Machine vision-based multi-parameter adaptive stirring system for traditional Chinese medicine preparation

Abstract

The present application relates to the technical field of image processing, and more particularly to a multi-parameter adaptive stirring system for traditional Chinese medicine preparation based on machine vision, comprising: a heating and stirring module for a jacketed glass heating reaction kettle; a data acquisition module for collecting surface images and bottom images of the traditional Chinese medicine preparation in the heating and stirring module after stirring at a preset stirring speed for a first preset time; a control module for determining whether the stirring of the traditional Chinese medicine preparation meets a preset standard according to a gray scale distribution characteristic value of the surface images; and a parameter adjustment module for determining an adjustment strategy of the heating and stirring module according to a bottom dark area proportion of the bottom images under the condition that the stirring of the traditional Chinese medicine preparation does not meet the preset standard according to the gray scale distribution characteristic value. The present application improves the stirring efficiency of the traditional Chinese medicine preparation stirring system.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image processing, and particularly relates to a traditional Chinese medicine preparation multi-parameter adaptive stirring system based on machine vision. BACKGROUND

[0002] The paste in traditional Chinese medicine preparation is actually an ointment containing a large amount of powder, so it has high hardness, large water absorption capacity and low greasiness, and is mainly used as a protective agent; the medical paste is mixed by powder medicine and base, and is used externally, which can be softened but not melted at body temperature, and can be kept on the skin for a long time. There are two types of greasy paste and water-soluble paste. The former uses petrolatum, liquid paraffin, lanolin, fatty oil and other bases. It is usually harder than ointment, has the functions of moisture absorption, drying and itching relief.

[0003] The preparation method of the paste is usually to crush the medicine into fine powder, or to prepare the extract by percolation or other methods according to the effective components contained in the medicine, and then to crush it into fine powder, to add an appropriate amount of binder or humectant, to stir uniformly, and to adjust it into paste, and then to obtain it. When applied, an appropriate amount is taken and applied to the skin or mucosa of the affected area, and replaced after a certain period of time to ensure the drug effect.

[0004] The traditional preparation process is usually carried out in a jacketed transparent glass heating reaction kettle. The jacket layer can pass in a heating medium (such as hot water or heat conducting oil) to realize the preheating function of the traditional Chinese medicine preparation in the kettle. The preheating of the medicine by passing the heating medium through the jacket can reduce the viscosity. After the preheating stage is over, the stirring paddle built in the reaction kettle is automatically started to stir the traditional Chinese medicine preparation and promote the mixing of the medicine.

[0005] In the preparation process of traditional Chinese medicine paste, the stirring link is very important, which directly affects the uniformity of the distribution of the medicine components, the stability of the preparation and the final drug effect.

[0006] Chinese patent application publication No. CN115661187A discloses an image enhancement method for traditional Chinese medicine preparation analysis. The method collects the medicine image in the automatic medicine frying pan to obtain the corresponding gradient image, so as to divide the pixel points into background pixel points, weak gradient pixel points and strong gradient pixel points. The connected domain is obtained based on the weak gradient pixel points and the strong gradient pixel points. The distance between each pixel point and the seed point in the traditional SLIC superpixel segmentation is corrected by using the fuzzy degree of the connected domain to obtain the corrected distance. The superpixel segmentation is carried out based on the corrected distance to obtain the segmentation image. The segmentation image is used to train the semantic segmentation network to obtain the monitoring information of the medicine frying state according to the trained semantic segmentation network.

[0007] It can be seen that the above technical scheme only monitors and identifies the frying state through surface image segmentation, but does not combine the image analysis result with the control parameters of the stirring system, and cannot dynamically adjust the parameters according to the real-time image data, resulting in poor stirring efficiency. SUMMARY

[0008] To this end, the present application provides a machine vision-based multi-parameter adaptive stirring system for traditional Chinese medicine preparation, which overcomes the problem in the prior art that only the frying state is monitored and identified through surface image segmentation, but the image analysis result is not combined with the control parameters of the stirring system, and the stirring efficiency is poor due to the inability to dynamically adjust the parameters according to real-time image data.

