time when a predetermined time has elapsed after the previous image data, and the area extracting unit 420 receives the predetermined time. The tongue region is extracted from the image data at the point in time, the fluorescence state determination unit 430 determines the ultraviolet fluorescence state of the tongue region, and the tongue amount determination unit 440 is based on the ultraviolet fluorescence state of the tongue region. You can determine the amount.

In addition, the snow tongue amount determination unit 440 of the apparatus 400 for estimating the amount of snow tongue determines the amount of snow tongue determined based on the previously acquired image data and the snow condition determined based on the image data at a point in time when a predetermined time has elapsed. Using the amount of can determine the amount of final tongue.

For example, the snow tongue amount determination unit 440 calculates the average of the amount of snow tongue determined based on the previously acquired image data and the amount of snow tongue determined based on the image data at a point in time when a predetermined time has elapsed. It can be determined by quantity.

In another embodiment, the snow tongue amount determination unit 440 may perform reliability evaluation of the determined amount of snow tongue. Specifically, the tongue amount determination unit 440 may calculate intraclass correlation coefficients (ICCs) of the calculated mCV value and the ratio occupied by the tongue area in the entire tongue area.

In one embodiment, the amount of snow tongue determining unit 440 may classify the amount of snow paste into cows, baktae, and posteriors based on the determined amount of tongues.

According to the apparatus for estimating the amount of tongue, it is possible to provide an objective method of measuring the amount of tongue that has sufficient reliability and accuracy without subjective judgment of an observer when determining the amount of tongue tongue.

13 is a flowchart illustrating a method of estimating the amount of tongue tongue according to an embodiment of the present disclosure.

Referring to FIG. 13, in the method of estimating the amount of tongue, the image data captured using an ultraviolet light source is obtained (S1310), the tongue region is extracted from the image data (S1320), and the ultraviolet fluorescence state of the tongue region is determined. After determining (S1330), the amount of tongue tongue is determined based on the ultraviolet fluorescence state of the tongue region (S1340).

Specifically, in the step of acquiring image data (S1310), the snowball device acquires image data captured using an ultraviolet light source.

In an embodiment, the image data may be image data obtained by photographing a tongue (snow quality) using an ultraviolet light source in an environment where external light is shielded.

In an embodiment, the image data may be image data of the tongue imaged using one or more near-ultraviolet light sources that irradiate the tongue. As an example, one or more near-ultraviolet light sources, such as one or more near-ultraviolet LED lamps, may be arranged surrounding the tongue (snow quality) to irradiate toward the tongue (snow quality) to be imaged. For example, one or more light sources may be arranged in a concentric circle around a tongue (snow quality) to be imaged.

After obtaining the image data from the imaging device, the apparatus 400 for estimating the amount of tongue can analyze the tongue based on the image data acquired under near ultraviolet rays. Specifically, the tongue tongue device extracts a tongue region from image data. In addition, the tongue diagnosis apparatus determines an ultraviolet fluorescence state of the tongue region based on image data acquired under near ultraviolet rays, and determines the amount of tongue tongue based on the ultraviolet fluorescence state of the tongue region.

First, the tongue device extracts the tongue area from the acquired image data.

In an embodiment, the tongue diagnosis apparatus may divide the tongue region and the background region from the image data, and extract the tongue region. Here, the tongue region refers to a region to which the tongue including tongue tongue belongs, and the background region refers to a region that does not include the tongue.

In an embodiment, the tongue diagnosis apparatus may extract a tongue region using an outline of the tongue. Specifically, a tongue region may be selected from image data through drag of a mouse, and color information on the tongue region may be analyzed. Here, the area of the tongue is an area of interest in which the user wants to analyze color information.

Specifically, the seoljin apparatus may create a layer on the acquired image data and display M nodes on the generated layer. Where M is a natural number greater than 1. In addition, the tongue region can be extracted or selected using M nodes. The M nodes can be connected to each other to form a closed figure.

In addition, the tongue diagnosis apparatus may extract or select a tongue region from image data using a drag-and-drop operation. By dragging-and-dropping the M nodes displayed on the image data, the positions of the M nodes are adjusted to be located on the outline of the tongue region, and the tongue region may be determined according to the positions of the M nodes. In addition, the tongue diagnosis device may analyze color information on the tongue area.

The tongue diagnosis device may erase the rest area except for the extracted tongue area, that is, the background area black. The tongue diagnosis apparatus may extract a tongue region obtained by separating the background from the acquired image.

