WO2017073823A1 - Device and method for deriving adaptive threshold value and distinguishing between tongue fur, tongue texture, and mixed area thereof - Google Patents

Abstract

The present invention relates to a device and a method for distinguishing between tongue fur, tongue texture, and a mixed area thereof, and an auxiliary computing device according to an embodiment comprises: a calculation unit for calculating a first adaptive threshold value for tongue texture and a second adaptive threshold value for tongue fur, in a tongue area of an input image; and a processing unit for classifying the input image into at least three areas on the basis of the calculated first adaptive threshold value and second adaptive threshold value.

Description

Apparatus and method for adaptive threshold derivation and separation of snow, snow, and mixed areas

A technique for finding adaptive thresholds in a snowy image of a given color, which primarily calculates snow thresholds that distinguish between tongues and non- tongues, and mixes tongues and tongues in areas that are not tongues. It's about a technique for calculating a state threshold that separates areas.

In modern society, the interest in health is increasing day by day. In addition to these times, as technology advances rapidly, such as data analysis methods and tools by real-time data collection, it is possible to monitor health status and provide personalized health care services.

In addition, the convenience and customization of health services and related systems are being strengthened by diversifying customer demands and improving expectations according to changes in consumer's consciousness. Personalized healthcare projects, such as weight management, are growing rapidly.

In recent years, the condition of the tongue has been used as a variety of measures to determine the health.

Tongue refers to moss-like parts on the tongue surface with tongues and heterogeneous colors, and is caused by substances that have flowed back from the digestive organs or keratinization of filamentous papilla. Therefore, the distribution and color of tongues change according to the state of health, and in traditional medicine, such as China, Japan, and Korea, these state changes are used for diagnosis.

Recently, an objective feature analysis algorithm has been developed using color tongue images. The most advanced technique for analysis of tongue features is the classification of tongue regions in tongue images.

According to the method of defining the tongue area, the characteristics of the tongue analyzed will be different and the results of diagnosis will be different. Therefore, the repeatability and accuracy of the diagnosis can be improved by defining the area based on objective and accurate criteria.

According to an embodiment, a computing assist device may include a calculator configured to calculate a first adaptive threshold for a tongue quality and a second adaptive threshold for a tongue in a tongue area of an input image, and the calculated first adaptive threshold and the second adaptive threshold value. And a processing unit classifying the input image into at least three areas based on an adaptation threshold.

The calculator may set a temporary threshold, and calculate a first total variation and a second total variation for each of the plurality of regions divided by the set temporary threshold. Calculate a sum total variation through the sum of the calculated first total variation and the second total variation, and calculate the sum total variation using the calculated total variation. At least one of the first adaptation threshold and the second adaptation threshold is calculated.

The calculator may be configured to calculate a threshold value corresponding to the minimum value of the calculated sum total variation as at least one of the first adaptive threshold value and the second adaptive threshold value.

According to an embodiment, the calculation unit may include the temporary threshold value using at least one of R, CIE L * a * b * (CIELAB) color space of sRGB color space, and H value of HSV color space. Set.

The calculator may remove a pixel corresponding to the boundary between the plurality of regions, and may include a first total variation and a second total variation for each of the plurality of regions from which the boundary pixel is removed. calculate total variation).

According to an exemplary embodiment, the calculator binarizes a color element in the snow region and calculates the first adaptation threshold and the second adaptation threshold based on the binarized color element.

According to an embodiment of the present invention, a computing assisting device may include a calculator configured to calculate adaptation thresholds for tongue quality in a tongue region of an input image, and a tongue texture region, a tongue region, and a tongue and tongue combination region based on the calculated adaptive thresholds. It includes a processing unit for classifying.

The calculator may set a temporary threshold and calculate a first total variation and a second total variation for each of the regions divided by the set temporary threshold. And calculating a sum total variation through the sum of the calculated first total variation and the second total variation, and using the calculated total variation, the adaptation threshold. Calculate at least one of the values.

The method may further include calculating a first adaptation threshold for tongue quality and a second adaptation threshold for appearance in a tongue region of an input image, and the calculated first adaptation threshold and the second adaptation threshold value. Classifying the lingual region, lingual region, and lingual and lingual mixture region based on the lingual region.

The calculating may include setting a temporary threshold value, a first total variation and a second total variation for each of the plurality of regions divided by the set temporary threshold. calculating a variation, calculating a sum total variation through a sum of the calculated first total variation and the second total variation, and calculating the sum Calculating at least one of the first adaptation threshold and the second adaptation threshold using a variation.