[0009] To achieve the above-mentioned purpose, the present application provides a machine vision-based multi-parameter adaptive stirring system for traditional Chinese medicine preparation, comprising:

[0010] a heating and stirring module, which is a jacketed glass heating reaction kettle, used to stir the traditional Chinese medicine preparation after preheating;

[0011] a data acquisition module connected with the heating and stirring module, used to acquire the surface image and the bottom image of the traditional Chinese medicine preparation in the heating and stirring module after stirring at a preset stirring speed for a first preset time;

[0012] a control module connected with the data acquisition module, used to determine whether the stirring of the traditional Chinese medicine preparation meets the preset standard according to the gray level distribution characteristic value of the surface image;

[0013] a parameter adjustment module connected with the heating and stirring module and the control module, respectively, used to determine the adjustment strategy of the heating and stirring module according to the bottom dark area proportion of the bottom image under the condition that the stirring of the traditional Chinese medicine preparation does not meet the preset standard according to the gray level distribution characteristic value.

[0014] Further, the control module determines whether the stirring of the traditional Chinese medicine preparation meets the preset standard according to the comparison result of the gray level distribution characteristic value of the surface image and a second preset gray level distribution characteristic value, wherein under the condition that the gray level distribution characteristic value is greater than or equal to a first preset gray level distribution characteristic value and less than a second preset gray level distribution characteristic value, the control module determines whether the stirring of the traditional Chinese medicine preparation meets the preset standard according to the gray level mutation rate of the surface image twice.

[0015] The first preset gray level distribution characteristic value is less than the second preset gray level distribution characteristic value.

[0016] Further, the control module determines that the stirring of the traditional Chinese medicine preparation does not meet the preset standard in response to the gray level distribution characteristic value being greater than or equal to the second preset gray level distribution characteristic value, and the parameter adjustment module determines the adjustment strategy of the heating and stirring module according to the bottom dark area proportion of the bottom image.

[0017] Further, the gray scale distribution representation value is a standard deviation of average gray scale values of each grid after the surface image is divided by grid.

[0018] Further, under the condition that the control module determines that the stirring of the traditional Chinese medicine preparation does not meet the preset standard according to the comparison result that the gray scale mutation rate is greater than the preset gray scale mutation rate, the parameter adjustment module increases the preset stirring speed according to a difference between the gray scale mutation rate and the preset gray scale mutation rate.

[0019] Further, the gray scale mutation rate is a ratio of a number of grid pairs in which a difference between average gray scale values of adjacent grids is greater than a preset gray scale difference to a total number of adjacent grid pairs of the surface image, wherein the adjacent grids are grids sharing an edge or a vertex.

[0020] Further, the parameter adjustment module is provided with a plurality of speed adjustment modes for the increase of the preset stirring speed, wherein,

[0021] if the gray scale mutation difference is less than a first preset gray scale mutation difference, the preset stirring speed is increased to a corresponding value by using a first adjustment coefficient;

[0022] if the gray scale mutation difference is greater than or equal to the first preset gray scale mutation difference and less than a second preset gray scale mutation difference, the preset stirring speed is increased to a corresponding value by using a second adjustment coefficient;

[0023] if the gray scale mutation difference is greater than or equal to the second preset gray scale mutation difference, the preset stirring speed is increased to a corresponding value by using a third adjustment coefficient;

[0024] The gray scale mutation difference is a difference between the gray scale mutation rate and the preset gray scale mutation rate.

[0025] Further, under the condition that the stirring of the traditional Chinese medicine preparation is determined to not meet the preset standard according to the gray scale distribution representation value, the parameter adjustment module determines an adjustment strategy of the heating and stirring module according to a bottom dark area area ratio of the bottom image, wherein,

[0026] if the bottom dark area area ratio is less than a preset dark area area ratio, the first preset time length is increased according to a difference between the preset dark area area ratio and the bottom dark area area ratio;

[0027] if the bottom dark area area ratio is greater than or equal to the preset dark area area ratio, the heating and stirring module immediately stops stirring and restarts jacket heating.

