Tobacco lamina alcoholization evaluation method, system, equipment and medium

Abstract

According to the tobacco lamina alcoholization evaluation method and system, the electronic equipment and the storage medium provided by the invention, the variance and linearity of the preprocessed tobacco lamina sample in multiple different color spaces are obtained, and the color space meeting the preset condition is screened out from the preprocessed tobacco lamina sample; combining an elbow method and a K-means clustering algorithm to construct an alcoholization evaluation model; and inputting the preprocessed alcoholization image of the to-be-detected tobacco lamina into the constructed alcoholization evaluation model to obtain an alcoholization evaluation result corresponding to the to-be-detected tobacco lamina. Compared with the prior art, manual participation is not needed, the appropriate color space is selected from the multiple color spaces, the objective and accurate alcoholization evaluation model is constructed in the color space, alcoholization evaluation is conducted on the to-be-detected strip alcoholization image through the model, and the efficiency and accuracy of tobacco leaf quality evaluation are effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of tobacco quality, and in particular to a method, system, equipment and medium for evaluating the aging of tobacco leaves. Background Art

[0002] In industrial production, the evaluation of the quality changes of redried tobacco strips mainly relies on sensory quality testing. This process usually requires a group of experienced tasters (usually 3 to 5 people) to complete. The tasters carefully observe the smoking process of the cigarettes and subjectively score the overall quality of the tobacco strips based on a series of core evaluation indicators such as aroma, taste, irritation and aftertaste. Specifically, aroma evaluation focuses on the intensity, flavor characteristics and persistence of the smoke. Tasters need to keenly capture the subtle changes in aroma from the moment of ignition to the entire puffing process, and record the stability and persistence of the aroma. The evaluation of taste and irritation focuses on the smoothness, softness and stimulation of the smoke when it contacts the mouth and throat. Tasters will pay attention to the feeling of the smoke in the mouth and throat during the smoking process, especially the changes between the first and last few puffs. Excessive irritation or harsh taste will reduce the quality score of the tobacco leaves. The aftertaste evaluation emphasizes the freshness and purity of the residual taste in the mouth and throat after puffing. The evaluation of combustion characteristics involves the burning speed of the cigarette, the ash shape and the stability of the combustion line, and records whether there is unevenness or extinction during the combustion process.

[0003] However, this sensory evaluation method is not only destructive, but also poses a potential threat to the health of tasters. Based on this, appearance quality recognition technology, as a non-destructive and efficient alternative, is gradually becoming a cutting-edge trend in the tobacco industry to evaluate the aging quality of tobacco leaves.

[0004] In the field of appearance evaluation, although modern instruments such as high-precision spectrophotometers can accurately quantify the color characteristics of the surface of flue-cured tobacco, traditional sensory judgment methods are still widely used because of their intuitiveness and convenience. In particular, for the changes in tobacco leaf color during the aging process, sensory measurement combined with quantitative analysis provides an important basis for quality judgment. During the aging process, the color of tobacco leaves undergoes a significant change from lemon yellow and orange to brown yellow, brown red, and brown. This process is not only accompanied by a deepening of the appearance color, but also indicates a significant improvement in the internal quality.

[0005] The industry has adopted a color grading system, which artificially divides the color of tobacco leaves from light yellow to brown into ten levels: light yellow, yellow, golden yellow, dark yellow, orange-red, red-brown, brown-yellow, brown-red, dark red and brown-brown, and assigns corresponding values ​​(0 to 10.0) to accurately quantify the color depth. In actual operation, the tobacco leaf samples must first be mixed evenly, impurities removed, and 40 to 70 g of samples are evenly obtained by quartering as test samples; then 11 A4 papers are taken, numbered from 0 to 10, and the samples are compared with the standard color cards one by one, and the closest color number is recorded and placed on the corresponding paper; after all samples are compared, the tobacco leaves on each number are weighed with an analytical balance and recorded separately. For single tobacco leaves containing multiple colors, the color with the largest area shall prevail. If the colors are half and half, the one with the smallest value shall prevail; finally, according to a specific alcoholization score calculation formula, the collected data is processed to intuitively reflect the magnitude of color change in numerical form, and then the intensity of alcoholization reaction and the improvement of tobacco leaf quality are evaluated.

