Tongue image objective evaluation method and device, medium and electronic equipment

Abstract

The invention discloses an objective evaluation method and device for a tongue picture image, a medium and electronic equipment. The method comprises the following steps: performing image processing on a to-be-evaluated tongue picture image by adopting each preset image processing method to obtain a target feature index of a preset format tower evaluation model index layer corresponding to each influence factor; based on each target feature index, performing calculation processing by adopting a weight calculation mode corresponding to each target feature index to obtain a weight value of each influence factor corresponding to a criterion layer of the preset format tower evaluation model; performing calculation processing based on each weight value to obtain a visual perception feature vector of a target layer of the preset format tower evaluation model; and performing calculation processing based on the visual perception feature vector and preset score values corresponding to a target layer, a criterion layer and an index layer of a preset format tower evaluation model to obtain an objective evaluation result of the tongue picture image. According to the method, objective evaluation of the tongue picture image can be realized, and the evaluation result meets clinical evaluation requirements.

Description

Technical Field

[0001] The present invention relates to the technical field of image evaluation, and in particular to an objective evaluation method, device, storage medium and electronic device for tongue images. Background Art

[0002] Tongue diagnosis in traditional Chinese medicine is developing towards digitization, standardization and objectivity. Tongue coating is an important feature in tongue diagnosis in traditional Chinese medicine, and is of great significance for the determination of TCM syndromes and the diagnosis of diseases. For a long time, the determination of tongue coating has always relied on the observation of TCM physicians with naked eyes, generally including the color of tongue coating (yellow, white, gray, black), the state of tongue coating (rotten, greasy, peeled, absent, etc.), thickness, etc. The development of computer technology has brought convenience to the identification of tongue coating. At present, the research on tongue coating is mostly focused on the automatic identification of the presence, color and state of tongue coating, as well as the evaluation of single tongue features such as color and morphology. There are few studies on the digital description, standardized definition and objective description of the overall degree of tongue coating. The evaluation of traditional tongue coating characteristics is mostly based on the subjective evaluation of doctors. In the process of evaluation, there may be factors that cannot be quantified or measured. At this time, it is necessary to introduce scientific evaluation standards to measure the relative importance of various factors affecting tongue coating, and then provide a reliable basis for decision-making. The overall evaluation of tongue coating is based on theories such as visual psychology and iconography. Therefore, with the help of Gestalt psychology theory and computer image processing technology, the overall evaluation process of tongue coating is decomposed and integrated, and a degree evaluation system that conforms to human vision is designed. In the evaluation process, the subjective opinion of the evaluator is the main basis for determining the weight of the indicator. Although the weight is given according to importance, the artificial weight obviously lacks scientific basis because the amount of information provided by each indicator is not fully considered, so the evaluation cannot fully reflect the actual situation of the evaluation system, resulting in inaccurate evaluation results. Summary of the invention

[0003] In view of this, the present invention provides a tongue image evaluation method, device, storage medium and electronic device, the main purpose of which is to solve the current problems of inaccurate and non-objective tongue image evaluation.

[0004] To solve the above problems, the present application provides an objective evaluation method of tongue images, comprising:

[0005] Using various preset image processing methods to process the tongue image to be evaluated, and obtaining target characteristic indicators of the preset Gestalt evaluation model indicator layer corresponding to various influencing factors of the preset Gestalt evaluation model criterion layer;

[0006] Based on each of the target characteristic indicators, a weight calculation method corresponding to each of the target characteristic indicators is used to perform calculation processing to obtain a weight value of each of the influencing factors corresponding to the criterion layer of the preset Gestalt evaluation model;

[0007] Calculation is performed based on each of the weight values ​​to obtain a visual perception feature vector of a target layer of a preset Gestalt evaluation model;

[0008] Based on the visual perception feature vector and the preset score values ​​corresponding to each of the influencing factors at the preset Gestalt evaluation model criterion layer, calculation and processing are performed to obtain an objective evaluation result of the tongue image.

[0009] Optionally, before using each preset image processing method to process the tongue image to be evaluated, the method further includes: constructing the preset Gestalt evaluation model, specifically including:

[0010] Based on the influencing factors of the tongue image to be evaluated, constructing the criterion layer of the preset Gestalt evaluation model, the influencing factors include: experience factors and behavior factors, the experience factors include: color factors, degree factors and state factors, and the behavior factors include: position factors and area factors;

[0011] Constructing an indicator layer of the preset Gestalt evaluation model based on each characteristic indicator corresponding to each of the influencing factors;

[0012] A target layer of a preset Gestalt evaluation model is constructed based on the visual perception target to construct the preset Gestalt evaluation model.

[0013] Optionally, the tongue image to be evaluated is processed by using various preset image processing methods to obtain target characteristic indicators of the preset Gestalt evaluation model indicator layer corresponding to various influencing factors of the preset Gestalt evaluation model criterion layer, specifically including:

[0014] Using a preset image classification model to perform image recognition processing on the tongue image to be evaluated, and obtaining a first target feature index of the preset Gestalt evaluation model index layer corresponding to each of the empirical factors;

[0015] The tongue image to be evaluated is subjected to image segmentation processing using a preset image segmentation model, and the second target feature index of the preset Gestalt evaluation model index layer corresponding to each of the behavioral factors is calculated.

[0016] Optionally, the image segmentation processing of the tongue image to be evaluated is performed using a preset image segmentation model to calculate the second target feature index of the preset Gestalt evaluation model index layer corresponding to each of the behavioral factors, specifically including:

[0017] The preset image segmentation model is used to separate the tongue quality and tongue coating of the tongue image to be evaluated, and the area value of the tongue coating region, the total area value of the tongue image, and the area value of the circumscribed rectangle of the tongue coating region corresponding to the tongue image to be evaluated are obtained;

[0018] Calculation is performed based on the tongue coating area value, the tongue image total area value, and the tongue coating area circumscribed rectangle area value to obtain a first evaluation parameter value corresponding to the area factor and a second evaluation parameter value corresponding to the position factor;

[0019] Based on the first evaluation parameter value and the second evaluation parameter value, query each preset evaluation parameter range interval to determine the target area parameter range interval corresponding to the first evaluation parameter value and the target position parameter range interval corresponding to the second evaluation parameter value;

[0020] Based on the target area parameter range interval and the target position parameter range interval, a second target characteristic indicator of the preset Gestalt evaluation model indicator layer corresponding to the area factor and a second target characteristic indicator of the preset Gestalt evaluation model indicator layer corresponding to the position factor are determined.