Computing at least one of the first adaptive threshold value and the second adaptive threshold value using the calculated total variation according to an embodiment corresponds to a minimum value of the calculated sum total variation. Calculating a threshold value to at least one of the first adaptive threshold value and the second adaptive threshold value.

The setting of the temporary threshold according to an embodiment may include setting at least one of R of a sRGB color space, a * or b * of a CIE L * a * b * (CIELAB) color space, and an H value of an HSV color space. And setting the temporary threshold value.

The calculating of the first total variation and the second total variation according to an embodiment may include removing pixels corresponding to the boundaries between the plurality of regions, and corresponding to the boundaries. Calculating a first total variation and a second total variation for each of the plurality of regions from which the pixel is removed.

The calculating may include binarizing a color component in the snow region and calculating the first adaptive threshold and the second adaptive threshold based on the binarized color component. do.

The program according to an exemplary embodiment may include a command set for calculating a first adaptive threshold for a tongue quality and a second adaptive threshold for a tongue in a tongue region of an input image, and the calculated first adaptive threshold and a second adaptive threshold. And a command set for classifying the input image into at least three regions based on a value.

FIG. 1 illustrates a tongue area, a tongue area, a tongue and a tongue mixed area classified through a computing assist device according to an embodiment.

2 is a diagram illustrating a computing assistant device according to an exemplary embodiment.

3 is a view for explaining different areas classified as temporary thresholds.

4A and 4B are diagrams illustrating an embodiment of calculating an adaptation threshold value from sum total variation.

FIG. 5 is a diagram for describing a method of classifying a tongue area, a tongue area, a tongue and a tongue mixture area, according to an exemplary embodiment.

6 is a diagram for explaining a method of calculating an adaptive threshold by setting a temporary threshold.

Specific structural or functional descriptions of the embodiments according to the inventive concept disclosed herein are merely illustrated for the purpose of describing the embodiments according to the inventive concept, and the embodiments according to the inventive concept. These may be embodied in various forms and are not limited to the embodiments described herein.

Embodiments according to the inventive concept may be variously modified and have various forms, so embodiments are illustrated in the drawings and described in detail herein. However, this is not intended to limit the embodiments in accordance with the concept of the present invention to specific embodiments, and includes modifications, equivalents, or substitutes included in the spirit and scope of the present invention.

Terms such as first or second may be used to describe various components, but the components should not be limited by the terms. The terms are only for the purpose of distinguishing one component from another component, for example, without departing from the scope of the rights according to the inventive concept, the first component may be called a second component, Similarly, the second component may also be referred to as the first component.

When a component is referred to as being "connected" or "connected" to another component, it may be directly connected to or connected to that other component, but it may be understood that other components may be present in between. Should be. On the other hand, when a component is said to be "directly connected" or "directly connected" to another component, it should be understood that there is no other component in between. Expressions describing relationships between components, such as "between" and "immediately between" or "directly neighboring", should be interpreted as well.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. Singular expressions include plural expressions unless the context clearly indicates otherwise. As used herein, the terms "comprise" or "having" are intended to designate that the stated feature, number, step, operation, component, part, or combination thereof is present, but one or more other features or numbers, It is to be understood that it does not exclude in advance the possibility of the presence or addition of steps, actions, components, parts or combinations thereof.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art. Terms such as those defined in the commonly used dictionaries should be construed as having meanings consistent with the meanings in the context of the related art, and are not construed in ideal or excessively formal meanings unless expressly defined herein. Do not.

Hereinafter, exemplary embodiments will be described in detail with reference to the accompanying drawings. However, the scope of the patent application is not limited or limited by these embodiments. Like reference numerals in the drawings denote like elements.

FIG. 1 illustrates a tongue area, a tongue area, a tongue and a tongue mixed area classified through a computing assist device according to an embodiment.

The color characteristics of the tongue and tongue surface (sulli) are different from each other through the threshold of color.

Most of classifications are classified by threshold value. Due to problems such as tongue color characteristics and image measurement environment among the measurers, when a certain threshold value is used in all situations, the accuracy of area classification is inevitably deteriorated. According to an embodiment, the computing assist device may derive an adaptive threshold value suitable for the color characteristics of the image, the quality of the snow, and the color of the tongue, thereby increasing the accuracy of the area classification.