[0006] Therefore, it is an urgent problem to be solved by those skilled in the art to provide a method, system, equipment and medium for evaluating the aging of tobacco leaves that overcomes the shortcomings of traditional manual smoking evaluation methods and sensory color judgment methods. Summary of the invention

[0007] The purpose of the present invention is to provide a tobacco leaf aging evaluation method, which has clear logic, is safe, effective, reliable and easy to operate, can overcome the shortcomings of traditional manual smoking evaluation methods and sensory color judgment methods, and effectively improve the efficiency and accuracy of tobacco leaf quality evaluation.

[0008] Based on the above objectives, the technical solution provided by the present invention is as follows: A method for evaluating the aging of tobacco leaves comprises the following steps: Acquire the pre-processed alcoholization image of the tobacco slice to be tested; Inputting the aging image of the tobacco strips to be tested into an aging evaluation model to obtain an aging evaluation result of the tobacco strips to be tested; Wherein, the alcoholization evaluation model is determined by the following steps: Obtain multiple sets of variance and linearity of the pre-processed tobacco sample aging images in different color spaces; Analyze each group of variance and each group of linearity to screen out the color space that meets the preset conditions; The aging evaluation model is constructed according to the elbow method, the K-means clustering algorithm and the color space that meets the preset conditions.

[0009] Preferably, the step of obtaining multiple sets of variances and linearities of the pre-processed aged tobacco sample images in different color spaces comprises the following steps: Select the aging images of pre-treated tobacco samples from different batches of the same grade; Calculate the standard deviation of each color space according to the STDEVP function and the aging images of the pre-processed tobacco samples of different batches of the same grade to obtain the variance corresponding to each color space; According to the SLOPE function and the aging images of the pre-processed tobacco leaf samples of different batches of the same grade, a linear regression analysis is performed on each color space to obtain the linearity corresponding to each color space.

[0010] Preferably, the analyzing each group of variance and each group of linearity to screen out a color space that meets a preset condition comprises the following steps: Compare the corresponding variances and linearities of each group to select the color space that meets the preset conditions; The preset condition is specifically: the variance value and the linearity value are both maximum.

[0011] Preferably, the step of constructing the aging evaluation model according to the elbow method, the K-means clustering algorithm and the color space satisfying the preset conditions comprises the following steps: Determine a color standard sample according to the elbow method, the K-means clustering algorithm, the aged image of the tobacco strip sample and the preset image of the tobacco strip sample at the end of aged period; Establishing the color standard in the color space that meets the preset conditions; The alcoholization evaluation model is constructed based on the color standard.

[0012] Preferably, the step of determining the color standard sample according to the elbow method, the K-means clustering algorithm, the aged tobacco sample image and the preset aged tobacco sample image at the end of the aged tobacco sample comprises the following steps: Determine a plurality of cluster centers according to the elbow method, the aged image of the tobacco strip sample and the preset image of the tobacco strip sample at the end of aged period; According to the K-means clustering algorithm, the Euclidean distance between each element in the aged image of the tobacco strip sample and the preset late-aged image of the tobacco strip sample and each cluster center is calculated respectively, so as to determine the cluster center corresponding to the minimum Euclidean distance; Each element in the aged tobacco sample image and the preset aged tobacco sample image at the end of the aged tobacco sample is assigned to the cluster center corresponding to the minimum Euclidean distance for iterative training until a color standard sample is determined.