[0021] Optionally, the step of performing calculation based on each of the target characteristic indicators and using a weight calculation method corresponding to each of the target characteristic indicators to obtain a weight value corresponding to each of the influencing factors of the criterion layer of the preset Gestalt evaluation model specifically includes:

[0022] Based on each of the target characteristic indicators, query the preset characteristic scale corresponding table corresponding to each of the influencing factors to obtain the weight calculation method corresponding to each of the target characteristic indicators;

[0023] Based on the image parameter values ​​of the tongue image, the scale parameter values ​​obtained by factor analysis, and the weight calculation methods, calculations are performed to obtain weight values ​​corresponding to the influencing factors.

[0024] Optionally, the calculating and processing based on each of the weight values ​​to obtain the visual perception feature vector of the target layer of the preset Gestalt evaluation model specifically includes:

[0025] Calculate and process each element variable in a preset weight calculation matrix based on each weight value to obtain a weight matrix corresponding to the tongue image;

[0026] Performing calculation processing based on the weight matrix to obtain an initial eigenvector corresponding to the weight matrix;

[0027] The initial feature vector is normalized to obtain a visual perception feature vector of a target layer of a preset Gestalt evaluation model.

[0028] Optionally, the calculation and processing based on the visual perception feature vector and the preset score values ​​corresponding to each layer of the preset Gestalt evaluation model to obtain the objective evaluation result of the tongue image specifically includes:

[0029] Perform multiplication processing based on the visual perception feature vector and the preset score values ​​corresponding to each of the influencing factors of the preset Gestalt evaluation model criterion layer, to obtain initial score values ​​corresponding to each of the influencing factors of the criterion layer of the gestalt evaluation model;

[0030] The initial scoring values ​​are added together to obtain an objective evaluation result of the tongue image.

[0031] In order to solve the above problems, the present application provides an objective evaluation device for tongue images, comprising:

[0032] Image processing module: used for performing image processing on the tongue image to be evaluated by using various preset image processing methods, and determining the target characteristic index of the preset Gestalt evaluation model index layer corresponding to each influencing factor of the preset Gestalt evaluation model criterion layer;

[0033] A weight value calculation module: used to calculate and process based on each of the target characteristic indicators using a weight calculation method corresponding to each of the target characteristic indicators to obtain a weight value of each of the influencing factors corresponding to the criterion layer of the preset Gestalt evaluation model;

[0034] Visual perception feature vector calculation module: used to perform calculation based on each weight value to obtain the visual perception feature vector of the target layer of the preset Gestalt evaluation model;

[0035] Evaluation module: used to calculate and process the preset score values ​​corresponding to each of the influencing factors in the visual perception feature vector and the preset Gestalt evaluation model criterion layer to obtain an objective evaluation result of the tongue image.

[0036] In order to solve the above problem, the present application provides a storage medium, characterized in that the storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned tongue image evaluation method are implemented.

[0037] To solve the above problem, the present application provides an electronic device including at least a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned tongue image evaluation method when executing the computer program on the memory.

[0038] The present application uses image processing technology to perform image recognition and image segmentation processing on the tongue image to be evaluated to determine the target feature index of the preset Gestalt evaluation model index layer corresponding to each influencing factor of the preset Gestalt evaluation model criterion layer, so as to improve the efficiency of obtaining the target feature index of the tongue image; based on each of the target feature indexes, the weight calculation method corresponding to each of the target feature indexes is used to calculate and process, and the weight value corresponding to each of the influencing factors of the preset Gestalt evaluation model criterion layer is obtained; the calculation of the weight value makes the acquisition of the weight value more accurate; based on each of the weight values, the visual perception feature vector of the target layer of the preset Gestalt evaluation model is obtained; based on the visual perception feature vector and the preset score value corresponding to each layer of the preset Gestalt evaluation model, the objective evaluation result of the tongue image is obtained. At the same time as the subjective evaluation, a computer tongue coating weight calculation method is set to correct the subjective evaluation with scientific evaluation indicators. The evaluation system can not only simulate the comprehensive evaluation process of the tongue coating by the human eye, but also refine and quantify the evaluation process from an objective perspective, so that the evaluation result is more accurate. The method in the present application can realize the objective evaluation of the tongue image, and the evaluation result meets the clinical evaluation requirements.

[0039] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0041] Figure 1 A schematic diagram showing a flow chart of an objective evaluation method for tongue images provided in an embodiment of the present application is shown;

[0042] Figure 2 A schematic diagram showing a flow chart of an objective evaluation method of tongue images provided by another embodiment of the present application is shown;

[0043] Figure 3 A structural block diagram of an objective evaluation device for tongue images provided in another embodiment of the present application is shown. DETAILED DESCRIPTION

[0044] Various aspects and features of the present application are described herein with reference to the accompanying drawings.

[0045] It should be understood that various modifications may be made to the embodiments of the present application. Therefore, the above description should not be regarded as limiting, but merely as exemplification of embodiments.

[0046] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the present application and, together with the general description of the present application given above and the detailed description of the embodiments given below, serve to explain the principles of the present application.

[0047] These and other characteristics of the present application will become apparent from the following description of a preferred form of embodiment given as a non-limiting example with reference to the accompanying drawings.

[0048] It should also be understood that although the present application has been described with reference to some specific examples, those skilled in the art will be able to readily implement many other equivalent forms of the present application.

[0049] The above and other aspects, features and advantages of the present application will become more apparent in view of the following detailed description when taken in conjunction with the accompanying drawings.

[0050] Specific embodiments of the present application are described hereinafter with reference to the accompanying drawings; however, it should be understood that the embodiments applied for are merely examples of the present application, which may be implemented in a variety of ways. Well-known and / or repeated functions and structures are not described in detail to avoid unnecessary or redundant details that obscure the present application. Therefore, the specific structural and functional details applied for herein are not intended to be limiting, but merely serve as the basis and representative basis for the claims to guide those skilled in the art to use the present application in a variety of ways with substantially any suitable detailed structure.

[0051] This specification may use the phrases "in one embodiment," "in another embodiment," "in yet another embodiment," or "in other embodiments," all of which may refer to one or more of the same or different embodiments according to the present application.

