JP2016144569A - Information processing device, information processing system, information processing method, and program for information processing - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an information processing device capable of recognizing characteristics of a tongue based on a medical finding by a more appropriate and simpler method, and capable of recognizing a health condition of a person with the tongue more appropriately and quickly.SOLUTION: An information processing device includes a processing part 2 for, based on a tongue image acquired by imaging the surface of a tongue, calculating the characteristics based on a medical finding, and weighting the calculated characteristics for each of predetermined regions, and a display 3 for displaying the result for each region.SELECTED DRAWING: Figure 1

Description

  The present invention belongs to a technical field of an information processing apparatus, an information processing system, an information processing method, and an information processing program. More specifically, it belongs to the technical field of an information processing apparatus and information processing method for recognizing the surface state of the tongue, an information processing system including the information processing apparatus, and a program for the information processing apparatus.

  In view of so-called health orientation in recent years, development of a method capable of objectively detecting or recognizing a person's health condition from the outside is underway. And as a prior art relevant to such a method, there exists the method described in the following patent document 1. FIG.

  In the method described in Patent Document 1 below, the overall health level is determined based on image information of a body part (mainly tongue). More specifically, in the method described in Patent Document 1, the color of the tongue, the shape of the tongue, for example, the tooth mark on the peripheral edge of the tongue, the cracks on the surface of the tongue, and the surface of the tongue are obtained from the image of the tongue taken with a digital still camera. The mathematical Mahalanobis distance between nine types of feature quantity information such as moss color and a preset healthy body reference sample is calculated, and the value is used as a scale for determining the health level. .

Japanese Patent No. 4487535

  However, according to the method described in Patent Document 1, when the health level mathematically obtained using the Mahalanobis distance changes such as increase or decrease, the change is affected (that is, the cause of the change). It is difficult to know what the feature amount is, and as a result, there is a problem that it is difficult to provide feedback for health care (that is, clarify the cause).

  Further, in the method described in Patent Document 1, a measure of health is obtained using a comparison with a predetermined healthy body reference sample. How to specifically obtain the healthy body reference sample There is no reference, and as a result, there is a problem that the criteria for determining “health” is unclear and the determination result by the method described in Patent Document 1 may not make sense.

  Therefore, the present invention has been made in view of the above problems, and one example of the problem is that the features of the tongue based on medical knowledge can be recognized by a more accurate and simple method. Information processing apparatus and information processing method capable of recognizing the state of the tongue more accurately and quickly (in other words, the health state of the person having the tongue), the information processing system including the information processing apparatus, and the The object is to provide a program for an information processing apparatus.

  In order to solve the above-mentioned problems, the invention according to claim 1 is based on acquisition means such as an interface for acquiring surface information obtained by imaging the surface of the tongue, and medical information based on the acquired surface information. Calculation means such as an image processing unit for calculating feature information indicating the feature of the surface based on a physical finding, and the surface at a part set in advance based on the medical knowledge with respect to the calculated feature information Generating means such as a health degree determination unit that performs weighting set in advance corresponding to the medical knowledge for each divided surface and generates weighting feature information for each divided surface, and each of the generations Output means such as an output control unit for outputting the weighted feature information for each of the divided surfaces.

  In order to solve the above-described problem, an invention according to claim 7 generates the surface information by imaging the information processing apparatus according to any one of claims 1 to 6 and the surface. And an imaging device such as a camera that outputs to the acquisition means, and a presentation device such as a display that presents an output result from the output means.

  In order to solve the above-mentioned problems, the invention according to claim 8 is based on an acquisition step of acquiring surface information obtained by imaging the surface of the tongue, and medical knowledge based on the acquired surface information. A calculation step for calculating feature information indicating the characteristics of the surface based on the calculated feature information, for each divided surface obtained by dividing the surface into a portion set in advance based on the medical knowledge, Each of the weights set in advance corresponding to the medical knowledge is generated, and the weighting feature information for each of the divided surfaces is generated, and the generated weighted feature information is output for each of the divided surfaces. An output step.

  In order to solve the above-described problem, the invention according to claim 9 includes a computer included in an information processing apparatus including an acquisition unit such as an interface for acquiring surface information obtained by imaging the surface of the tongue. Based on the acquired surface information, a calculation means for calculating feature information indicating the surface features based on medical knowledge, and a portion preset based on the medical knowledge for the calculated feature information Generating means for generating weighting feature information for each of the divided surfaces, and for each of the divided surfaces obtained by dividing the surface to each of the divided surfaces. The weighting feature information is made to function as an output means for outputting each divided surface.