[0028] Further, the bottom dark area area ratio is a ratio of a pixel area with a gray value less than a preset gray value in the bottom image to a total pixel area of the bottom image, wherein the pixel area with the gray value less than the preset gray value in the bottom image is recorded as a bottom dark area area.

[0029] Further, the first preset time length is positively correlated with a dark area area deviation, wherein the dark area area deviation is a difference between a preset dark area area ratio and the bottom dark area area ratio.

[0030] Compared with the prior art, the present application has the beneficial effects that the present application integrates a heating and stirring module, a data acquisition module, a control module and a parameter adjustment module to construct a closed-loop adaptive control system based on machine vision, synchronously acquires a surface image and a bottom image of a traditional Chinese medicine preparation, evaluates the overall uniformity based on the surface image, and identifies the precipitation based on the bottom image, so as to realize multi-dimensional monitoring of the stirring state, integrate the preheating and stirring functions of the jacketed glass reaction kettle, realize the dynamic adaptation of the real-time state of the traditional Chinese medicine preparation and the stirring device based on the real-time feedback of the parameter adjustment module, avoid local overheating or precipitation solidification, and thus improve the adaptability of the stirring system.

[0031] Further, the present application compares the gray scale distribution characteristic value with the first preset value and the second preset value respectively, designs a step threshold value of the preset gray scale distribution characteristic value, firstly performs preliminary screening, and then performs secondary determination on the critical state by introducing the gray scale mutation rate, optimizes the determination logic of the stirring in line with the preset standard, avoids the limitation of a single determination standard, can more accurately identify the critical state in the stirring process, reduces the misjudgment, and thus improves the reliability of the determination of the stirring system.

[0032] Further, the present application defines the gray scale distribution characteristic value as a standard deviation of the average gray scale value of each grid after the surface image is divided by a grid, reflects the dispersion degree of the gray scale distribution of the surface image through the quantitative index of the standard deviation, can objectively quantify the stirring uniformity of the surface of the traditional Chinese medicine preparation, converts the abstract stirring uniformity evaluation into a calculable specific value, enhances the objectivity of the judgment, avoids subjective evaluation, and thus improves the accuracy of the stirring state evaluation.

[0033] Further, the present application sets the gray scale mutation rate, comprehensively considers the positional relationship between each grid in the image, can more carefully capture the mutation area of the gray scale in the surface image, and thus reflects the local non-uniform phenomenon existing in the stirring process.

[0034] Further, the application formulates a differentiated adjustment strategy according to different situations of the bottom dark area proportion, prolongs the stirring time when the proportion is less than a preset value, and stops stirring and restarts heating when the proportion is greater than or equal to the preset value, which can solve the problems of insufficient stirring at the bottom or deposition of the preparation, ensure that the stirring effect at the bottom area is consistent with the whole, and avoid continuous processing of unqualified preparation by timely stopping and restarting heating, thereby improving the efficiency of the stirring system.

[0035] Further, the application positively correlates the stirring time increase amplitude with the dark area deviation, thereby realizing precise control of the stirring time increase amplitude. BRIEF DESCRIPTION OF DRAWINGS

[0036] Figure 1 A module connection schematic diagram of the machine vision-based multi-parameter adaptive stirring system for traditional Chinese medicine preparation according to the embodiment of the application;

[0037] Figure 2 A flowchart for determining whether the stirring of the traditional Chinese medicine preparation meets the preset standard according to the gray scale distribution representation value of the surface image according to the embodiment of the application;

[0038] Figure 3 A flowchart for twice determining whether the stirring of the traditional Chinese medicine preparation meets the preset standard according to the embodiment of the application;

[0039] Figure 4 A flowchart for determining the adjustment strategy of the heating and stirring module according to the embodiment of the application. DETAILED DESCRIPTION

[0040] In order to make the objects and advantages of the application clearer, the application will be further described below with reference to the embodiments; it should be understood that the specific embodiments described herein are only used to explain the application, and do not limit the protection scope of the application.