[0052] The present application embodiment provides a tongue image evaluation method, such as Figure 1 As shown, including:

[0053] Step S101: using various preset image processing methods to process the tongue image to be evaluated, and obtaining target characteristic indicators of the preset Gestalt evaluation model indicator layer corresponding to various influencing factors of the preset Gestalt evaluation model criterion layer;

[0054] In the specific implementation process of this step, the preset image classification model is used to perform image recognition processing on the tongue image to be evaluated, and the first target feature index of the preset Gestalt evaluation model index layer corresponding to each of the empirical factors is obtained; the empirical factors include: color factors, degree factors, and state factors. The preset image segmentation model is used to perform image segmentation processing on the tongue image to be evaluated, and the second target feature index of the preset Gestalt evaluation model index layer corresponding to each of the behavioral factors is calculated. The behavioral factors include: location factors and area factors. Specifically, a preset image segmentation model is used to separate the tongue quality and tongue coating of the tongue image to be evaluated, and the area value of the tongue coating region, the total area value of the tongue image and the area value of the circumscribed rectangle of the tongue coating region corresponding to the tongue image to be evaluated are obtained; calculation and processing are performed based on the area value of the tongue coating region and the total area value of the tongue image to obtain an evaluation parameter value of the area factor; based on the evaluation parameter value, each preset evaluation parameter range interval is queried to determine the target evaluation parameter range interval corresponding to the evaluation parameter value; based on the target evaluation parameter range interval, the second target feature indicator of the preset Gestalt evaluation model indicator layer corresponding to each of the behavioral factors is determined, and each of the target feature indicators includes: each of the first target feature indicators and each of the second target feature indicators.

[0055] Step S102: Based on each of the target characteristic indicators, a weight calculation method corresponding to each of the target characteristic indicators is used to perform calculation processing to obtain a weight value of each of the influencing factors corresponding to the criterion layer of the preset Gestalt evaluation model;

[0056] During the specific implementation of this step, based on each of the target feature indicators, each preset feature scale correspondence table is queried to obtain a weight calculation method corresponding to each of the target feature indicators; based on each image parameter value of the tongue image, the scale parameter value obtained by factor analysis and each of the weight calculation methods, calculations are performed to obtain weight values ​​corresponding to each of the influencing factors.

[0057] Step S103: performing calculation based on each of the weight values ​​to obtain a visual perception feature vector of a target layer of a preset Gestalt evaluation model;

[0058] During the specific implementation of this step, each element variable in the preset weight calculation matrix is ​​calculated based on each weight value to obtain a weight matrix corresponding to the tongue image; calculation processing is performed based on the weight matrix to obtain an initial feature vector corresponding to the weight matrix; and normalization processing is performed on the initial feature vector to obtain a visual perception feature vector of the target layer of the preset Gestalt evaluation model.

[0059] Step S104: Calculate and process the preset score values ​​corresponding to the influencing factors of the preset Gestalt evaluation model criterion layer based on the visual perception feature vector to obtain an objective evaluation result of the tongue image.

[0060] In the specific implementation process of this step, multiplication operations are performed on the visual perception feature vector and the preset scoring values ​​corresponding to each layer of the preset Gestalt evaluation model to obtain initial scoring values ​​corresponding to each layer of the tower evaluation model; and addition operations are performed on each of the initial scoring values ​​to obtain an objective evaluation result of the tongue image.

[0061] The present application adopts image processing technology to perform image recognition and image segmentation processing on the tongue image to be evaluated to determine the target feature index of the preset Gestalt evaluation model index layer corresponding to each tongue image influencing factor of the preset Gestalt evaluation model criterion layer, so as to improve the efficiency of obtaining the image target feature index; based on each of the target feature indexes, the weight calculation method corresponding to each of the target feature indexes is used to calculate and process, and the weight value corresponding to each of the influencing factors of the preset Gestalt evaluation model criterion layer is obtained; the calculation of the weight value makes the acquisition of the weight value more accurate; based on each of the weight values, the visual perception feature vector of the target layer of the preset Gestalt evaluation model is obtained; based on the visual perception feature vector and the preset score value corresponding to each layer of the preset Gestalt evaluation model, the objective evaluation result of the tongue image is obtained. At the same time as the subjective evaluation, a computer tongue coating weight calculation method is set to correct the subjective evaluation with scientific evaluation indicators. The evaluation system can not only simulate the comprehensive evaluation process of the tongue coating by the human eye, but also refine and quantify the evaluation process from an objective perspective, so that the evaluation result is more accurate. The method in this application can realize the objective evaluation of tongue images, breaking through the limitation of traditional tongue image judgment that relies solely on subjective judgment, and the evaluation results meet the needs of clinical evaluation.

[0062] Another embodiment of the present application provides another tongue image evaluation method, such as Figure 2 As shown. Includes:

[0063] Step S201: constructing a preset Gestalt evaluation model;

[0064] In the specific implementation process of this step, based on the various influencing factors of the tongue image to be evaluated, the criterion layer of the preset Gestalt evaluation model is constructed, the influencing factors include: experience factors and behavioral factors, the experience factors include: color factors, degree factors and state factors, the behavioral factors include: position factors and area factors; the preset Gestalt evaluation model includes at least three layers, namely the target layer, the criterion layer and the indicator layer, the target layer (D) is the visual perception layer; the criterion layer (Z) is the layer of various influencing factors, and the indicator layer (F) is the characteristic indicator layer corresponding to each of the influencing factors. For example: the tongue image is evaluated, and the influencing factors corresponding to the criterion layer in the preset Gestalt evaluation model are determined to include: experience factors such as color factors, degree factors and state factors; and also include behavioral factors such as area factors and position factors. The indicator layer of the preset Gestalt evaluation model is constructed based on the characteristic indicators corresponding to each of the influencing factors; for example: the characteristic indicators corresponding to the color factor are white, yellow, and black; the characteristic indicators corresponding to the degree factor are thin and thick; the characteristic indicators corresponding to the state factor are normal, dry, smooth, rotten, and greasy; the characteristic indicators corresponding to the area factor are: few, medium, and many; the characteristic indicators corresponding to the position factor are scattered, moderate, and clustered. The target layer of the preset Gestalt evaluation model is constructed based on the visual perception target to construct the preset Gestalt evaluation model. The preset Gestalt evaluation model is as follows

[0065] As shown in Table 1:

[0066]

[0067] Table 1

[0068] Step S202: using a preset image classification model to perform image recognition processing on the tongue image to be evaluated, and obtaining a first target feature index of the preset Gestalt evaluation model index layer corresponding to each of the empirical factors;