  According to the invention described in claim 1 or claims 7 to 9, the feature information is calculated based on the surface information obtained by imaging the surface of the tongue, and the calculated feature The information is subjected to predetermined weighting for each divided surface, weighting feature information is generated and output for each divided surface. Therefore, it is possible to recognize the characteristics of the tongue based on medical knowledge only by acquiring surface information corresponding to the surface of the tongue. In addition, since the features of each part weighted based on medical knowledge can be recognized for each part of the surface of the tongue, the state of the tongue (in other words, the person with the tongue can be more accurately and quickly) Health status).

  In order to solve the above-mentioned problem, the invention according to claim 2 is the information processing apparatus according to claim 1, wherein the health level determination unit generates summation information by adding the output weighting feature information. Based on the generated addition information, a health level determination unit that calculates health level information indicating the level of health based on the tongue using a calculation method set in advance based on the medical knowledge The health level calculation means is further provided, and the output means is configured to output the calculated health level information.

  According to invention of Claim 2, in addition to the effect | action of Claim 1, since health degree information is calculated and output based on the addition information which added each weighting characteristic information, for every site | part of a tongue A specific health level based on the features can be recognized.

  In order to solve the above problems, the invention according to claim 3 is the information processing apparatus according to claim 1 or 2, wherein the surface is a surface on the front side of the tongue, It is comprised so that it may be at least one of the front-end | tip part in the surface of the said front side, a tongue base part, and a side part.

  According to the invention described in claim 3, in addition to the action of the invention described in claim 1 or 2, the surface is a surface on the front side of the tongue, and each part is a tip part on the surface on the front side, Since it is specified in at least one of the tongue base part and the side part, it is possible to accurately recognize the characteristics of the front side state of the tongue while reducing the processing load.

  In order to solve the above-mentioned problem, the invention according to claim 4 is the information processing apparatus according to claim 3, wherein the feature is any one of a surface shape, a color, and an outer edge shape on each of the divided surfaces. And the calculating means is configured to calculate the feature information indicating any one of the calculation means.

  According to the invention described in claim 4, in addition to the action of the invention described in claim 3, the feature as the divided surface is any one of the surface shape, color and outer edge shape of the front side of the tongue. Since the feature information indicating the above is calculated, the state of the surface on the front side of the tongue can be accurately recognized based on medical knowledge.

  In order to solve the above-described problem, the invention according to claim 5 is the information processing device according to claim 1 or 2, wherein the surface is a surface on the back side of the tongue, It is configured to be at least one of the divided parts obtained by dividing the surface on the back side into two left and right by a dividing line in the longitudinal direction.

  According to invention of Claim 5, in addition to the effect | action of the invention of Claim 1 or Claim 2, the surface is the surface of the back side of a tongue, and each site | part is the said back side by the dividing line of a longitudinal direction. Since the surface is divided into at least one of the divided parts divided into left and right parts, it is possible to accurately recognize the characteristics of the state on the back side of the tongue while reducing the processing load.

  In order to solve the above-described problem, the invention according to claim 6 is the information processing apparatus according to claim 5, wherein the features include a surface shape, a color, an outer edge shape, and a deep tongue vein on each of the divided surfaces. The calculation means is configured to calculate the feature information indicating any one of the shapes.

  According to the invention described in claim 6, in addition to the action of the invention described in claim 5, the feature as the divided surface is any of the surface shape, color, outer edge shape and deep tongue vein shape on the back side of the tongue. Since the feature information indicating either of them is calculated, the state of the surface on the back side of the tongue can be accurately recognized based on medical knowledge.

  According to the present invention, the feature information is calculated based on the surface information obtained by imaging the surface of the tongue, the weighting feature is performed for each of the divided surfaces with respect to the calculated feature information. Generate information and output for each split surface. Therefore, it is possible to recognize the characteristics of the tongue based on medical knowledge only by acquiring surface information corresponding to the surface of the tongue.

  In addition, since the features of each part weighted based on medical knowledge can be recognized for each part of the surface of the tongue, the state of the tongue (in other words, the person with the tongue can be more accurately and quickly) Health status).

1 is a block diagram illustrating a schematic configuration of a health degree determination system according to a first embodiment. It is a flowchart which shows the health degree determination process which concerns on 1st Embodiment. It is a figure which illustrates the tongue image which concerns on 1st Embodiment, (a) is a figure which illustrates the image containing the said tongue image, (b) is a figure which illustrates the said tongue image. It is a figure which illustrates the extraction process of the feature which concerns on 1st Embodiment, (a) is an example of the original tongue image, (b) is a figure which illustrates extraction of a shape feature, (c) and ( d) is a diagram illustrating the extraction of color features. It is a figure which illustrates the division | segmentation state of the tongue image which concerns on 1st Embodiment. It is a figure which illustrates the evaluation point for every part concerning a 1st embodiment. It is a figure which illustrates the weighting process etc. which concern on 1st Embodiment, (a) is a figure which illustrates the evaluation point before weighting, (b) is a figure which illustrates the evaluation point after weighting, (c ) Is a diagram illustrating the sum of the weighted evaluation points, and (d) is a diagram illustrating the value of the health level according to the embodiment. It is a figure which illustrates the display state of the health degree which concerns on 1st Embodiment. It is a figure which illustrates determination of the health degree which concerns on 2nd Embodiment, (a) is a figure which shows the example of the image of the back side of the tongue which concerns on 2nd Embodiment, (b) is the division | segmentation of the image of the said back side It is a figure which illustrates a state.