[0041] The preferred embodiments of the application will be described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the application, and are not intended to limit the protection scope of the application.

[0042] It should be pointed out that the data in the embodiments are obtained by comprehensive analysis and evaluation of historical detection data and corresponding historical detection results of the application in the past three months before the detection. Those skilled in the art can understand that the determination method of the single item described in the application can be to select the value with the highest proportion as the preset standard parameter according to the data distribution, to use weighted summation to obtain the value as the preset standard parameter, to substitute each historical data into a specific formula and to obtain the value as the preset standard parameter, or other selection methods, as long as the method described in the application can clearly define different specific situations in the single item determination process through the obtained value.

[0043] Please refer to Figure 1 、 Figure 2 、 Figure 3 and Figure 4 respectively, which are the module connection schematic diagram of the traditional Chinese medicine preparation multi-parameter adaptive stirring system based on machine vision according to the embodiment of the application; the flow chart of determining whether the stirring of the traditional Chinese medicine preparation meets the preset standard according to the gray scale distribution characteristic value of the surface image according to the embodiment of the application; the flow chart of twice determining whether the stirring of the traditional Chinese medicine preparation meets the preset standard according to the embodiment of the application; and the flow chart of determining the adjustment strategy of the heating stirring module according to the embodiment of the application.

[0044] The embodiment of the application provides a traditional Chinese medicine preparation multi-parameter adaptive stirring system based on machine vision, which comprises:

[0045] A heating stirring module, which is a jacketed glass heating reaction kettle, is used to stir the traditional Chinese medicine preparation after preheating, wherein the preheating temperature is 60 DEG C, and the preheating time is 20 min.

[0046] A data acquisition module is connected with the heating stirring module, and is used to acquire the surface image and the bottom image of the traditional Chinese medicine preparation of the heating stirring module by using an industrial camera after the heating stirring module is stirred at a preset stirring speed of 150 rpm for a first preset time of 15 min;

[0047] A control module is connected with the data acquisition module, and is used to determine whether the stirring of the traditional Chinese medicine preparation meets a preset standard according to a gray scale distribution characteristic value of the surface image.

[0048] A parameter adjustment module is connected with the heating stirring module and the control module respectively, and is used to determine an adjustment strategy of the heating stirring module according to a bottom dark area area ratio of the bottom image on the condition that the stirring of the traditional Chinese medicine preparation does not meet the preset standard according to the gray scale distribution characteristic value.

[0049] It should be pointed out that the data in the embodiment are results obtained through preliminary experiments before the detection by the method of the application, and each preset value can be adjusted according to specific use conditions, as long as the method of the application can clearly define different specific conditions in the single determination process through the obtained values. The preset values set in the embodiment are obtained according to preliminary experiments, and each correction coefficient is also selected through experimental verification.

[0050] Specifically, the specific structure of the control module and the parameter adjustment module is not limited, and each unit thereof can be composed of a logic component, which includes a field programmable component, a computer or a microprocessor in the computer.

[0051] Specifically, the control module determines whether the stirring of the traditional Chinese medicine preparation meets the preset standard according to a gray scale distribution characteristic value of the surface image, wherein

[0052] If the gray scale distribution characteristic value is less than a first preset gray scale distribution characteristic value 8.5, it is determined that the stirring of the traditional Chinese medicine preparation meets the preset standard.

[0053] If the gray scale distribution characteristic value is greater than or equal to the first preset gray scale distribution characteristic value and less than a second preset gray scale distribution characteristic value 15.5, it is determined that the stirring of the traditional Chinese medicine preparation meets the preset standard, and the stirring of the traditional Chinese medicine preparation is determined again according to a gray scale mutation rate of the surface image whether it meets the preset standard.