[0069] In the specific implementation process of this step, the preset image classification model can be an image classification model obtained by using a neural network training method; the specific process of using the neural network training method to train the image classification model is: first, collect a number of historical tongue image data including different colors. Then preprocess each of the tongue images, and the preprocessing includes scaling, cropping and other operations on a number of historical tongue images to facilitate the training of the neural network. Then, build a neural network model: select an appropriate neural network structure, and use a convolutional neural network (CNN) to process the image data to build a neural network model including an input layer, a convolution layer, a pooling layer, a fully connected layer and an output layer. Mark and divide the data of each of the historical tongue images: mark the collected historical tongue image data, that is, assign corresponding labels such as color and degree to each tongue image. Then divide the data set into a training set and a test set, usually using 70% of the data as the training set and 30% of the data as the test set; use the training set and the test set to perform model training; specifically: use the training set data to train the constructed neural network model, and continuously adjust the model parameters through the back propagation algorithm so that the model can learn the characteristics and classification rules of the tongue image, and train the classification model; use the test set data to evaluate the trained model, calculate the model's accuracy, precision, recall rate and other indicators, and tune the model according to the evaluation results, including adjusting the network structure, optimizing parameters, etc., until the adjusted network structure and optimized parameters meet the preset requirements to obtain the image classification model. The image classification model in this application can also use other classification methods for model training, and this application does not limit the training method of the classification model. Use the trained image classification model to identify and process the tongue image to be evaluated, and obtain the first target feature indicator of the preset Gestalt evaluation model indicator layer corresponding to each of the empirical factors.

[0070] Step S203: using a preset image segmentation model to perform tongue quality and tongue coating separation processing on the tongue image to be evaluated, and obtaining the tongue coating area value, the tongue image total area value, and the tongue coating area circumscribed rectangle area value corresponding to the tongue image to be evaluated;

[0071] In the specific implementation of this step, the preset image segmentation model in this application can adopt traditional image processing technology. Specifically, the image is first preprocessed, and the tongue image is subtracted from the background by manual or automatic methods. Then the image is feature extracted to obtain the tongue quality area image and the tongue coating area image. Specifically, according to the color difference of the tongue quality and the tongue coating in the image, the tongue quality and the tongue coating are distinguished by clustering, threshold segmentation method or color space conversion method. An appropriate segmentation threshold or color threshold can be selected to divide the image into two areas: the tongue quality image area and the tongue coating image area. The segmentation threshold and color threshold can be set according to actual needs. Then, based on the tongue quality and tongue coating segmentation results, the tongue coating area area value, the tongue image total area value and the tongue coating area circumscribed rectangle area value corresponding to the tongue image to be evaluated are read. The image segmentation model described in this application can also be constructed by a deep learning method. This application does not limit the construction method of the image segmentation model. The preset image segmentation model is used to separate the tongue quality and tongue coating of the tongue image to obtain the tongue coating area area value Area corresponding to the tongue image to be evaluated. tai 、Total tongue area value Area all And the area value of the rectangle surrounding the tongue coating area juxing .

[0072] Step S204: performing calculation based on the tongue coating area value, the tongue image total area value and the tongue coating area circumscribed rectangle area value to obtain a first evaluation parameter value corresponding to the area factor and a second evaluation parameter value corresponding to the position factor;

[0073] In the specific implementation process of this step, a division operation is performed based on the tongue coating area value and the tongue image total area value to calculate the first evaluation parameter value of the area factor. The calculation mathematical formula of the first evaluation parameter value h of the area factor is as shown in the following formula 1:

[0074]

[0075] A division operation is performed based on the area value of the tongue coating region and the area value of the circumscribed rectangle of the tongue coating region to calculate a second evaluation parameter value of the position factor. The calculation mathematical formula of the second evaluation parameter value p of the position factor is as shown in the following formula 2:

[0076]

[0077] Step S205: querying each preset evaluation parameter range interval based on the first evaluation parameter value and the second evaluation parameter value to determine the target area parameter range interval corresponding to the first evaluation parameter value and the target position parameter range interval corresponding to the second evaluation parameter value;

[0078] In the specific implementation process of this step, the value ranges of the first evaluation parameter value and the second evaluation parameter value are pre-set for the area factor and the location factor. For example, for the area factor, the value interval of the first evaluation parameter value is divided into three area parameter range intervals. The first area parameter range interval is: the first evaluation parameter value is greater than the first preset threshold value; the second area parameter range interval is: the first evaluation parameter value is greater than the second preset threshold value and less than or equal to the first preset threshold value; the third area parameter range interval is: the first evaluation parameter value is greater than the third preset threshold value and less than or equal to the second preset threshold value. The first preset threshold value can be 0.6, the second preset threshold value can be 0.3, and the third preset threshold value can be 0.05, and the first preset threshold value, the second preset threshold value and the third preset threshold value can be set according to actual needs. Based on the calculated first evaluation parameter value h, the above three area parameter range intervals are queried, and the area parameter range interval into which the first evaluation parameter value h falls is determined as the target area parameter range interval.

[0079] In view of the location factor, the value interval of the second evaluation parameter value is divided into three location parameter range intervals. The first location parameter range interval is: the second evaluation parameter value is greater than the first preset threshold value; the second area parameter range interval is: the first evaluation parameter value is greater than the second preset threshold value and less than or equal to the first preset threshold value; the third area parameter range interval is: the first evaluation parameter value is greater than the third preset threshold value and less than or equal to the second preset threshold value. The first preset threshold value can be 0.6, the second preset threshold value can be 0.3, and the third preset threshold value can be 0.05, and the first preset threshold value, the second preset threshold value and the third preset threshold value can be set according to actual needs. Based on the calculated second evaluation parameter value p, the above three location parameter range intervals are queried, and the location parameter range interval in which the second evaluation parameter value p falls is determined as the target location parameter range interval.

[0080] Step S206: determining a second target characteristic index of a preset Gestalt evaluation model index layer corresponding to an area factor and a second target characteristic index of a preset Gestalt evaluation model index layer corresponding to a position factor based on the target area parameter range interval and the target position parameter range interval;

[0081] In the specific implementation of this step, for the area factor, the three area parameter range intervals correspond to three different area indicators respectively; less tongue coating corresponds to the first area parameter range interval; medium tongue coating corresponds to the second area parameter range interval; and more tongue coating corresponds to the third area parameter range interval. For the position factor, the three position parameter range intervals correspond to three different position indicators respectively; dispersed tongue coating corresponds to the first position parameter range interval; moderate tongue coating corresponds to the second position parameter range interval; and concentrated tongue coating corresponds to the third position parameter range interval. Therefore, based on the target area parameter range interval and the target position parameter range interval, the second target characteristic indicator of the preset Gestalt evaluation model indicator layer corresponding to the area factor and the second target characteristic indicator of the preset Gestalt evaluation model indicator layer corresponding to the position factor are determined.