  Next, modes for carrying out the present invention will be described based on the drawings. In addition, each embodiment described below determines the health level of the subject based on the state of the tongue of the subject, and presents the determination result to the subject or the doctor in charge thereof. It is an embodiment when the invention is applied.

(I) First Embodiment First, a first embodiment according to the present invention will be described with reference to FIGS. FIG. 1 is a block diagram showing a schematic configuration of the health level determination system according to the first embodiment, FIG. 2 is a flowchart showing health level determination processing according to the first embodiment, and FIG. It is a figure which illustrates the tongue image which concerns on a form. 4 is a diagram illustrating feature extraction processing according to the first embodiment, FIG. 5 is a diagram illustrating a segmented state of a tongue image according to the first embodiment, and FIG. 6 is a diagram illustrating the first embodiment. It is a figure which illustrates the evaluation score for every part which concerns on. Further, FIG. 7 is a diagram illustrating weighting processing and the like according to the first embodiment, and FIG. 8 is a diagram illustrating a display state of the health level according to the first embodiment.

  As shown in FIG. 1, the health degree determination system SS according to the first embodiment includes a camera C as an example of an “imaging device” according to the present invention, which includes, for example, a digital still camera similar to a conventional one, and the camera. And a health degree determination device S according to the first embodiment connected to C. Then, the tongue image obtained by imaging the subject's tongue with the camera C is analyzed by the health level determination device S, and the health level of the subject is determined and presented by the health level determination device S using the analysis result. To do. In the following description, a tongue image obtained by imaging the subject's tongue is simply referred to as a “tongue image”.

  As shown in FIG. 1, the health determination device S according to the first embodiment includes an interface 1, a processing unit 2 including a CPU, a ROM (Read Only Memory), a RAM (Random Access Memory), and the like, and a liquid crystal display. And a display 3 as an example of the “presentation device” according to the present invention, an operation unit 4 including a keyboard and a mouse, and a recording unit 5 including, for example, a hard disk. At this time, the health degree determination apparatus S is specifically configured by a personal computer, for example.

  On the other hand, the processing unit 2 includes an image registration unit 20, an image processing unit 21, a health degree determination unit 22, and an output control unit 23. At this time, the image registration unit 20, the image processing unit 21, the health degree determination unit 22, and the output control unit 23 may be configured by, for example, a hardware logic circuit that configures the processing unit 2, or will be described later. The program corresponding to the flowchart showing the health degree determination process according to the first embodiment may be executed by software by the CPU of the processing unit 2 reading and executing the program. At this time, the program may be recorded in advance in the ROM constituting the processing unit 2, or may be acquired via a network such as the Internet as necessary.

  Further, the interface 1 corresponds to an example of “acquisition unit” according to the present invention, the image processing unit 21 corresponds to an example of “calculation unit” according to the present invention, and the health level determination unit 22 corresponds to the present invention. One example of the “generating unit”, one example of the “adding unit”, and one example of the “health degree calculating unit” correspond to each other, and the output control unit 23 corresponds to an example of the “output unit” according to the present invention.

  In the configuration described above, the interface 1 of the health degree determination apparatus S acquires the tongue image information corresponding to the tongue image from the camera C when the subject's tongue is imaged by the camera C, as will be described later. The image is output to the image registration unit 20. Next, the image registration unit 20 records (registers) the output tongue image information in the recording unit 5 in association with identification information for identifying a subject or a doctor in charge from another person, for example. In the following description, the subject or the doctor in charge thereof is simply referred to as “subject”.

  Next, the image processing unit 21 extracts features according to the first embodiment from the tongue image information, generates feature information corresponding to the extracted features, and outputs the feature information to the health degree determination unit 22. Thereby, the health level determination unit 22 determines the health level of the subject using the tongue image using the health level determination process according to the first embodiment based on the feature information, and the determination result is sent to the output control unit 23. Output.