[0013] Preferably, the step of inputting the aging image of the tobacco strips to be tested into an aging evaluation model to obtain an aging evaluation result of the tobacco strips to be tested comprises the following steps: The aging evaluation model calculates and obtains all elements in the aging image of the tobacco leaf to be tested; Obtaining the proportion of each cluster center in the alcoholized image of the tobacco leaf to be tested; Define a linear scoring rate array whose length is the same as the number of cluster centers and whose element values ​​decrease from a preset value; The proportion of each cluster center and the corresponding element of the linear scoring rate array are weightedly summed to obtain the aging evaluation result of the tested tobacco strips.

[0014] A tobacco aging evaluation system, comprising: An image module is used to obtain and pre-process the alcohol-aged image of the tobacco leaf to be tested; Model building module, used to build alcoholization evaluation model; The aging evaluation module is used to obtain the aging evaluation result of the tobacco strips to be tested according to the preprocessed aging image of the tobacco strips to be tested and the aging evaluation model.

[0015] Preferably, the model construction module includes: a parameter submodule, an analysis module and a construction submodule; The parameter submodule is used to obtain multiple sets of variances and linearities of the pre-processed tobacco sample aged images in different color spaces; The analysis submodule is used to analyze each group of variance and each group of linearity to screen out the color space that meets the preset conditions; The construction submodule is used to construct the aging evaluation model according to the elbow method, the K-means clustering algorithm and the color space that meets the preset conditions.

[0016] An electronic device, comprising: Memory, storing programs or instructions; A processor, executing the program or instructions; Wherein, when executing the program or instruction, the processor implements the steps of any of the above-mentioned methods for evaluating the aging of tobacco leaves.

[0017] A readable storage medium, characterized in that a program or instruction is stored on the readable storage medium, and when the program or instruction is executed by a processor, the steps of the tobacco aging evaluation method as described in any one of the above are implemented.

[0018] The method for evaluating the aging of tobacco strips provided by the present invention is to obtain the variance and linearity of pre-processed tobacco strip samples in a plurality of different color spaces, and screen out the color space that meets the preset conditions; to construct an aging evaluation model by combining the elbow method and the K-means clustering algorithm; and to input the pre-processed aging image of the tobacco strips to be tested into the constructed aging evaluation model to obtain the aging evaluation result corresponding to the tobacco strips to be tested.

[0019] Compared with the existing technology, this case does not require human intervention. A suitable color space is selected from a variety of color spaces. An objective and accurate aging evaluation model is constructed in the color space. The model is used to perform aging evaluation on the aging images of the tested tobacco leaves, effectively improving the efficiency and accuracy of tobacco leaf quality evaluation.

[0020] The present invention also provides a tobacco aging evaluation system, electronic equipment and storage medium. Since they adopt the same technical concept as the method and solve the same technical problem, they should have the same beneficial effects and will not be described in detail here. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0022] Figure 1 A flow chart of a method for evaluating the aging of tobacco leaves provided by an embodiment of the present invention; Figure 2 A flowchart of step S1 provided in an embodiment of the present invention; Figure 3 A flowchart of step S3 provided in an embodiment of the present invention; Figure 4 A flowchart of step B1 provided in an embodiment of the present invention; Figure 5 A flow chart for obtaining the aging results of the tested tobacco leaves provided in an embodiment of the present invention; Figure 6 A schematic diagram of the structure of a tobacco aging evaluation system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] The embodiments of the present invention are written in a progressive manner.

[0025] The embodiment of the present invention provides a tobacco aging evaluation method and system, which mainly solves the technical problem in the prior art that the traditional manual smoking evaluation method and sensory color determination method lead to low efficiency and accuracy in tobacco leaf quality evaluation.

[0026] like Figure 1 As shown, a method for evaluating the aging of tobacco slices comprises the following steps: Acquire the pre-processed alcoholization image of the tobacco slice to be tested; Inputting the aging image of the tobacco strips to be tested into the aging evaluation model to obtain the aging evaluation result of the tobacco strips to be tested; Among them, the alcoholization evaluation model is determined by the following steps: S1. Obtaining multiple sets of variances and linearities of the preprocessed tobacco sample aging images in different color spaces; S2. analyzing each group of variance and each group of linearity to screen out a color space that meets preset conditions; S3. Construct an aging evaluation model based on the elbow method, K-means clustering algorithm and a color space that meets preset conditions.