[0082] Step S207: Based on each of the target characteristic indicators, query the preset characteristic scale corresponding table corresponding to each of the influencing factors to obtain the weight calculation method corresponding to each of the target characteristic indicators;

[0083] In the specific implementation process of this step, the preset color feature scale correspondence table in each preset feature scale correspondence table is shown in the following Table 2:

[0084]

[0085] Table 2

[0086] Among them, a corresponds to the weight variable corresponding to the color factor, L is the L component of the pixel value of the tongue image in LAB space; B is the B component of the LAB space pixel value.

[0087] The preset degree characteristic scale correspondence table in each preset characteristic scale correspondence table is shown in the following Table 3:

[0088]

[0089] Among them, b corresponds to the weight variable corresponding to the degree factor.

[0090] Table 3

[0091] The preset state characteristic scale correspondence table in each preset characteristic scale correspondence table is shown in the following Table 4:

[0092]

[0093] Table 4

[0094] Wherein, c corresponds to the weight variable corresponding to the state factor.

[0095] The preset area characteristic scale correspondence table in each preset characteristic scale correspondence table is shown in the following Table 5:

[0096]

[0097] Table 5

[0098] Wherein, d corresponds to the weight variable corresponding to the area factor.

[0099] The preset position characteristic scale correspondence table in each preset characteristic scale correspondence table is shown in the following Table 6:

[0100]

[0101] Table 6

[0102] Wherein, e corresponds to the weight variable corresponding to the position factor; F, M, and N in Tables 2 to 6 are scale parameter values, and the scale parameter values ​​are determined in the manner shown in Table 7 below:

[0103]

[0104] Table 7

[0105] The subjective determination of parameter values ​​according to the requirements of F, M, and N values ​​in Table 7 combined with actual needs is obtained by comparing the severity of the two elements at different layers according to the actual situation by experts, and the final values ​​of F, M, and N satisfy M>0, F>M, and N>M at the same time. For example, the subjectively determined values ​​of F, M, and N are 1, 5, 10, etc., respectively. This application does not limit the values ​​of F, M, and N, as long as the above conditions are met, and F, M, and N are all positive integers greater than 0 and less than 10. Based on each of the target feature indicators, query each preset feature scale corresponding table to obtain the weight calculation method corresponding to each of the target feature indicators, for example: when the preset image classification model is used to perform image recognition processing on the tongue image to be evaluated, the first target feature indicator of the preset Gestalt evaluation model indicator layer corresponding to each of the empirical factors is obtained, specifically, the first target feature indicator corresponding to the recognition result is: white, thin, normal; the weight calculation method corresponding to the first target feature indicator white is a=M·j; the weight calculation method corresponding to the first target feature indicator thin is b=M; the weight calculation method corresponding to the first target feature indicator normal is c=1, etc. When the second target feature indicator of the preset Gestalt evaluation model indicator layer corresponding to the area factor and the second target feature indicator of the preset Gestalt evaluation model indicator layer corresponding to the position factor are determined based on the target area parameter range interval and the target position parameter range interval; for example: when the second target feature indicator corresponding to the area factor is small, the corresponding area factor weight calculation method is d=N·h; when the second target feature indicator corresponding to the position factor is scattered, the corresponding position factor weight calculation method is e=N·p.

[0106] Step S208: performing calculations based on the image parameter values ​​of the tongue image, the scale parameter values ​​obtained by factor analysis, and the weight calculation methods to obtain weight values ​​corresponding to the influencing factors;

[0107] In the specific implementation process of this step, based on the values ​​of the image parameter values ​​L and B of the tongue image, the values ​​of the scale parameter values ​​F, M, and N obtained by factor analysis and the weight calculation methods, the weight values ​​corresponding to the influencing factors are calculated and processed. After calculation, the weight values ​​corresponding to the weight variables a, b, c, d, and e corresponding to the influencing factors can be obtained.

[0108] Step S209: performing calculation based on each of the weight values ​​to obtain a visual perception feature vector of the target layer of the preset Gestalt evaluation model;

[0109] In the specific implementation process of this step, each element variable in the preset weight calculation matrix Z is calculated and processed based on each weight value to obtain a weight matrix corresponding to the tongue image; the preset weight calculation matrix is ​​shown in the following formula 3:

[0110]

[0111] Substitute the calculated weight values ​​a, b, c, d, and e into the preset matrix to calculate the initial eigenvector corresponding to the weight matrix; perform normalization on the initial eigenvector to obtain the visual perception eigenvector of the target layer of the preset Gestalt evaluation model. The visual perception eigenvector can be expressed as the following formula 4:

[0112] α'={Q1, Q2, Q3, Q4, Q5} (4)

[0113] Step S210: Calculate and process the preset score values ​​corresponding to the influencing factors of the preset Gestalt evaluation model criterion layer based on the visual perception feature vector to obtain an objective evaluation result of the tongue image.

[0114] In the specific implementation process of this step, the visual perception feature vector and the preset score values ​​corresponding to each layer of the preset Gestalt evaluation model are multiplied to obtain the initial score values ​​corresponding to each layer of the Gestalt evaluation model; each initial score value is added to obtain the objective evaluation result of the tongue image. The calculation formula of the tongue image is as follows:

[0115] As shown in formula 5:

[0116]

[0117] Among them, T i is the initial score value corresponding to each layer of the tower evaluation model, α' is the visual perception feature vector, K is the tongue coating evaluation result value, and the larger the k value is, the higher the severity of the tongue coating is.