  Here, the above-mentioned features are characterized by characterizing the state of the tongue corresponding to the tongue image according to the first embodiment from the viewpoints of “shape”, “color”, and “outer edge”. More specifically, for example, the above-mentioned shape is characterized by the presence or absence of “scratches”, “bumps” or “points” on the front surface of the tongue, and “color tone” or “light red color as the color of the front surface of the tongue ”,“ Red ”,“ black ”and the like, and the shape of the outer edge of the tongue (more specifically, the presence or absence of“ dental marks ”,“ scratches ”or“ points ”) Features of the outer edge. Note that the characteristics and the like and the method for determining the health level will be described in detail later.

  Thereafter, the output control unit 23 generates a display screen for presenting (displaying) the determination result to a subject or the like based on the determination result output from the health level determination unit 22, and displays information corresponding to the display screen. The determination result is displayed on the display 3.

  Next, the health degree determination process according to the first embodiment will be specifically described with reference to FIGS.

  That is, as illustrated in FIG. 2, the health degree determination process according to the first embodiment is performed by, for example, a doctor in charge as a user using the operation unit 4 of the health degree determination apparatus S. It is started when an instruction operation is performed. When the health level determination process is started, an image including the front surface of the subject's tongue is first captured using the camera C (step S1).

  Here, the image imaged by said step S1 is the image G containing the test subject's tongue T which is illustrated to Fig.3 (a), for example. In the example shown in FIG. 2 (a), markers M1 to M4 for extracting only the tongue T later and forming the tongue image are added. However, in the step S1, the marker M1 and the like are added. It is not an essential matter.

  When an image including a tongue image is captured in step S1, the image registration unit 20 of the processing unit 2 acquires image information corresponding to the image via the interface 1, and temporarily stores this image information in the recording unit 5. Is recorded in a nonvolatile manner (step S2). At this time, the image registration unit 20 records (registers) the image information in the recording unit 5 in association with the identification information corresponding thereto.

  Next, the image processing unit 21 of the processing unit 2 reads out the image information recorded in the recording unit 5 based on, for example, an operation in the operation unit 4, and obtains it from the camera C by referring to, for example, the marker M 1 and the like. The tongue image including only the tongue T is extracted from the processed image G (step S3). As a result of the processing in step S3, a tongue image TG including the tongue T as exemplified in FIG. 3B is obtained. In extracting the tongue image TG in the process of step S3, the tongue image TG can be extracted by arbitrarily using a conventional method in addition to the method using the marker M1 and the like.

  Next, based on the tongue image information corresponding to the tongue image TG, the image processing unit 21 of the processing unit 2 extracts a shape feature on the tongue T (step S40), a color feature extraction process (step S41), and The outer edge feature extraction process (step S42) is performed, and each extraction result is output to the health level determination unit 22.

  More specifically, the image processing unit 21 detects the presence or absence of “scratches” or “points” on the front surface of the tongue T as the shape feature extraction processing according to step S40. At this time, when the tongue image TG including the tongue T illustrated in FIG. 4A is obtained, in the shape feature extraction process according to step S40, for example, a scratch illustrated in FIG. For example, it is extracted as a crack CR using a conventional so-called edge detection method or the like.

  Further, the image processing unit 21 performs, for example, a color clustering process on the front surface of the tongue T as the color collection amount extraction process according to step S41. For example, as illustrated in FIG. While extracting color information, for example, as illustrated in FIG. 4D, the portion of the tongue T in the tongue image TG is divided into sections of a predetermined size, and average color information (for example, (Color information indicating the color such as “color tone”, “light red”, “red”, “black”, etc.) is detected. The reason why the color feature extraction process illustrated in FIG. 4D is performed is to extract a portion of the tongue T where the color changes extremely more than the surroundings.

  Further, the image processing unit 21 extracts the presence / absence of the “tooth marks”, “scratches”, or “points” in the outer edge as the feature extraction processing of the outer edge according to the step S42, for example, the edge detection method. Use to detect.

  Next, when the health level determination unit 22 obtains each extraction result according to the above steps S40 to S42, based on each extraction result, the shape health level calculation process on the tongue T (step S50), the color health level Calculation processing (step S51) and outer edge health level calculation processing (step S52) are performed.

  Here, as shown in FIG. 5, the health degree determination unit 22 extracts a part obtained by dividing the tongue T into six parts from the tongue image TG, and uses the detection of the characteristics and the detection result for each of these parts. The above health level calculation processing is performed. At this time, as illustrated in FIG. 5, the first part I is a part including the tip of the tongue T, the second part II is a part including the tongue base of the tongue T, and the third part III is the left end of the tip of the tongue T. It is a part including an outer edge part. The fourth part IV is a part including the right outer edge of the tip of the tongue T, the fifth part V is a part including the left outer edge of the tongue T, and the sixth part VI is the right outer edge of the tongue T. It is a part containing. In addition, how to divide the part according to the first embodiment, for example, is set in advance based on the medical knowledge that is the basis of the present invention, and is not limited to the way illustrated in FIG. Various changes can be made in response to various medical findings.