[0027] In step S1, a tobacco sample is prepared in advance, a front area of ​​the liquid surface of the tobacco sample is collected, an alcohol-adapted image of the tobacco sample is obtained, and the alcohol-adapted image of the tobacco sample is preprocessed; then, color analysis is performed on the preprocessed alcohol-adapted image of the tobacco sample in different color spaces, specifically, multiple groups of variances and linearities are obtained by analysis and calculation; In step S2, by horizontally comparing and analyzing each group of variance and each group of linearity, a color space that meets a preset condition is selected from different color spaces; In step S3, a tobacco aging evaluation model is constructed based on the elbow method, the K-means clustering algorithm, and a color space that meets preset conditions.

[0028] like Figure 2 As shown, preferably, step S1 includes the following steps: A1. Select the aging images of pre-treated tobacco samples of the same grade but different batches; A2. Calculate the standard deviation of each color space based on the STDEVP function and the aged images of pre-processed tobacco samples of different batches of the same grade to obtain the variance corresponding to each color space; A3. Based on the SLOPE function and the aged images of pre-processed tobacco leaf samples of the same grade but different batches, a linear regression analysis is performed on each color space to obtain the linearity corresponding to each color space.

[0029] In step A1, based on qualitative and quantitative analysis considerations, multiple groups of pre-treated tobacco leaf samples from different batches of the same grade are selected for aging images; In step A2, the standard deviation of the aged images of multiple groups of pre-processed tobacco leaf samples of the same grade but different batches in each color space is calculated; In step A3, the linearity of the aged images of multiple groups of pre-processed tobacco leaf samples of the same grade but different batches in each color space is calculated; It should be noted that color space is a method or model used to represent color; The STDEVP function is a computer function that calculates the standard deviation based on the entire sample population given as a parameter. The standard deviation reflects the degree of dispersion relative to the mean; The main function of the SLOPE function is to calculate the slope of the linear relationship between two data sets. The slope is a numerical value that describes how one variable responds to the change in another variable. In linear regression analysis, the SLOPE function can help analysts understand the correlation between two variables, which can be positive or negative. The positive and negative sign and size of the slope can reflect the direction and strength of the relationship, that is, the linearity; In this embodiment, color spaces such as RGB, HSV and Lab are selected. RGB color space: an additive color model based on the three primary colors of red, green and blue. HSV color space: a color model based on hue, saturation and brightness, which is closer to human visual perception. Lab color space: a model based on brightness and two color axes, designed to simulate the color perception of the human eye; In this embodiment, the pixel points of each image are traversed and calculated, and the means of the three channels in the three color spaces of RGB (red, green and blue), HSV (hue, saturation and brightness) and Lab (brightness, a color axis and b color axis) are calculated and a data table is formed; the standard deviation of the overall sample is calculated using the STDEVP function; the linear correlation of the data in the color space is evaluated through linear regression analysis with the help of the SLOPE function, and the distribution and numerical differences of different color spaces are observed.

[0030] Preferably, step S2 comprises the following steps: Compare the corresponding variances and linearities of each group to select the color space that meets the preset conditions; The preset conditions are as follows: both the variance value and the linearity value are maximum.

[0031] In actual application, each group of variances obtained through the above steps is subjected to variance analysis; variance, as an indicator of the degree of data dispersion, reflects the difference in color changes of tobacco leaf images in different color spaces. The analysis found that the RGB color space is particularly good at expressing the diversity of tobacco leaf colors, and its calculated variance is significantly higher than that of the other two color spaces, which indicates that the RGB space has greater potential and advantages in subsequent refined technical analysis such as scoring; Each set of linearity obtained through the above steps is subjected to linearity analysis; the linearity analysis reveals the regularity of color change of tobacco leaves in different aging cycles. The linear correlation calculated by the SLOPE function shows that the RGB color space also exhibits excellent regularity capture ability, which once again proves its efficiency and accuracy in processing tobacco leaf color data.