[0118] The present application constructs a preset Gestalt evaluation model to divide the influencing factors and characteristic indicators of the tongue image into layers; uses a preset image classification model to perform image recognition processing on the tongue image to be evaluated, and obtains the first target characteristic indicator of the preset Gestalt evaluation model indicator layer corresponding to each of the empirical factors; uses a preset image segmentation model to perform tongue quality and tongue coating separation processing on the tongue image to be evaluated, and obtains the area value of the tongue coating area, the total area value of the tongue image, and the area value of the circumscribed rectangle of the tongue coating area corresponding to the tongue image to be evaluated; calculates and processes based on the area value of the tongue coating area, the total area value of the tongue image, and the area value of the circumscribed rectangle of the tongue coating area to obtain the first evaluation parameter value corresponding to the area factor and the position factor. a second evaluation parameter value corresponding to the first evaluation parameter value and the second evaluation parameter value; query each preset evaluation parameter range interval based on the first evaluation parameter value and the second evaluation parameter value, and determine the target area parameter range interval corresponding to the first evaluation parameter value and the target position parameter range interval corresponding to the second evaluation parameter value; determine the second target characteristic indicator of the preset Gestalt evaluation model indicator layer corresponding to the area factor and the second target characteristic indicator of the preset Gestalt evaluation model indicator layer corresponding to the position factor based on the target area parameter range interval and the target position parameter range interval; with the help of Gestalt psychology theory and computer image processing technology, the overall evaluation process of tongue coating is decomposed and integrated, and a degree evaluation system that conforms to human vision is designed. Based on each of the target feature indicators, query each preset feature scale corresponding table to obtain the weight calculation method corresponding to each of the target feature indicators; based on each image parameter value of the tongue image, the scale parameter value obtained by factor analysis and each of the weight calculation methods, calculate and process to obtain the weight value corresponding to each of the influencing factors; based on each of the weight values, calculate and process to obtain the visual perception feature vector of the target layer of the preset Gestalt evaluation model; calculate and process based on the visual perception feature vector and the preset score value corresponding to each layer of the preset Gestalt evaluation model to obtain the objective evaluation result of the tongue image. At the same time as the subjective evaluation, a computer tongue coating weight calculation method is set to correct the subjective evaluation with scientific evaluation indicators. The evaluation system can simulate the comprehensive evaluation process of the tongue coating by the human eye, and can also refine and quantify the evaluation process from an objective perspective, so that the evaluation result is more accurate. The method in the present application can realize the objective evaluation of tongue image, breaking through the limitation of traditional tongue image judgment relying solely on subjective judgment, and the evaluation result meets the clinical evaluation needs.

[0119] Another embodiment of the present application provides an objective evaluation device for tongue images, such as Figure 3 As shown, including:

[0120] Image processing module 1: used to process the tongue image to be evaluated by using various preset image processing methods, and determine the target characteristic index of the preset Gestalt evaluation model index layer corresponding to each influencing factor of the preset Gestalt evaluation model criterion layer;

[0121] Weight value calculation module 2: used to calculate and process based on each of the target characteristic indicators using a weight calculation method corresponding to each of the target characteristic indicators to obtain the weight value of each of the influencing factors corresponding to the criterion layer of the preset Gestalt evaluation model;

[0122] Visual perception feature vector calculation module 3: used to perform calculation based on each of the weight values ​​to obtain the visual perception feature vector of the target layer of the preset Gestalt evaluation model;

[0123] Evaluation module 4: used to perform calculations based on the visual perception feature vector and the preset score values ​​corresponding to each of the influencing factors at the preset Gestalt evaluation model criterion layer to obtain an objective evaluation result of the tongue image.

[0124] In the specific implementation process, the tongue image evaluation device also includes a preset Gestalt evaluation model construction module, and the preset Gestalt evaluation model construction module is specifically used to: construct the criterion layer of the preset Gestalt evaluation model based on the various influencing factors of the tongue image to be evaluated, the influencing factors include: experience factors and behavior factors, the experience factors include: color factors, degree factors and state factors, and the behavior factors include: position factors and area factors; construct the indicator layer of the preset Gestalt evaluation model based on the characteristic indicators corresponding to each of the influencing factors; construct the target layer of the preset Gestalt evaluation model based on the visual perception target, so as to construct the preset Gestalt evaluation model.

[0125] During the specific implementation process, the image processing module 1 is specifically used to: use a preset image classification model to perform image recognition processing on the tongue image to be evaluated, and obtain the first target feature index of the preset Gestalt evaluation model indicator layer corresponding to each of the empirical factors; use a preset image segmentation model to perform image segmentation processing on the tongue image to be evaluated, and calculate and obtain the second target feature index of the preset Gestalt evaluation model indicator layer corresponding to each of the behavioral factors.

[0126] During the specific implementation process, the image processing module 1 is also used to: use a preset image segmentation model to separate the tongue quality and tongue coating of the tongue image to be evaluated, and obtain the area value of the tongue coating area, the total area value of the tongue image, and the area value of the circumscribed rectangle of the tongue coating area corresponding to the tongue image to be evaluated; perform calculations based on the area value of the tongue coating area, the total area value of the tongue image, and the area value of the circumscribed rectangle of the tongue coating area to obtain a first evaluation parameter value corresponding to the area factor and a second evaluation parameter value corresponding to the position factor; query each preset evaluation parameter range interval based on the first evaluation parameter value and the second evaluation parameter value, and determine the target area parameter range interval corresponding to the first evaluation parameter value and the target position parameter range interval corresponding to the second evaluation parameter value; determine the second target feature indicator of the preset Gestalt evaluation model indicator layer corresponding to the area factor and the second target feature indicator of the preset Gestalt evaluation model indicator layer corresponding to the position factor based on the target area parameter range interval and the target position parameter range interval.

[0127] During the specific implementation process, the weight value calculation module 2 is specifically used to: based on each of the target feature indicators, query each preset feature scale correspondence table to obtain a weight calculation method corresponding to each of the target feature indicators; based on each image parameter value of the tongue image, the scale parameter value obtained by factor analysis and each of the weight calculation methods, calculate and process to obtain a weight value corresponding to each of the influencing factors.

[0128] During the specific implementation process, the visual perception feature vector calculation module 3 is specifically used to: calculate and process each element variable in the preset weight calculation matrix based on each weight value to obtain a weight matrix corresponding to the tongue image; calculate and process based on the weight matrix to obtain an initial feature vector corresponding to the weight matrix; normalize the initial feature vector to obtain the visual perception feature vector of the target layer of the preset Gestalt evaluation model.

[0129] In the specific implementation process, the evaluation module 4 is specifically used for: performing multiplication operations based on the visual perception feature vector and the preset scoring values ​​corresponding to each layer of the preset Gestalt evaluation model to obtain the initial scoring values ​​corresponding to each layer of the tower evaluation model; performing addition operations on each of the initial scoring values ​​to obtain the objective evaluation results of the tongue image.