  Then, as illustrated in FIG. 6 as the color health level for the first part I, the health level determination unit 22 determines, for example, a score indicating the health level when the tip of the tongue T is detected to be light red. When “0 point” is set and the tip is detected to be red, for example, “−1 point” is set as the score, and when the tip is detected to be black, the score is set to “ -2 points ". Further, as illustrated in FIG. 6 as the health degree of the shape of the first part I, the health degree determination unit 22 may have a crack CR (see FIG. 4B) as a scratch at the tip of the tongue T, for example, “ -2 point "is set, and if there is a crack CR as a point at the tip, for example," -1 point "is set (step S50 and step S51).

  Further, as illustrated in FIG. 6 as the color health level for the second part II, the health level determination unit 22 may detect, for example, a score indicating the health level when the tongue base of the tongue T is detected to be light red. When “0 point” is set and the tongue base is detected to be red or white, for example, “−1 point” is set as the above score, and when the tongue base is detected to be black, the above score is set. For example, “−2 points” is set. Further, as illustrated in FIG. 6 as the health degree of the shape of the second part II, the health degree determination unit 22 may have a crack CR (see FIG. 4B) as a scratch on the tongue base of the tongue T, for example, “ -2 point "is set, and if there is a crack CR as a point at the tongue base, for example," -1 point "is set (step S50 and step S51).

  Furthermore, as illustrated in FIG. 6 as the color health level for the third part III, the health level determination unit 22 determines the health level when it is detected that the left outer edge of the tip of the tongue T is light red. For example, “0 point” is set as the indicated score, and when it is detected that the left outer edge of the tip is a color other than light red, for example, “−1” is set as the above score. Further, the health degree determination unit 22 has a crack CR (see FIG. 4B) as a scratch on the left outer edge of the tip of the tongue T, as illustrated in FIG. 6 as the health degree of the shape of the third part III. For example, “−2 point” is set, and if there is a crack CR as a mark of a point or a tooth on the left outer edge of the tip, for example, “−1 point” is set (step S50 to step S52).

  Further, as illustrated in FIG. 6 as the color health level for the fourth portion IV, the health level determination unit 22 indicates the health level when it is detected that the tip outer right edge of the tongue T is light red. For example, “0 point” is set as the score, and when the right outer edge of the tip is detected to be a color other than light red, for example, “−1” is set as the score. Further, the health degree determination unit 22 has a crack CR (see FIG. 4B) as a scratch on the right outer edge of the tip of the tongue T as illustrated in FIG. 6 as the health degree of the shape of the fourth part IV. For example, “−2 point” is set, and if there is a crack CR as a point or a tooth mark at the right outer edge of the tip, for example, “−1 point” is set (step S50 to step S52).

  Furthermore, as illustrated in FIG. 6 as the color health level for the fifth part V, the health level determination unit 22 determines the health level when the tongue base left outer edge portion of the tongue T is detected to be light red. For example, “0 point” is set as the score, and when it is detected that the tongue base left outer edge is red, for example, “−1 point” is set as the score, and the tongue base left outer edge is black. When detected, for example, “−2 points” is set as the above-mentioned score. In addition, as illustrated in FIG. 6 as the health degree of the shape of the fifth region V, the health level determination unit 22 has a crack CR (see FIG. 4B) as a scratch on the left outer edge of the tongue T. For example, “−2 point” is set, and if there is a crack CR as a point at the left outer edge of the tongue base, for example, “−1 point” is set (step S50 and step S51).

  Finally, as illustrated in FIG. 6 as the color health degree for the sixth part VI, the health degree determination unit 22 determines the health degree when the right outer edge of the tongue base of the tongue T is detected to be light red. For example, “0 point” is set as the score, and when it is detected that the tongue base right outer edge is red, for example, “−1 point” is set as the score, and the tongue base right outer edge is black. When detected, for example, “−2 points” is set as the above-mentioned score. Further, the health degree determination unit 22 has a crack CR (see FIG. 4B) as a scratch on the right outer edge of the tongue T, as exemplified in FIG. 6 as the health degree of the shape of the sixth part VI. For example, “−2 point” is set, and if there is a crack CR as a point at the right outer edge of the tongue base, for example, “−1 point” is set (step S50 and step S51).

  In addition, the setting method of the above-described health evaluation score according to the first embodiment defines an abnormal state (that is, not healthy) first, and when the defined abnormal state is detected, This is a setting method based on a so-called deduction method in which points are deducted by a number corresponding to the degree of abnormality.