[0054] If the gray scale distribution characteristic value is greater than or equal to the second preset gray scale distribution characteristic value, it is determined that the stirring of the traditional Chinese medicine preparation does not meet the preset standard, and the parameter adjustment module determines an adjustment strategy of the heating and stirring module according to a bottom dark area area ratio of the bottom image.

[0055] The first preset gray scale distribution characteristic value is less than the second preset gray scale distribution characteristic value.

[0056] Specifically, the first preset gray scale distribution characteristic value is in a range of [8, 10], and the second preset gray scale distribution characteristic value is in a range of [13, 20]. Preferably, the first preset gray scale distribution characteristic value is 8.5, and the second preset gray scale distribution characteristic value is 15.5. In this embodiment, the more the precipitate sinks due to the density difference, the more the gray scale distribution of the upper paste is dispersed (i.e., the greater the gray scale distribution characteristic value is).

[0057] Specifically, when the gray scale distribution characteristic value is less than the first preset gray scale distribution characteristic value, the gray scale distribution is uniform, indicating that the stirring is sufficient; when the gray scale distribution characteristic value is greater than or equal to the first preset gray scale distribution characteristic value and less than the second preset gray scale distribution characteristic value, the gray scale distribution has local fluctuations, but meets the overall requirements; and when the gray scale distribution characteristic value is greater than or equal to the second preset gray scale distribution characteristic value, the gray scale distribution is significantly uneven.

[0058] Specifically, the gray scale distribution characteristic value is a standard deviation of average gray scale values of each grid after the surface image is divided into grids, and the gray scale distribution characteristic value reflects the uniformity of surface concentration distribution. In this embodiment, the grid division of the surface image is realized by OpenCV.

[0059] In this embodiment, the grid is a rectangular grid, and the number of rows and the number of columns of the grid are less than or equal to 10.

[0060] Specifically, the control module determines whether the stirring of the traditional Chinese medicine preparation meets the preset standard according to the gray scale mutation rate, wherein

[0061] If the gray scale mutation rate is less than the preset gray scale mutation rate 0.15, it is determined that the stirring of the traditional Chinese medicine preparation meets the preset standard;

[0062] If the gray scale mutation rate is greater than or equal to the preset gray scale mutation rate, it is determined that the stirring of the traditional Chinese medicine preparation does not meet the preset standard, and the parameter adjustment module increases the preset stirring speed according to the difference between the gray scale mutation rate and the preset gray scale mutation rate.

[0063] In this embodiment, the preset gray scale mutation rate is 0.15, but the above value is not limited thereto, and those skilled in the art can adjust the above value according to actual needs.

[0064] Specifically, the gray scale mutation rate is the ratio of the number of grid pairs whose difference between the average gray scale values of adjacent grids of the surface image is greater than a preset gray scale difference 20 to the total number of adjacent grid pairs of the surface image, wherein the adjacent grids are grids sharing edges or vertices.

[0065] Specifically, the gray scale mutation rate less than the preset gray scale mutation rate indicates that the proportion of grid pairs with a gray scale difference greater than the preset gray scale difference in adjacent grids is low, indicating that the local concentration difference of the traditional Chinese medicine preparation surface is small and the distribution is dispersed; the gray scale mutation rate greater than or equal to the preset gray scale mutation rate indicates that there are many places with concentration mutation in the traditional Chinese medicine preparation, i.e., the local particle agglomeration in the preparation is serious.