[0130] The present application adopts image processing technology to perform image recognition and image segmentation processing on the tongue image to be evaluated to determine the target feature index of the preset Gestalt evaluation model index layer corresponding to each influencing factor of the preset Gestalt evaluation model criterion layer, so as to improve the efficiency of obtaining the target feature index of the tongue image; based on each of the target feature indexes, the weight calculation method corresponding to each of the target feature indexes is used to calculate and process, and the weight value corresponding to each of the influencing factors of the preset Gestalt evaluation model criterion layer is obtained; the calculation of the weight value makes the acquisition of the weight value more accurate; based on each of the weight values, the visual perception feature vector of the target layer of the preset Gestalt evaluation model is obtained; based on the visual perception feature vector and the preset score value corresponding to each layer of the preset Gestalt evaluation model, the objective evaluation result of the tongue image is obtained. At the same time as the subjective evaluation, a computer tongue coating weight calculation method is set to correct the subjective evaluation with scientific evaluation indicators. The evaluation system can not only simulate the comprehensive evaluation process of the tongue coating by the human eye, but also refine and quantify the evaluation process from an objective perspective, so that the evaluation result is more accurate.

[0131] Another embodiment of the present application provides a storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the following method steps are implemented:

[0132] Step 1: using various preset image processing methods to process the tongue image to be evaluated, and obtaining target characteristic indicators of the preset Gestalt evaluation model indicator layer corresponding to various influencing factors of the preset Gestalt evaluation model criterion layer;

[0133] Step 2: Based on each of the target characteristic indicators, a weight calculation method corresponding to each of the target characteristic indicators is used to perform calculation processing to obtain a weight value of each of the influencing factors corresponding to the criterion layer of the preset Gestalt evaluation model;

[0134] Step 3: Calculate and process based on each of the weight values ​​to obtain a visual perception feature vector of the target layer of the preset Gestalt evaluation model;

[0135] Step 4: Calculate and process the preset score values ​​corresponding to the influencing factors of the visual perception feature vector and the preset Gestalt evaluation model criterion layer to obtain an objective evaluation result of the tongue image.

[0136] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0137] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0138] The specific implementation process of the above method steps can be found in the embodiments of the above-mentioned method for evaluating any tongue image, and this embodiment will not be repeated here.

[0139] The present application adopts image processing technology to perform image recognition and image segmentation processing on the tongue image to be evaluated to determine the target feature index of the preset Gestalt evaluation model index layer corresponding to each influencing factor of the preset Gestalt evaluation model criterion layer, so as to improve the efficiency of obtaining the target feature index of the tongue image; based on each of the target feature indexes, the weight calculation method corresponding to each of the target feature indexes is used to calculate and process, and the weight value corresponding to each of the influencing factors of the preset Gestalt evaluation model criterion layer is obtained; the calculation of the weight value makes the acquisition of the weight value more accurate; based on each of the weight values, the visual perception feature vector of the target layer of the preset Gestalt evaluation model is obtained; based on the visual perception feature vector and the preset score value corresponding to each layer of the preset Gestalt evaluation model, the objective evaluation result of the tongue image is obtained. At the same time as the subjective evaluation, a computer tongue coating weight calculation method is set to correct the subjective evaluation with scientific evaluation indicators. The evaluation system can not only simulate the comprehensive evaluation process of the tongue coating by the human eye, but also refine and quantify the evaluation process from an objective perspective, so that the evaluation result is more accurate. The method in this application can realize the objective evaluation of tongue images, breaking through the limitation of traditional tongue image judgment that relies solely on subjective judgment, and the evaluation results meet the clinical evaluation needs.

[0140] Another embodiment of the present application provides an electronic device, which can be a server, and the electronic device includes a processor, a memory, a network interface and a database connected through a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile and / or volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external client through a network connection. When the electronic device program is executed by the processor, it implements the functions or steps of a tongue image evaluation method server side.

[0141] In one embodiment, an electronic device is provided, which may be a client. The electronic device includes a processor, a memory, a network interface, a display screen, and an input device connected via a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external server via a network connection. When the electronic device program is executed by the processor, the functions or steps on the client side of a tongue image evaluation method are implemented.

[0142] Another embodiment of the present application provides an electronic device, comprising at least a memory and a processor, wherein the memory stores a computer program, and the processor implements the following method steps when executing the computer program in the memory:

[0143] Step 1: using various preset image processing methods to process the tongue image to be evaluated, and obtaining target characteristic indicators of the preset Gestalt evaluation model indicator layer corresponding to various influencing factors of the preset Gestalt evaluation model criterion layer;

[0144] Step 2: Based on each of the target characteristic indicators, a weight calculation method corresponding to each of the target characteristic indicators is used to perform calculation processing to obtain a weight value of each of the influencing factors corresponding to the criterion layer of the preset Gestalt evaluation model;

[0145] Step 3: Calculate and process based on each of the weight values ​​to obtain a visual perception feature vector of the target layer of the preset Gestalt evaluation model;

[0146] Step 4: Calculate and process the preset score values ​​corresponding to the influencing factors of the visual perception feature vector and the preset Gestalt evaluation model criterion layer to obtain an objective evaluation result of the tongue image.

[0147] The specific implementation process of the above method steps can be found in the embodiments of the above-mentioned method for evaluating any tongue image, and this embodiment will not be repeated here.

[0148] The present application adopts image processing technology to perform image recognition and image segmentation processing on the tongue image to be evaluated to determine the target feature index of the preset Gestalt evaluation model index layer corresponding to each influencing factor of the preset Gestalt evaluation model criterion layer, so as to improve the efficiency of obtaining the target feature index of the tongue image; based on each of the target feature indexes, the weight calculation method corresponding to each of the target feature indexes is used to calculate and process, and the weight value corresponding to each of the influencing factors of the preset Gestalt evaluation model criterion layer is obtained; the calculation of the weight value makes the acquisition of the weight value more accurate; based on each of the weight values, the visual perception feature vector of the target layer of the preset Gestalt evaluation model is obtained; based on the visual perception feature vector and the preset score value corresponding to each layer of the preset Gestalt evaluation model, the objective evaluation result of the tongue image is obtained. At the same time as the subjective evaluation, a computer tongue coating weight calculation method is set to correct the subjective evaluation with scientific evaluation indicators. The evaluation system can not only simulate the comprehensive evaluation process of the tongue coating by the human eye, but also refine and quantify the evaluation process from an objective perspective, so that the evaluation result is more accurate. The method in this application can realize the objective evaluation of tongue images, breaking through the limitation of traditional tongue image judgment that relies solely on subjective judgment, and the evaluation results meet the clinical evaluation needs.