  Here, FIG. 6 illustrates an evaluation score as a result of the above-described health degree calculation process for three samples (sample A to sample C). In addition, the hatching part in FIG. 6 shows the item which is not the object of evaluation about the site | part. Further, the samples A to C illustrated in FIG. 6 may be samples based on the tongue images TG captured at different times for the same subject, or the tongue images TG captured for different subjects. Each sample may be based on.

  For example, in the sample A illustrated in FIG. 6, since the color of the first part I is red, the health degree of the color of the first part I is −1, while the first part I has scratches or the like. Since there was no crack CR, as a result, the evaluation score of the health degree as the 1st site | part I is -1. On the other hand, in the fourth part IV of sample A, crack CR as a tooth mark was detected, but there was no other crack CR and the color was light red. As a result, the fourth part IV As a result, the health score is -1. Similarly, in the sample B illustrated in FIG. 6, since the color of the first part I is red, it is −1, the color of the second part II is red or white, and a crack CR as a scratch is detected. Therefore, the total is -3 points, and since the crack CR as a point is detected for the fifth part V, it is -1 point, and since the crack CR as a scratch is detected for the sixth part VI, it is -1 point. Furthermore, in the sample C illustrated in FIG. 6, since the color is red for the first part I and crack CR as a point is detected, the total is −2 points, and the color is red or white for the second part II. Since the crack CR as a tooth mark was detected for each of the third part III and the fourth part IV, each point was -1, and each of the fifth part VI and the sixth part VI had a crack CR as a point. Since it was detected, each point is −1.

  When the evaluation score for each part is calculated as illustrated in FIG. 6, the health degree determination unit 22 then weights the calculated evaluation point for each part to determine the final health degree for each part. Is calculated (step S6). That is, when the health degree determination unit 22 is the evaluation point illustrated in FIG. 7A for each sample illustrated in FIG. 6, for example, the weight ratio of each of the first part I to the sixth part VI is set to, for example, As illustrated in FIG. 7B, “3: 3: 1: 1: 1: 1” is sequentially set. The degree of weighting is set in advance based on medical knowledge that forms the basis of the present invention. Then, the health degree determination unit 22 performs the weighting illustrated in FIG. 7B on the evaluation points illustrated in FIG. 7A, for example, and as a result, the weights after the weighting illustrated in FIG. An evaluation score is calculated for each part (step S6). Thereafter, the health degree determination unit 22 adds the weighted evaluation points illustrated in FIG. 7B for each sample, thereby setting the highest score to 0 without any deduction and the lowest score to the lowest score for all the parts. The sum of the weighted evaluation values for each sample illustrated in FIG. 7C is calculated, which is −50 points, which is the sum of the evaluation points. In the case illustrated in FIG. 7C, the sum of the weighted evaluation values of the sample A is −4 points, the sum of the weighted evaluation values of the sample B is −14 points, and the weight of the sample C is weighted. The sum of the evaluation values is -13 points.

  Thereafter, the health level determination unit 22 calculates the health level to be presented to the subject or the like by display. At this time, for example, when the sum of the evaluation values illustrated in FIG. 7C is obtained, the health level determination unit 22 sets the highest score as 100 points and the lowest score as 0 points in the first embodiment. The health level is calculated by the following equation (1), and the health level information as the calculation result is output to the output control unit 23 (step S7).

Health degree = 100 × [1- {absolute value of sum of evaluation values after weighting / (highest score−lowest score)}]
... (1)
At this time, for example, in the case of sample A, if the example of FIG. 7C is cited, the absolute value of the sum of the weighted evaluation values is “4”, the highest score is 0, and the lowest score is Since it is −50 points, when these are applied to the above equation (1), the health level as the sample A is “92 points” as illustrated in FIG. Hereinafter, it can be understood that the health level as the sample B and the health level as the sample C are “72 points” and “74 points”, respectively, when the formula (1) is similarly used for the sample B and the sample C.

  Thereafter, the output control unit 23 generates a display screen as illustrated in FIG. 8 based on the health level information output from the health level determination unit 22 and outputs the display screen to the display 3, for example, and the health level according to the first embodiment. The subject is presented as a result of the determination process (step S8). At this time, in the case illustrated in FIG. 8, in addition to the health value illustrated in FIG. 7D, the weighted evaluation value illustrated in FIG. It is displayed for easy viewing. In the radar chart illustrated in FIG. 8, each evaluation value standard (a scale such as “−2” and “−6”) is also displayed.

  Thereafter, the processing unit 2 detects whether the power switch as the health level determination device S is turned off or a predetermined end operation is executed in the operation unit 4, and the like, thereby determining the health level according to the first embodiment. It is determined whether or not to end the determination process (step S9). When the health level determination process is continuously executed in the determination in step S9 (step S9; NO), the processing unit 2 returns to step S1 and repeats the health level determination process described above. On the other hand, when the said health degree determination process is complete | finished in determination of step S9 (step S9; YES), the process part 2 complete | finishes the said health degree determination process as it is.