In the case of the filamentous papilla, which is one of the factors of the tongue, the filamentous papilla is fine, so when the image is acquired, the color value of the corresponding pixel represents the color characteristics of the parietal and the angled filamentous papilla (white). Accordingly, the computing assist device according to an embodiment may be divided into a tongue area 120, a tongue area 140, a tongue area and a mixture of tongues 130 in the general color image 110, and through the classification, And color analysis of tongues more accurately.

In detail, the computing assisting apparatus according to an exemplary embodiment is a method of finding an adaptive threshold value in a given color tongue image, and primarily calculates a tongue quality threshold that distinguishes between a tongue and a non- tongue state, and secondarily, it is not a tongue quality. It is possible to calculate the tongue threshold value that distinguishes between tongue and tongue mixture zone and tongue zone.

In order to calculate an adaptation threshold, the computing assisting apparatus calculates a total variation (TV) within two regions separated by an arbitrary threshold (temporary threshold), respectively, and calculates the total variation (T). The sum total variation (STV), which is a sum of TV and total variation, may be calculated to calculate a threshold value that minimizes the sum total variation (STV).

Because tongues and tongues are heterogeneous colors, the color value changes large in the boundary region of the two regions, and the color value changes within the tongue and tongue region relatively small. With this characteristic, when the sum total variation (STV) is minimized, an optimized adaptation threshold for distinguishing two regions can be derived.

After all, using the present invention, it is easy to apply to the mobile analysis system that was not easy with the existing patent technology as a robust algorithm for the image measurement environment.

2 is a diagram illustrating an example of a computing assisting device 200 according to an exemplary embodiment.

The computing assisting device 200 according to an embodiment may derive an adaptive threshold value suitable for the color characteristics of the image, the quality of the snow, and the shape of the tongue, and thus may increase the accuracy of the area classification.

To this end, the computing assistance device 200 according to an embodiment may include a calculator 210 and a processor 220.

The calculator 210 may calculate a plurality of adaptation thresholds for snow quality in the snow region of the input image.

For example, the calculator 210 may calculate a first adaptation threshold for tongue quality and a second adaptation threshold for appearance in the tongue region of the input image. To this end, the calculator 210 may binarize the color elements in the snow region and calculate a first adaptation threshold value and a second adaptation threshold value based on the binarized color elements.

The first adaptation threshold is a threshold value for distinguishing a region where tongues appear and a region where tongues do not appear in the tongue region, and distinguish a tongue zone and a tongue zone and a tongue mix zone.

In addition, the second adaptation threshold is a threshold value for distinguishing a region where tongue quality appears and a region where tongue quality does not appear, and classifies a tongue quality, tongue mix region, and a tongue region.

That is, the tongue quality region, tongue quality and tongue mix region, and tongue style area may be distinguished through the first adaptation threshold value and the second adaptation threshold value.

The calculator 210 may calculate a first adaptive threshold value and a second adaptive threshold value for the condition according to the characteristics of the input image.

To this end, the calculator 210 may set a temporary threshold. For example, the calculation unit 210 uses a temporary threshold value using at least one of R of the sRGB color space, a * or b * of the CIELAB color space, and H values of the HSV color space. Can be set.

Next, the calculator 210 may calculate a first total variation and a second total variation for each of the plurality of regions divided by the set temporary threshold.

In addition, the calculator 210 may calculate a sum total variation through the sum of the calculated first total variation and the second total variation. In this case, the calculator 210 may calculate at least one of the first adaptation threshold and the second adaptation threshold using the calculated total variation. For example, the calculator 210 may calculate a threshold value corresponding to the calculated minimum value of the sum total variation as at least one of the first adaptive threshold value and the second adaptive threshold value.

The processor 220 according to an embodiment may classify a plurality of areas, for example, a tongue area, a tongue area, and a tongue and tongue mixture area based on the calculated first and second adaptive threshold values. have.

On the other hand, the calculator 210 removes pixels corresponding to the boundaries between the plurality of regions, and first and second total variations for each of the regions where the boundary pixels are removed. ) Can also be calculated. This will be described in detail with reference to FIG. 3.

3 is a view for explaining different areas classified as temporary thresholds.

Reference numeral 310 denotes an image classified into different areas as a temporary threshold. Among these, reference numeral 311 may be classified as a settling area, and in order to calculate a first total variation and a second total variation, the pixel 312 corresponding to the boundary may be removed.

Reference numeral 320 is an image generated by removing a pixel 312 corresponding to a boundary from the image 310, and reference numeral 321 is classified as a setting region. In this case, the computing assist device may calculate a first total variation and a second total variation from the image 320 by using an algorithm.