[0149] The above embodiments are only exemplary embodiments of the present application and are not intended to limit the present application. The protection scope of the present application is defined by the claims. Those skilled in the art may make various modifications or equivalent substitutions to the present application within the essence and protection scope of the present application, and such modifications or equivalent substitutions shall also be deemed to fall within the protection scope of the present application.

Claims

1. An objective evaluation method for tongue image, characterized in that: include: Using various preset image processing methods to process the tongue image to be evaluated, and obtaining target characteristic indicators of the preset Gestalt evaluation model indicator layer corresponding to various influencing factors of the preset Gestalt evaluation model criterion layer; Based on each of the target characteristic indicators, a weight calculation method corresponding to each of the target characteristic indicators is used to perform calculation processing to obtain a weight value of each of the influencing factors corresponding to the criterion layer of the preset Gestalt evaluation model; Calculation is performed based on each of the weight values ​​to obtain a visual perception feature vector of a target layer of a preset Gestalt evaluation model; Based on the visual perception feature vector and the preset score values ​​corresponding to each of the influencing factors at the preset Gestalt evaluation model criterion layer, calculation and processing are performed to obtain an objective evaluation result of the tongue image.

2. The method according to claim 1, characterized in that Before using each preset image processing method to process the tongue image to be evaluated, the method further includes: constructing the preset Gestalt evaluation model, specifically including: Based on the influencing factors of the tongue image to be evaluated, constructing the criterion layer of the preset Gestalt evaluation model, the influencing factors include: experience factors and behavior factors, the experience factors include: color factors, degree factors and state factors, and the behavior factors include: position factors and area factors; Constructing an indicator layer of the preset Gestalt evaluation model based on each characteristic indicator corresponding to each of the influencing factors; A target layer of a preset Gestalt evaluation model is constructed based on the visual perception target to construct the preset Gestalt evaluation model.

3. The method according to claim 2, characterized in that The method of using each preset image processing method to process the tongue image to be evaluated to obtain the target characteristic index of the preset Gestalt evaluation model index layer corresponding to each influencing factor of the preset Gestalt evaluation model criterion layer specifically includes: Using a preset image classification model to perform image recognition processing on the tongue image to be evaluated, and obtaining a first target feature index of the preset Gestalt evaluation model index layer corresponding to each of the empirical factors; The tongue image to be evaluated is subjected to image segmentation processing using a preset image segmentation model, and the second target feature index of the preset Gestalt evaluation model index layer corresponding to each of the behavioral factors is calculated.

4. The method according to claim 3, characterized in that The method of using a preset image segmentation model to perform image segmentation processing on the tongue image to be evaluated, and calculating the second target feature index of the preset Gestalt evaluation model index layer corresponding to each of the behavioral factors, specifically includes: The preset image segmentation model is used to separate the tongue quality and tongue coating of the tongue image to be evaluated, and the area value of the tongue coating region, the total area value of the tongue image, and the area value of the circumscribed rectangle of the tongue coating region corresponding to the tongue image to be evaluated are obtained; Calculation is performed based on the tongue coating area value, the tongue image total area value, and the tongue coating area circumscribed rectangle area value to obtain a first evaluation parameter value corresponding to the area factor and a second evaluation parameter value corresponding to the position factor; Based on the first evaluation parameter value and the second evaluation parameter value, query each preset evaluation parameter range interval to determine the target area parameter range interval corresponding to the first evaluation parameter value and the target position parameter range interval corresponding to the second evaluation parameter value; Based on the target area parameter range interval and the target position parameter range interval, a second target characteristic indicator of the preset Gestalt evaluation model indicator layer corresponding to the area factor and a second target characteristic indicator of the preset Gestalt evaluation model indicator layer corresponding to the position factor are determined.

5. The method according to claim 1, characterized in that The method of calculating and processing based on each of the target characteristic indicators by using a weight calculation method corresponding to each of the target characteristic indicators to obtain a weight value corresponding to each of the influencing factors of the criterion layer of the preset Gestalt evaluation model specifically includes: Based on each of the target characteristic indicators, query the preset characteristic scale corresponding table corresponding to each of the influencing factors to obtain the weight calculation method corresponding to each of the target characteristic indicators; Based on the image parameter values ​​of the tongue image, the scale parameter values ​​obtained by factor analysis and the weight calculation methods, calculations are performed to obtain weight values ​​corresponding to the influencing factors.

6. The method according to claim 1, characterized in that The calculation based on each of the weight values ​​is performed to obtain the visual perception feature vector of the target layer of the preset Gestalt evaluation model, specifically including: Calculate and process each element variable in a preset weight calculation matrix based on each weight value to obtain a weight matrix corresponding to the tongue image; Performing calculation processing based on the weight matrix to obtain an initial eigenvector corresponding to the weight matrix; The initial feature vector is normalized to obtain a visual perception feature vector of a target layer of a preset Gestalt evaluation model.

7. The method according to claim 1, characterized in that The calculation and processing based on the visual perception feature vector and the preset score values ​​corresponding to each layer of the preset Gestalt evaluation model to obtain the objective evaluation result of the tongue image specifically includes: Perform multiplication processing based on the visual perception feature vector and the preset score values ​​corresponding to each of the influencing factors of the preset Gestalt evaluation model criterion layer, to obtain initial score values ​​corresponding to each of the influencing factors of the criterion layer of the gestalt evaluation model; The initial scoring values ​​are added together to obtain an objective evaluation result of the tongue image.

8. An objective evaluation device for tongue image, characterized in that: include: Image processing module: used for performing image processing on the tongue image to be evaluated by using various preset image processing methods, and determining the target characteristic index of the preset Gestalt evaluation model index layer corresponding to each influencing factor of the preset Gestalt evaluation model criterion layer; A weight value calculation module: used to calculate and process based on each of the target characteristic indicators using a weight calculation method corresponding to each of the target characteristic indicators to obtain a weight value of each of the influencing factors corresponding to the criterion layer of the preset Gestalt evaluation model; Visual perception feature vector calculation module: used to perform calculation based on each weight value to obtain the visual perception feature vector of the target layer of the preset Gestalt evaluation model; Evaluation module: used to calculate and process the preset score values ​​corresponding to each of the influencing factors in the visual perception feature vector and the preset Gestalt evaluation model criterion layer to obtain an objective evaluation result of the tongue image.

9. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the objective evaluation method of tongue images described in any one of claims 1 to 7 are implemented.

10. An electronic device, characterized in that: The method at least comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method for objectively evaluating tongue images as described in any one of claims 1 to 7 when executing the computer program on the memory.

Images