[0032] like Figure 3 As shown, preferably, step S3 includes the following steps: B1. Determine the color standard sample according to the elbow method, the K-means clustering algorithm, the aged image of the tobacco strip sample and the preset image of the tobacco strip sample at the end of aged period; B2. Create a color standard in a color space that meets the preset conditions; B3. Construct an alcoholization evaluation model based on color standards.

[0033] In step B1 to step B3, the color standard sample is first determined by the elbow method, K-means clustering algorithm, and tobacco leaf sample images; that is, the number of cluster centers is determined by the elbow method, and the color standard sample that covers the entire tobacco leaf color space to the greatest extent is found through the K-means clustering algorithm and the cluster centers, and the color standard sample is established in the RGB color space; based on the color standard sample, an aging evaluation model is constructed.

[0034] like Figure 4 As shown, preferably, step B1 includes the following steps: C1. Determine multiple cluster centers based on the elbow method, the aged image of the tobacco strip sample and the preset image of the tobacco strip sample at the end of aged period; C2. According to the K-means clustering algorithm, the Euclidean distance between each element in the aged image of the tobacco strip sample and the preset late aged image of the tobacco strip sample and each cluster center is calculated to determine the cluster center corresponding to the minimum Euclidean distance; C3. Allocate each element in the aged tobacco sample image and the preset aged tobacco sample image at the end of the aged period to the cluster center corresponding to the minimum Euclidean distance for iterative training until the color standard sample is determined.

[0035] In step C1 to step C3, since the color variation of the certified tobacco leaves in each sample is usually small, an appropriate number of clusters must be determined, and the elbow method is used to determine the cluster center. After the cluster center is determined, the Euclidean distance is calculated according to the K-means clustering algorithm to determine the cluster center corresponding to the minimum Euclidean distance; each element in the aging image of the tobacco leaf sample and the preset image of the tobacco leaf sample at the end of aging is assigned to the cluster center corresponding to the minimum Euclidean distance for iterative training, thereby determining the color standard sample.

[0036] It should be noted that the elbow method is specifically: a method for determining the optimal number of clusters in cluster analysis by observing the trend of the sum of squared errors (SSE) as the number of clusters increases; In this embodiment, the specific implementation process of step C1 is: select a cluster number k within a range, run the K-means algorithm for each k value (cluster number) within the selected range, and calculate the SSE (sum of squared errors) after each iteration. Plot the relationship between SSE and the number of clusters: plot the SSE corresponding to each k value as a line graph or a scatter plot. Find the "elbow" point: find an obvious inflection point on the graph, where the rate of decline of SSE slows down significantly. The k value corresponding to this point is generally considered to be the optimal number of clusters, and the line graph shows k=3. Based on the previous step, three cluster centers were determined for the modular tobacco samples and the late-stage aging samples of the sheet tobacco, respectively, for a total of six cluster centers, which will be used as standard samples for color scoring within the same grade.

[0037] Steps C2 and C3 are specifically implemented as follows: select modular tobacco samples and late-aging leaf tobacco samples as standards to establish a color standard covering all grades and origins, with a total of six cluster centers, so that the color standard covering the entire tobacco leaf color space can be found to the greatest extent. Based on the K-means clustering algorithm, while only retaining the front of the tobacco leaf, calculate the Euclidean distance between each pixel and each cluster center, and then assign the pixel to the nearest cluster center.

[0038] Initialization: Randomly select K data points as the initial centroid ; Assignment step: For each data point , calculate its distance to each centroid and assign it to the cluster where the nearest centroid is located .

[0039]

[0040] Update step: For each cluster , recalculate the centroid is the average position of all points in the cluster:

[0041] The assignment and update steps are repeated until the centroids no longer change or the maximum number of iterations is reached.