For example, the calculator of the computing assist device may calculate a first total variation and a second total variation using Equation 1.

In [Equation 1],

Is

, A 'represents an area divided by a temporary threshold.

In the related art, a specific method for deriving an adaptation threshold is not specified, and the first total variation and the second total variation used in the patent used in the present invention are not used. That is, the present invention categorizes into a tongue zone, a tongue zone and a tongue zone, and a tongue zone, and provides an algorithm for this.

Therefore, the present invention can be implemented with a robust algorithm in the image measurement environment, so it is easy to apply to a mobile analysis system that was not easy with the existing patent technology.

4A and 4B are diagrams illustrating an embodiment of calculating an adaptation threshold value from sum total variation.

First, referring to FIG. 4A, a graph 410 shows a sum total variation for CIE a *. The sum total variation may be expressed as a sum of a first total variation and a second total variation, which represents a minimum value at a point 411. Reference numeral 411 corresponding to the minimum value denotes a point having a CIE of 15 and may be interpreted as a point having a sum total variation of 15. Therefore, it may be classified into a tongue area or a tongue area based on the adaptation threshold value (CIE = 15).

As shown in FIG. 4B, the computing assist device may divide the tongue image 420 into a tongue area or a tongue area based on an adaptive threshold value (CIE = 15).

FIG. 5 is a diagram for describing a method of classifying a tongue area, a tongue area, a tongue and a tongue mixture area, according to an exemplary embodiment.

When a certain threshold value is used, the accuracy of the area classification is inevitably deteriorated. The present invention can derive an adaptive threshold value suitable for the color characteristics of the image, the quality of the snow, and the shape of the tongue, thereby increasing the accuracy of the area classification.

To this end, the method according to an embodiment calculates a first adaptation threshold for the tongue quality and a second adaptation threshold for the condition in the tongue region of the input image, and calculates the calculated first adaptation threshold value and the second adaptation threshold value. On the basis of this, the tongue, tongue, and tongue can be classified into tongue and tongue.

Specifically, the method according to an embodiment may allocate a tongue area representing the tongue of color to the memory (step 501).

Next, the method according to one embodiment may calculate an adaptation threshold for snow quality (step 502). The threshold for adaptation to the lingual quality is to distinguish between lingual and non-lingual qualities, and may be used as a criterion for distinguishing a mixed area of lingual lingual and lingual and lingual area, or for distinguishing between a lingual area and a lingual area.

The method according to one embodiment may derive a non-snow area using the calculated threshold for adaptation to snow quality (step 503).

The area that is not the tongue is a region in which the tongue is distributed above the threshold, and may be interpreted as the tongue.

On the other hand, the method according to an embodiment may calculate an adaptation threshold for the setting (step 504).

The adaptation threshold for tongues is to distinguish between tongues and non- tongues, and it can be used as a criterion for distinguishing tongues and tongues from mixed areas and tongues, or to distinguish tongues from tongues.

According to an embodiment, the method may derive a tongue area and a tongue / tongue mix area by using an adaptation threshold for the tongue (step 505).

6 is a diagram for explaining a method of calculating an adaptive threshold by setting a temporary threshold.

In order to set the temporary threshold to calculate the adaptive threshold, first, a temporary threshold must be set (step 601). For example, the method according to the present invention uses a temporary threshold value using at least one of R, CIE L * a * b * (CIELAB) color space of sRGB color space, and H value of HSV color space. Can be set.

Next, the method according to the present invention removes a pixel corresponding to a plurality of inter-region boundaries (step 602), and includes a first total variation and a first total variation for each of the plurality of regions from which a pixel corresponding to the boundary is removed. Second total variation is calculated (step 603).

The method according to the invention calculates the sum total variation through the sum of the calculated first total variation and the second total variation, and calculates the sum total variation using the calculated total variation. At least one of the first adaptation threshold and the second adaptation threshold may be calculated. In this case, the color component may be binarized in the snow region, and the first adaptation threshold value and the second adaptation threshold value may be calculated based on the binarized color element.

The method according to the present invention may repeat the calculation of the sum total variation for all threshold candidates and derive a threshold value that satisfies the sum total variation as a result of the iteration (step 605).

As a result, according to the present invention, an adaptive threshold value suitable for the color characteristics of the image and the quality of the snow and the tongue may be derived, thereby increasing the accuracy of the area classification.