[0066] Specifically, the parameter adjustment module sets several speed adjustment modes for the increase of the preset stirring speed, wherein,

[0067] If the gray scale mutation difference is less than a first preset gray scale mutation difference 0.06, the preset stirring speed is increased to a corresponding value by using a first adjustment coefficient 1.08;

[0068] If the gray scale mutation difference is greater than or equal to the first preset gray scale mutation difference and less than a second preset gray scale mutation difference 0.16, the preset stirring speed is increased to a corresponding value by using a second adjustment coefficient 1.11;

[0069] If the gray scale mutation difference is greater than or equal to the second preset gray scale mutation difference, the preset stirring speed is increased to a corresponding value by using a third adjustment coefficient 1.14;

[0070] The gray scale mutation difference is the difference between the gray scale mutation rate and the preset gray scale mutation rate.

[0071] Specifically, under the condition that it is determined according to the gray scale distribution representation value that the stirring of the traditional Chinese medicine preparation does not meet the preset standard, the parameter adjustment module determines the adjustment strategy of the heating and stirring module according to the bottom dark area proportion of the bottom image, wherein,

[0072] the bottom dark area area ratio is less than the preset dark area area ratio by 0.2, the first preset time length is increased according to a difference between the preset dark area area ratio and the bottom dark area area ratio;

[0073] the bottom dark area area ratio is greater than or equal to the preset dark area area ratio, the heating and stirring module immediately stops stirring and restarts jacket heating.

[0074] In this embodiment, the preset dark area area ratio is 0.2, but the above value is not limited thereto, and those skilled in the art can adjust the above value according to actual needs.

[0075] In this embodiment, the dark area area ratio reflects the mixing effect of the bottom of the traditional Chinese medicine preparation.

[0076] Specifically, when the bottom dark area area ratio is less than the preset dark area area ratio, the precipitated particles have not yet formed hard lumps, and by extending the stirring time length, the particles can be re-suspended; when the bottom dark area area ratio is greater than or equal to the preset dark area area ratio, the precipitated particles have undergone obvious agglomeration, and stirring alone cannot break the lumps, but heating can reduce the binding force between the particles, creating conditions for subsequent stirring and dispersion, and avoiding the influence of lump residues on the quality of the traditional Chinese medicine preparation.

[0077] Specifically, the bottom dark area area ratio is a ratio of a pixel area with a gray value less than a preset gray value 40 in the bottom image to a total pixel area of the bottom image, wherein the pixel area with a gray value less than the preset gray value 40 in the bottom image is recorded as a bottom dark area area.

[0078] Specifically, the increase in the first preset time length is positively correlated with the dark area area deviation, wherein the positive correlation is, for example, linear positive correlation or nonlinear positive correlation, and the linear slope of the linear positive correlation is not specifically limited. It can be understood that the greater the dark area area deviation, the greater the increase in the first preset time length, and the dark area area deviation is a difference between the preset dark area area ratio and the bottom dark area area ratio.

[0079] So far, the technical solutions of the present application have been described in combination with the preferred embodiments shown in the drawings, but those skilled in the art can easily understand that the protection scope of the present application is obviously not limited to these specific embodiments. Those skilled in the art can make equivalent changes or replacements to related technical features without departing from the principles of the present application, and the technical solutions after these changes or replacements will fall within the protection scope of the present application.