[0042] like Figure 5 As shown, preferably, the aging image of the tobacco strips to be tested is input into the aging evaluation model to obtain the aging evaluation result of the tobacco strips to be tested, including the following steps: D1. The aging evaluation model calculates and obtains all elements in the aging image of the tobacco leaf to be tested; D2. Obtaining the proportion of each cluster center in the alcoholized image of the tested tobacco leaf; D3. Define a linear scoring rate array with the same length as the number of cluster centers and whose element values ​​decrease from the preset value; D4. Perform a weighted summation of the proportion of each cluster center and the corresponding element of the linear score rate array to obtain the aging evaluation result of the tested tobacco strips.

[0043] In step D1 to step D4, the aging image of the tobacco strips to be tested is input into the aging evaluation model, and the aging evaluation model calculates all elements in the aging image of the tobacco strips to be tested, and calculates the proportion of each cluster center in the aging image of the tobacco strips to be tested; defines a linear scoring rate array, the length of which is the same as the number of cluster centers, and the element value decreases from a preset value; and weightedly sums the proportion of each cluster center and the corresponding elements of the linear scoring rate array to obtain the aging evaluation result of the tobacco strips to be tested.

[0044] In this embodiment, the specific implementation process is: Calculate the total number of pixels in the image, that is, the total number of all pixel labels; Calculate the proportion of each clustering level in the image, that is, proportions = cluster_sizes / total_pixels.

[0045] Define a linear scoring rate array score_rate, whose element values ​​decrease from 100 to 0, and whose length is the same as the number of cluster centers. This array reflects that the higher the clustering level, the lower the corresponding score.

[0046] The weighted score is obtained by multiplying the clustering ratio and the corresponding elements of the scoring rate array one by one, and then summing them up to calculate the total score. The clustering ratio is to determine the proportion of the specified standard samples in the sample. The length of the linear scoring rate array is the same as the number of standard samples, and its element values ​​decrease evenly from 100 to 0. The standards are sorted from dark to light in color, and the array element values ​​decrease from front to back. Therefore, the lower the degree of alcoholization, the greater the proportion of the standard samples at the back, and the less the score after multiplication with the array. Therefore, the degree of alcoholization of the sample can be reflected by the score from low to high.

[0047] Calculate the weighted score: multiply the cluster proportion by the corresponding element of the score rate array one by one, and then sum them up to calculate the total score. In this way, the score contribution of each cluster level is proportional to its proportion in the image, and is penalized by the score rate.

[0048] After weighted scoring of the alcoholization degree of the tobacco samples, in order to intuitively display the alcoholization score trend of the samples, a polynomial fitting curve is used to approximate the trend change of the entire alcoholization cycle. The specific process is as follows: A polynomial function is used to approximate the overall trend of a set of data points. In polynomial fitting, we usually have a set of discrete data points, each of which consists of a pair of coordinates: , indicating the Data points in Values ​​on the axis And the corresponding Axis Value The goal is to find a polynomial function , and determine the coefficients of the polynomial through an optimization algorithm so that the polynomial function is as close to the given data points as possible.

[0049] like Figure 6 As shown, a tobacco aging evaluation system comprises: An image module is used to obtain and pre-process the alcohol-aged image of the tobacco leaf to be tested; Model building module, used to build alcoholization evaluation model; The aging assessment module is used to obtain the aging assessment result of the tobacco strips to be tested based on the preprocessed aging image of the tobacco strips to be tested and the aging assessment model.

[0050] In actual application, the present invention also provides a tobacco aging evaluation system, which is provided with an image module, a model building module and an aging evaluation module; the multiple modules implement the corresponding steps of the tobacco aging evaluation method and have the same beneficial effects, which will not be repeated here.