  As described above, according to the health level determination process according to the first embodiment, the features viewed from the viewpoint of health are extracted based on the tongue image information obtained by imaging the front surface of the tongue T ( 2 (see step S40 to step S42 in FIG. 2), the extracted feature is weighted for each part of the tongue T (see step S6 in FIG. 2), and the result is displayed for each part (see FIG. 2). Step S8, see FIG. 8). Therefore, the feature of the tongue T based on medical knowledge can be recognized only by imaging the surface of the tongue T. In addition, since each feature of the surface of the tongue T that has been weighted based on medical knowledge can be recognized, the state of the tongue T (in other words, the tongue T has the tongue more accurately and quickly). Human health condition).

  In addition, since the health level is calculated and displayed based on the result of adding the weighted evaluation points, the specific health level based on the characteristics of each part of the tongue T can be recognized.

  Furthermore, since the evaluation target on the front side of the tongue T is the tip, tongue base, and outer edge, the processing load as the health degree determination device S can be reduced by specifying the evaluation target (limited to the tip and other parts). The feature of the state of the front side of the tongue T can be accurately recognized.

  Furthermore, since the characteristic of each portion of the tongue T is any one of its shape, color and outer edge, the state of the surface on the front side of the tongue T can be accurately recognized based on medical knowledge.

(II) Second Embodiment Next, a second embodiment which is another embodiment according to the present invention will be described with reference to FIG. FIG. 9 is a diagram illustrating determination of the health level according to the second embodiment.

  In the health degree determination process according to the first embodiment described above, the health state of the subject was evaluated using the tongue image TG obtained by capturing the front side of the subject's tongue T with the camera C. On the other hand, in the second embodiment described below, the health condition of the subject is evaluated using a tongue image TG obtained by capturing the back side of the tongue T with the camera C. In the following description, a tongue image obtained by imaging the back side of the tongue T is simply referred to as a “back side tongue image”.

  The hardware configuration of the health degree determination system according to the second embodiment is basically the same as the hardware configuration of the health degree determination system SS according to the first embodiment. Therefore, in the following second embodiment, using the same member numbers as the health determination system SS according to the first embodiment, only the parts and processes different from the health determination system SS are related to the health according to the second embodiment. A degree determination system will be described.

  It is the back side (surface) of the tongue T as exemplified in FIG. 9A that is imaged using the camera C in the health level determination process by the health level determination system according to the second embodiment. Then, as shown in FIG. 9B, the division method for the tongue image TG on the back side corresponds to the first part Ia that hits the entire left side toward the back side of the tongue T and the entire right side toward the back side of the tongue T. The second part IIa and the two parts. These 1st site | part Ia and 2nd site | part IIa are the site | parts preset and divided | segmented so that each may include deep tongue vein VP in the longitudinal direction of the back side of the tongue T, respectively.

  Then, in the health degree determination process according to the second embodiment, the image processing unit 21 extracts features of tongue image information corresponding to the tongue image TG on the back side, and obtains feature information corresponding to the extracted features. Generate and output to the health level determination unit 22.

  Here, the feature according to the second embodiment is that the state of the tongue T corresponding to the back side tongue image TG is determined from the viewpoints of “shape”, “color”, “outer edge”, and “tongue deep vein VP”. Characterize each. More specifically, for example, the presence or absence of “scratches”, “bumps”, or “points” on the back surface of the tongue T is characterized by the above shape, and “color tone” or “color pattern” as the color of the back surface ”Or the like, and the shape of the outer edge of the back side (more specifically, the presence or absence of“ dental marks ”,“ scratches ”or“ dots ”) as the characteristics of the outer edge, and further the tongue The “width and length”, “presence / absence of meandering”, “presence / absence of varicose veins”, “presence / absence of anger”, “presence / absence of left / right difference” and the like of the deep tongue vein VP of T To do.

  Then, the health level determination unit 22 performs the evaluation score calculation process, the weighting process, and the addition process for each of the features as in the health level determination process according to the first embodiment, and further uses the results to determine the health level. The calculation process and display process are executed.

  As described above, according to the health degree determination process according to the second embodiment, the tongue based on the medical knowledge is obtained just by imaging the surface of the tongue T, similarly to the health degree determination process according to the first embodiment. The feature of T can be recognized, and the health condition of a person having the tongue T can be recognized more accurately and quickly.

  Moreover, since the back side (the surface) of the tongue T is the first part Ia and the second part IIa divided into the left and right parts by the dividing line in the longitudinal direction, the part to be evaluated is specified (limited). ), The characteristics of the state of the back side of the tongue T can be accurately recognized while reducing the processing burden as the health degree determination device S.