In one embodiment, the tongue (snow quality) device may extract the tongue (snow quality) region using a difference in a* value of the CIE-LAB color model. The CIE-Lab color model is a color system re-established in 1976 by an international standard color measurement organization called CIE. In Lab color, L stands for luminosity, a combination of green to red, and b combination of yellow. It means the complementary color of blue.

In an embodiment, the tongue tongue apparatus may distinguish between a fluorescent state of the tongue region and a fluorescent state of the tongue region. It has the lowest fluorescence intensity at the lateral border of the tongue than other parts of the oral cavity. Even if the tongue (snow quality) is covered with the entire back, the tongue is mostly distributed in the center or root of the tongue, and less in the tip or lateral border of the tongue. Accordingly, it is possible to distinguish between the fluorescence state of the tongue region in which a large amount of tongue tongue is distributed and the fluorescence state of the tongue region in which the tongue tongue is less distributed. Here, an area in which a lot of tongue tongue is distributed can be regarded as a tongue area, and an area where there is a small amount of tongue tongue can be regarded as a tongue area. Whether the tongue is more or less distributed can be determined based on the value of the fluorescence state.

As described above, the seoljin apparatus may calculate the mean color value (mCV) of the red and green color channels of the image data, and estimate the amount of tongue by using the calculated mCV value as an independent variable. For a method of estimating the amount of tongue, refer to the contents described in the apparatus 400 for estimating the amount of tongue.

In an embodiment, in order to ensure the reliability of the estimation of the amount of tongue tongue, the apparatus may determine the amount of tongue tongue by performing operations S910, S920, S930, and S940 after a predetermined period of time has elapsed.

In addition, the tongue diagnosis apparatus may determine the final amount of tongue tongue using the amount of tongue tongue determined based on the previously acquired image data and the amount of tongue tongue determined based on the image data at a point in time when a predetermined time has elapsed. For example, the tongue diagnosis apparatus may determine the final amount of tongue tongue an average of the amount of tongue tongue determined based on the previously acquired image data and the amount of tongue tongue determined based on the image data at a point in time when a predetermined time has elapsed. .

In another embodiment, the tongue diagnosis apparatus may perform a reliability evaluation of the determined amount of tongue tongue. Specifically, the tongue diagnosis apparatus may calculate intraclass correlation coefficients (ICCs) of the ratio of the tongue area occupied by the tongue area and the calculated mCV value.

In one embodiment, the seoljin apparatus may be classified into a small tae, a baktae, and a posterior tae on the basis of the determined amount of tongue.

According to the method of estimating the amount of tongue, it is possible to provide an objective method of measuring the amount of tongue tongue having sufficient reliability and accuracy without subjective judgment of an observer when determining the amount of tongue tongue.

Terms such as "system", "processor", "controller", "component", "module", "interface", "model" and "unit" described above are generally computer-related entity hardware, a combination of hardware and software , May mean software or running software. For example, the above-described components may be, but are not limited to, a process driven by a processor, a processor, a controller, a control processor, an object, an execution thread, a program, and/or a computer. For example, both the controller or processor and the application running on the controller or processor can be components. One or more components may reside within a process and/or thread of execution, and a component may reside on one system or may be deployed on more than one system.

The terms such as "include", "consist of" or "have" described above mean that the corresponding component may be embedded, unless otherwise specified, and thus other components are not excluded. It should be construed as being able to further include other components. All terms, including technical or scientific terms, unless otherwise defined, have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs. Terms generally used, such as terms defined in the dictionary, should be interpreted as being consistent with the meaning in the context of the related technology, and are not interpreted in an ideal or excessively formal meaning unless explicitly defined in the present disclosure.

The description above and the accompanying drawings are merely illustrative of the technical idea of the present disclosure, and those of ordinary skill in the technical field to which the present disclosure belongs can combine configurations without departing from the essential characteristics of the present disclosure. Various modifications and variations, such as separation, substitution, and alteration, will be possible. Accordingly, the embodiments disclosed in the present disclosure are not intended to limit the technical idea of the present disclosure, but to describe the technical idea, and the scope of the technical idea of the present disclosure is not limited by these embodiments. That is, within the scope of the object of the present disclosure, all of the components may be selectively combined with one or more and operated. The scope of protection of the present disclosure should be interpreted by the following claims, and all technical ideas within the scope equivalent thereto should be construed as being included in the scope of the present disclosure.