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 are, for example, processors, controllers, arithmetic logic units (ALUs), digital signal processors, microcomputers, field programmable gate arrays (FPGAs). Can be implemented using one or more general purpose or special purpose computers, such as a programmable logic unit (PLU), a 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, other implementations, other embodiments, and equivalents to the claims are within the scope of the claims that follow.

Claims (16)

1. At least temporarily implemented by the computer:

   A calculator configured to calculate a first adaptive threshold value for tongue quality and a second adaptive threshold value for tongue shape in the tongue region of the input image; And

   A processor that classifies the input image into at least three regions based on the calculated first and second adaptive thresholds

   Computing assistant device comprising a.
2. The method of claim 1,

   The calculation unit,

   Setting a temporary threshold, calculating a first total variation and a second total variation for each of the plurality of regions divided by the set temporary threshold, and calculating the calculated first total Compute sum total variation through the sum of the first total variation and the second total variation, and use the calculated total variation to adjust the first adaptation threshold and the second adaptation. Computing assistant device for calculating at least one of the threshold.
3. The method of claim 2,

   The calculation unit,

   And calculating a threshold value corresponding to the minimum value of the calculated sum total variation to at least one of the first adaptive threshold value and the second adaptive threshold value.
4. The method of claim 2,

   The calculation unit,

   Computing assist device for setting the temporary threshold using at least one of R, CIE L * a * b * (CIELAB) color space of the sRGB color space, H value of the HSV color space.
5. The method of claim 2,

   The calculation unit,

   A computing assist device for removing pixels corresponding to the plurality of regions and calculating a first total variation and a second total variation for each of the plurality of regions from which the boundary pixels are removed. .
6. The method of claim 1,

   The calculation unit,

   And binarizing a color component in the snow region and calculating the first adaptation threshold and the second adaptation threshold based on the binarized color component.
7. At least temporarily implemented by the computer:

   A calculator configured to calculate adaptation thresholds for snow quality in the snow region of the input image; And

   A processing unit classifying the tongue quality area, tongue quality area, and tongue quality and tongue quality mixing area based on the calculated adaptation thresholds

   Computing assistant device comprising a.
8. The method of claim 7, wherein

   The calculation unit,

   Setting a temporary threshold, calculating a first total variation and a second total variation for each of the plurality of regions divided by the set temporary threshold, and calculating the calculated first total Calculating a sum total variation through a sum of a first total variation and a second total variation, and calculating at least one of the adaptation thresholds using the calculated total variation Computing Assistant.
9. In a method implemented at least temporarily by a computer,

   Calculating a first adaptive threshold for tongue quality and a second adaptive threshold for tongue shape in a tongue area of an input image; And

   Classifying the tongue quality region, tongue style area, and tongue quality and tongue mix region based on the calculated first adaptive threshold value and the second adaptive threshold value.

   How to include.
10. The method of claim 9,

    The calculating step,

    Setting a temporary threshold;

    Calculating a first total variation and a second total variation for each of the plurality of regions divided by the set temporary threshold value;

    Calculating a sum total variation through a sum of the calculated first total variation and second total variation; And

    Calculating at least one of the first adaptive threshold value and the second adaptive threshold value using the calculated total variation;

    How to include.
11. The method of claim 10,

    Computing at least one of the first adaptive threshold value and the second adaptive threshold value using the calculated total variation,

    Calculating a threshold value corresponding to the minimum value of the calculated sum total variation to at least one of the first adaptive threshold value and the second adaptive threshold value;

    How to include.
12. The method of claim 10,

    Setting the temporary threshold value,

    setting the temporary threshold using at least one of R, CIE L * a * b * (CIELAB) color space of sRGB color space, and H value of HSV color space

    How to include.
13. The method of claim 10,

    Computing the first total variation (second total variation) and the second total variation (second total variation),

    Removing pixels corresponding to the boundaries between the plurality of regions; And

    Calculating a first total variation and a second total variation for each of the plurality of regions from which pixels corresponding to the boundary are removed;

    How to include.
14. The method of claim 9,

    The calculating step,

    Binarizing color elements in the snow region; And

    Calculating the first adaptation threshold and the second adaptation threshold based on the binarized color component

    How to include.
15. A computer-readable recording medium having recorded thereon a program for performing the method of claim 9.
16. A program stored on a record carrier, the program being executed in a computing system:

    An instruction set for calculating a first adaptive threshold for tongue quality and a second adaptive threshold for tongue shape in a tongue area of an input image; And

    An instruction set for classifying the input image into at least three regions based on the calculated first adaptive threshold value and a second adaptive threshold value

    Program comprising a.

Images