  In addition, since the feature as each part is any one of its shape, color, outer edge, deep tongue VP shape, etc., the state of the surface on the back side of the tongue T is accurately recognized based on medical knowledge. can do.

  In addition, although the setting method of the evaluation score of the health degree in each of the above-described embodiments is based on the deduction method as described above, in addition to this, first, a normal (ie, healthy) state is defined and the definition is made. When a normal state is detected, a setting method based on a so-called addition method may be used in which only points corresponding to the normal degree are added.

  In each of the above-described embodiments, the total value of the radar chart and the evaluation score for each sample illustrated in FIG. 8 is displayed, but any one of the radar chart or the total value of the evaluation points for each sample is displayed. It may be only.

  Furthermore, the health level can be more effectively determined by accumulating the samples in the recording unit 5 in time series and making them subject to analysis.

  Furthermore, the details of the method for dividing the region of the tongue image TG and the method for setting the evaluation points according to each embodiment are adopted in addition to the division method according to each embodiment as long as it is based on medical knowledge. It is possible.

  As described above, the present invention can be used in the field of a health level determination system that determines the health level and presents it to the subject. In particular, the tongue image TG is acquired to determine the health level. When applied to the field of health judgment systems, particularly remarkable effects can be obtained.

DESCRIPTION OF SYMBOLS 1 Interface 2 Processing part 3 Display 4 Operation part 5 Recording part 20 Image registration part 21 Image processing part 22 Health degree determination part 23 Output control part SS Health degree determination system S Health degree determination apparatus C Camera T Tongue G Image TG Tongue image M1 , M2, M3, M4 Marker CR Crack I, Ia First part
II, IIa 2nd site
III Third part
IV 4th part V 5th part
VI Sixth part

Claims (9)

Acquisition means for acquiring surface information obtained by imaging the surface of the tongue;
Based on the acquired surface information, calculating means for calculating feature information indicating the characteristics of the surface based on medical knowledge;
For each of the divided surfaces obtained by dividing the surface into parts set in advance based on the medical knowledge, the calculated feature information is weighted in advance corresponding to the medical knowledge, Generating means for generating weighting feature information for each of the divided surfaces;
Output means for outputting each generated weighting feature information for each of the divided surfaces;
An information processing apparatus comprising: The information processing apparatus according to claim 1,
Adding means for adding each of the output weighting feature information to generate addition information;
Based on the generated addition information, health level calculation means for calculating health level information indicating the level of health based on the tongue by a preset calculation method based on the medical knowledge;
Further comprising
The information processing apparatus characterized in that the output means outputs the calculated health information. The information processing apparatus according to claim 1 or 2,
The surface is a surface on the front side of the tongue;
Each of the parts is at least one of a tip part, a tongue base part, and a side part on the front side surface. The information processing apparatus according to claim 3.
The feature is any one of a surface shape, a color, and an outer edge shape in each of the divided surfaces,
The information processing apparatus, wherein the calculation unit calculates the feature information indicating any one of the calculation means. The information processing apparatus according to claim 1 or 2,
The surface is a surface on the back side of the tongue;
The information processing apparatus according to claim 1, wherein each of the parts is at least one of divided parts obtained by dividing the surface on the back side into two left and right parts by a dividing line in a longitudinal direction. The information processing apparatus according to claim 5,
The feature is any one of a surface shape, a color, an outer edge shape, and a deep tongue vein shape on each of the divided surfaces,
The information processing apparatus, wherein the calculation unit calculates the feature information indicating any one of the calculation means. The information processing apparatus according to any one of claims 1 to 6,
An imaging device that images the surface to generate the surface information and outputs the surface information;
A presentation device for presenting an output result from the output means;
An information processing system comprising: An acquisition step of acquiring surface information obtained by imaging the surface of the tongue;
Based on the acquired surface information, a calculation step for calculating feature information indicating characteristics of the surface based on medical knowledge;
For each of the divided surfaces obtained by dividing the surface into parts set in advance based on the medical knowledge, the calculated feature information is weighted in advance corresponding to the medical knowledge, A generation step of generating weighting feature information for each of the divided surfaces;
Outputting each of the generated weighting feature information for each of the divided surfaces;
An information processing method comprising: A computer included in an information processing apparatus including an acquisition unit that acquires surface information obtained by imaging the surface of the tongue;
Based on the acquired surface information, calculation means for calculating feature information indicating the characteristics of the surface based on medical knowledge,
For each of the divided surfaces obtained by dividing the surface into parts set in advance based on the medical knowledge, the calculated feature information is weighted in advance corresponding to the medical knowledge, Generating means for generating weighting feature information for each of the divided surfaces; and
Output means for outputting each generated weighting feature information for each of the divided surfaces;
An information processing program characterized by functioning as