Claims (15)

As a method for estimating the amount of snow flakes, the apparatus for estimating the amount of snow flakes,
Obtaining, by an image data acquisition unit of the apparatus for estimating the amount of snow condition, image data captured using an ultraviolet light source;
Extracting a tongue region from the image data by an area extracting unit of the apparatus for estimating the amount of tongue tongue;
Determining an ultraviolet fluorescence state of the tongue region by a fluorescence state determination unit of the apparatus for estimating the amount of tongue tongue; And
Including the step of determining the amount of tongue tongue based on the ultraviolet fluorescence state of the tongue region, by the amount of tongue determining unit of the apparatus for estimating the amount of tongue,
Determining the ultraviolet fluorescence state of the tongue region,
Removing a blue (B) pixel from the tongue region based on an RGB color model, and determining an ultraviolet fluorescence intensity value using only a red (R) pixel and a green (G) pixel,
The step of determining the amount of tongue tongue based on the ultraviolet fluorescence state of the tongue region,
Using the ultraviolet fluorescence intensity value to determine the amount of seoltae,
The final amount of tongue tongue is calculated by using the average of the amount of tongue tongue determined based on the image data acquired at a specific time point and the amount of tongue tongue determined based on the image data acquired at the time elapsed from the specific time point. A method, characterized in that to determine.
The method of claim 1,
The image data,
Method, characterized in that the image data of the tongue using an ultraviolet light source in an environment in which external light is shielded.
The method of claim 1,
Extracting the tongue region from the image data,
Dividing a tongue region and a background region from the image data; And
Extracting the tongue region
It characterized in that it comprises a, method.
The method of claim 1,
Extracting the tongue region from the image data,
Extracting a tongue region from the image data; And
Extracting the tongue area from the tongue area by using the difference in the a* value of the CIE-LAB color model
It characterized in that it comprises a, method.
The method of claim 1,
Extracting the tongue region from the image data,
Extracting a tongue region from the image data using a drag-and-drop operation
It characterized in that it comprises a, method.
delete The method of claim 1,
The step of determining the ultraviolet fluorescence intensity value,
Determining an ultraviolet fluorescence intensity value by calculating an average value of color information of red (R) pixels and green (G) pixels based on an RGB color model in the tongue region
It characterized in that it comprises a, method.
As a device for estimating the amount of snow formation,
An image data acquisition unit that acquires image data captured using an ultraviolet light source;
A region extracting unit for extracting a tongue region from the image data;
A fluorescence state determination unit for determining an ultraviolet fluorescence state of the tongue region; And
Including a snow tongue amount determination unit for determining the amount of snow tongue based on the ultraviolet fluorescence state of the tongue region,
The fluorescence state determination unit,
The blue (B) pixel is removed from the tongue region based on the RGB color model, and the ultraviolet fluorescence intensity value is determined using only the red (R) pixel and the green (G) pixel,
The snow content determination unit,
Using the ultraviolet fluorescence intensity value to determine the amount of seoltae,
The final amount of tongue tongue is calculated by using the average of the amount of tongue tongue determined based on the image data acquired at a specific time point and the amount of tongue tongue determined based on the image data acquired at the time elapsed from the specific time point. Device, characterized in that to determine.
The method of claim 8,
The image data,
An apparatus, characterized in that the image data obtained by photographing a tongue using an ultraviolet light source in an environment in which external light is shielded.
The method of claim 8,
The region extraction unit,
Distinguishing the tongue region and the background region from the image data,
Device, characterized in that for extracting the tongue region.
The method of claim 8,
The region extraction unit,
Extracting a tongue region from the image data,
The apparatus, characterized in that for extracting the tongue area from the tongue area by using a difference between the a* value of the CIE-LAB color model.
The method of claim 8,
The region extraction unit,
An apparatus, characterized in that the tongue region is extracted from the image data using a drag-and-drop operation.
delete The method of claim 8,
The fluorescence state determination unit,
The apparatus, characterized in that the ultraviolet fluorescence intensity value is determined by calculating an average value of color information of red (R) pixels and green (G) pixels based on an RGB color model in the tongue region.
As a system for estimating the amount of snow formation,
An imaging device for imaging the back portion of the tongue using an ultraviolet light source, and
Acquiring image data captured by the imaging device, extracting a tongue region from the image data, determining an ultraviolet fluorescence state of the tongue region, and determining an amount of tongue based on the ultraviolet fluorescence state of the tongue region Including a tongue diaphragm
The seoljin device,
From the tongue region, the blue (B) pixel is removed based on the RGB color model, the ultraviolet fluorescence intensity value is determined using only the red (R) pixel and the green (G) pixel, and Determine the amount,
The final amount of tongue tongue is calculated by using the average of the amount of tongue tongue determined based on the image data acquired at a specific time point and the amount of tongue tongue determined based on the image data acquired at the time elapsed from the specific time point. System to determine.

Images