[0080] The above merely illustrates the preferred embodiments of the present application, and is not used to limit the present application; for those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A machine vision-based multi-parameter adaptive stirring system for traditional Chinese medicine preparation, characterized in that, The application relates to a traditional Chinese medicine preparation stirring device. The device comprises a heating and stirring module, a data acquisition module and a control module. The heating and stirring module is a jacketed glass heating reactor used for preheating and stirring traditional Chinese medicine preparation. The data acquisition module is connected to the heating and stirring module and used for acquiring surface and bottom images of the traditional Chinese medicine preparation in the heating and stirring module after the module is stirred at a preset stirring speed for a first preset time length. The control module is connected to the data acquisition module and used for judging whether the stirring of the traditional Chinese medicine preparation meets preset standards according to a gray scale distribution characteristic value of the surface image. The parameter adjustment module is connected to the heating and stirring module and the control module and used for determining an adjustment strategy of the heating and stirring module according to a bottom dark area proportion of the bottom image when the stirring of the traditional Chinese medicine preparation is judged not to meet the preset standards according to the gray scale distribution characteristic value. The control module judges whether the stirring of the traditional Chinese medicine preparation meets the preset standards according to a comparison result of the gray scale distribution characteristic value of the surface image and a second preset gray scale distribution characteristic value. If the gray scale distribution characteristic value is less than a first preset gray scale distribution characteristic value, the stirring of the traditional Chinese medicine preparation is judged to meet the preset standards. When the gray scale distribution characteristic value is greater than or equal to the first preset gray scale distribution characteristic value and less than the second preset gray scale distribution characteristic value, the control module further judges whether the stirring of the traditional Chinese medicine preparation meets the preset standards according to a gray scale mutation rate of the surface image. The first preset gray scale distribution characteristic value is less than the second preset gray scale distribution characteristic value. When the gray scale distribution characteristic value is greater than or equal to the second preset gray scale distribution characteristic value, the control module judges that the stirring of the traditional Chinese medicine preparation does not meet the preset standards, and the parameter adjustment module determines the adjustment strategy of the heating and stirring module according to the bottom dark area proportion of the bottom image. The gray scale distribution characteristic value is a standard deviation of average gray scales of each grid after the surface image is divided by a grid. When the stirring of the traditional Chinese medicine preparation is judged not to meet the preset standards according to the gray scale distribution characteristic value, the parameter adjustment module determines the adjustment strategy of the heating and stirring module according to the bottom dark area proportion of the bottom image.

2. The machine vision-based multi-parameter adaptive stirring system for traditional Chinese medicine preparation according to claim 1, characterized in that, If the bottom dark area proportion is less than a preset dark area proportion, the first preset time length is increased according to a difference between the preset dark area proportion and the bottom dark area proportion. If the bottom dark area proportion is greater than or equal to the preset dark area proportion, the heating and stirring module is immediately stopped and restarted. The bottom dark area proportion is a ratio of a pixel area with a gray scale less than a preset gray scale to a total pixel area of the bottom image. When the stirring of the traditional Chinese medicine preparation is judged not to meet the preset standards according to the comparison result that the gray scale mutation rate is greater than a preset gray scale mutation rate, the parameter adjustment module increases the preset stirring speed according to a difference between the gray scale mutation rate and the preset gray scale mutation rate.

3. The machine vision-based multi-parameter adaptive stirring system for traditional Chinese medicine preparation according to claim 2, characterized in that, The gray scale mutation rate is a ratio of a number of grid pairs with a difference between average gray scale values of adjacent grids of the surface image greater than a preset gray scale difference value to a total number of adjacent grid pairs of the surface image, wherein the adjacent grids are grids sharing an edge or a vertex.

4. The machine vision-based multi-parameter adaptive stirring system for traditional Chinese medicine preparation according to claim 3, characterized in that, The parameter adjustment module is provided with a plurality of rotation speed adjustment modes for increasing the preset stirring rotation speed, wherein, if the gray scale mutation difference value is less than a first preset gray scale mutation difference value, the preset stirring rotation speed is increased to a corresponding value by using a first adjustment coefficient; if the gray scale mutation difference value is greater than or equal to the first preset gray scale mutation difference value and less than a second preset gray scale mutation difference value, the preset stirring rotation speed is increased to a corresponding value by using a second adjustment coefficient; if the gray scale mutation difference value is greater than or equal to the second preset gray scale mutation difference value, the preset stirring rotation speed is increased to a corresponding value by using a third adjustment coefficient; The gray scale mutation difference value is a difference between the gray scale mutation rate and the preset gray scale mutation rate.

5. The machine vision-based multi-parameter adaptive stirring system for traditional Chinese medicine preparation according to claim 4, characterized in that, The increasing amplitude of the first preset time length is positively correlated with a dark area area deviation, wherein the dark area area deviation is a difference between a preset dark area area proportion and a bottom dark area area proportion.

Images