[0051] Preferably, the model construction module includes: a parameter submodule, an analysis module and a construction submodule; The parameter submodule is used to obtain multiple sets of variances and linearities of the preprocessed tobacco sample aging images in different color spaces; An analysis submodule, used for analyzing each group of variance and each group of linearity, so as to screen out a color space that meets preset conditions; A submodule is constructed to construct an alcoholization evaluation model based on the elbow method, K-means clustering algorithm and a color space that meets preset conditions.

[0052] In the actual application process, the model construction module is specifically provided with a parameter submodule, an analysis submodule and a construction submodule, and the multiple submodules are used to implement the model construction process.

[0053] An electronic device, comprising: Memory, storing programs or instructions; processor, which executes programs or instructions; Wherein, when the processor executes the program or instruction, it implements the steps of any of the above-mentioned methods for evaluating the aging of tobacco leaves.

[0054] A readable storage medium, characterized in that a program or instruction is stored on the readable storage medium, and when the program or instruction is executed by a processor, the steps of any of the above-mentioned tobacco aging evaluation methods are implemented.

[0055] In actual application, the present invention also provides an electronic device and a readable storage medium, which solve the same technical problems as the tobacco aging evaluation method and system and should have the same beneficial effects.

[0056] In the embodiments provided in the present application, it should be understood that the disclosed methods and systems can be implemented in other ways. The system embodiments described above are merely schematic. For example, the division of modules is only a logical function division. There may be other division methods in actual implementation, such as: multiple modules or components can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0057] In addition, all functional modules in the embodiments of the present invention may be integrated into one processor, or each module may be a separate device, or two or more modules may be integrated into one device; each functional module in the embodiments of the present invention may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0058] A person of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiment can be completed by program instructions and related hardware. The aforementioned program instructions can be stored in a computer-readable storage medium. When the program instructions are executed, the steps of the above method embodiment are executed; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a magnetic disk or an optical disk, and other media that can store program codes.

[0059] It should be understood that the use of "system", "device", "unit" and / or "module" in this application is only a method for distinguishing different components, elements, parts, parts or assemblies at different levels. However, if other words can achieve the same purpose, the word can be replaced by other expressions.

[0060] As shown in this application and claims, unless the context clearly indicates an exception, the words "a", "an", "a kind" and / or "the" do not refer to the singular, but also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of clearly identified steps and elements, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements. The elements defined by the sentence "includes a..." do not exclude the existence of other identical elements in the process, method, commodity or device that includes the elements.

[0061] In the description of the embodiments of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B; "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, "multiple" means two or more than two.

[0062] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features.

[0063] If a flow chart is used in the present application, the flow chart is used to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, each step can be processed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or a certain step or several steps of operations can be removed from these processes.

[0064] The above is a detailed introduction to a tobacco aging evaluation method, system, and electronic device, i.e., a storage medium, provided by the present invention. The above description of the disclosed embodiments enables professionals and technicians in the field to implement or use the present invention. Various modifications to these embodiments will be obvious to professionals and technicians in the field, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for evaluating the aging of tobacco leaves, characterized in that: The steps include: Acquire the pre-processed alcoholization image of the tobacco slice to be tested; Inputting the aging image of the tobacco strips to be tested into an aging evaluation model to obtain an aging evaluation result of the tobacco strips to be tested; Wherein, the alcoholization evaluation model is determined by the following steps: Obtain multiple sets of variance and linearity of the pre-processed tobacco sample aging images in different color spaces; Analyze each group of variance and each group of linearity to screen out the color space that meets the preset conditions; The aging evaluation model is constructed according to the elbow method, the K-means clustering algorithm and the color space that meets the preset conditions.

2. The method for evaluating the aging of tobacco leaves according to claim 1, wherein: The method of obtaining multiple groups of variances and linearities of the pre-processed aged tobacco sample images in different color spaces comprises the following steps: Select the aging images of pre-treated tobacco samples from different batches of the same grade; Calculate the standard deviation of each color space based on the STDEVP function and the aged images of pre-processed tobacco samples of different batches of the same grade to obtain the variance corresponding to each color space; According to the SLOPE function and the aging images of the pre-processed tobacco leaf samples of different batches of the same grade, a linear regression analysis is performed on each color space to obtain the linearity corresponding to each color space.

3. The method for evaluating the aging of tobacco leaves according to claim 2, wherein: The analysis of each group of variance and each group of linearity to screen out a color space that meets a preset condition includes the following steps: Compare the corresponding variances and linearities of each group to select the color space that meets the preset conditions; The preset condition is specifically: the variance value and the linearity value are both maximum.

4. The method for evaluating the aging of tobacco leaves according to claim 1, wherein: The method of constructing the alcoholization evaluation model according to the elbow method, the K-means clustering algorithm and the color space satisfying the preset conditions comprises the following steps: Determine a color standard sample according to the elbow method, the K-means clustering algorithm, the aged image of the tobacco strip sample and the preset image of the tobacco strip sample at the end of aged period; Establishing the color standard in the color space that meets the preset conditions; The alcoholization evaluation model is constructed based on the color standard.

5. The method for evaluating tobacco aging according to claim 4, characterized in that: Determining the color standard sample according to the elbow method, the K-means clustering algorithm, the aged image of the tobacco strip sample and the preset image of the tobacco strip sample at the end of aged period comprises the following steps: Determine a plurality of cluster centers according to the elbow method, the aged image of the tobacco strip sample and the preset image of the tobacco strip sample at the end of aged period; According to the K-means clustering algorithm, the Euclidean distance between each element in the aged image of the tobacco strip sample and the preset late-aged image of the tobacco strip sample and each cluster center is calculated respectively, so as to determine the cluster center corresponding to the minimum Euclidean distance; Each element in the aged tobacco sample image and the preset aged tobacco sample image at the end of the aged tobacco sample is assigned to the cluster center corresponding to the minimum Euclidean distance for iterative training until a color standard sample is determined.

6. The method for evaluating the aging of tobacco leaves according to claim 5, wherein: The step of inputting the aging image of the tobacco strips to be tested into the aging evaluation model to obtain the aging evaluation result of the tobacco strips to be tested comprises the following steps: The aging evaluation model calculates and obtains all elements in the aging image of the tobacco leaf to be tested; Obtaining the proportion of each cluster center in the alcoholized image of the tobacco leaf to be tested; Define a linear scoring rate array whose length is the same as the number of cluster centers and whose element values ​​decrease from a preset value; The proportion of each cluster center and the corresponding element of the linear scoring rate array are weightedly summed to obtain the aging evaluation result of the tested tobacco strips.

7. A tobacco aging evaluation system, characterized in that: include: An image module is used to obtain and pre-process the alcohol-aged image of the tobacco leaf to be tested; Model building module, used to build alcoholization evaluation model; The aging evaluation module is used to obtain the aging evaluation result of the tobacco strips to be tested according to the preprocessed aging image of the tobacco strips to be tested and the aging evaluation model.

8. The tobacco aging evaluation system according to claim 7, characterized in that: The model building module includes: a parameter submodule, an analysis module and a building submodule; The parameter submodule is used to obtain multiple sets of variances and linearities of the pre-processed tobacco sample aged images in different color spaces; The analysis submodule is used to analyze each group of variance and each group of linearity to screen out the color space that meets the preset conditions; The construction submodule is used to construct the aging evaluation model according to the elbow method, the K-means clustering algorithm and the color space that meets the preset conditions.

9. An electronic device, characterized in that: include: Memory, storing programs or instructions; A processor, executing the program or instructions; Wherein, when executing the program or instruction, the processor implements the steps of the tobacco aging evaluation method according to any one of claims 1 to 6.

10. A readable storage medium, characterized in that: The readable storage medium stores a program or instruction, and when the program or instruction is executed by the processor, the steps of the tobacco aging evaluation method according to any one of claims 1 to 6 are implemented.

Images