A plant stomatal opening detection method for exploratory experiments and related products

Abstract

This application relates to the field of microscopic image analysis technology and provides a method and related products for detecting plant stomatal aperture in exploratory experiments. The method includes: acquiring leaf epidermal images under different light intensities; segmenting the preprocessed leaf epidermal images; extracting multiple stomatal regions from the segmented leaf epidermal images; calculating stomatal aperture indices for each stomatal region under different light intensities; recording stomatal aperture data from each field of view; removing outliers from the stomatal aperture data to obtain an effective stomatal set; statistically calculating the average and standard deviation of the stomatal aperture data of the effective stomatal set under the same light intensity as representative values ​​for the corresponding light intensities; obtaining fitting results based on the light intensities under various experimental conditions and the representative values ​​for the corresponding light intensities; and generating exploratory experimental conclusions and reports based on the fitting results. This application enables a lightweight quantitative investigation of the relationship between stomatal opening and closing and environmental factors.

Description

Technical Field

[0001] This application relates to the field of microscopic image analysis technology, and in particular to a method for detecting plant stomatal aperture for exploratory experiments, a device for detecting plant stomatal aperture for exploratory experiments, a corresponding electronic device, and a corresponding computer-readable storage medium. Background Technology

[0002] In junior high school biology experiments exploring the effect of light intensity on stomatal opening, the core experimental requirement is to observe the degree of stomatal opening and closing of plant leaves under different light conditions, thereby exploring the intrinsic relationship between the two.

[0003] Currently, this experiment uses traditional teaching methods and various existing detection and analysis technologies, resulting in several significant shortcomings in its overall application. Traditional experiments typically employ manual observation, relying solely on students' naked-eye observation under a microscope. This method only allows for qualitative judgments of stomatal opening and closing, failing to quantify the opening degree and establish a quantitative correlation between light intensity and stomatal opening. Manually measuring stomatal length, width, and area is not only cumbersome and inefficient but also yields poor accuracy. Limited classroom time allows for the selection of only a small number of stomata as observation samples, resulting in insufficient sample coverage, poor representativeness, and an inability to reflect the overall distribution characteristics of leaf stomata. Consequently, the experimental conclusions lack scientific rigor and representativeness, leading to low reliability. Furthermore, the inability to automatically correlate light intensity and stomatal opening to generate the necessary charts and graphs hinders data analysis.

[0004] Currently available auxiliary technologies for stomatal detection also suffer from insufficient adaptability. For example, image measurement software such as ImageJ requires manual annotation of stomatal outlines before size calculation can be completed through software calculation. The operation process is complicated and has a high threshold, making it unsuitable for mass teaching in junior high school classrooms. Furthermore, it cannot automatically link and integrate stomatal detection data with light intensity experimental conditions, and cannot generate the analytical charts required for exploratory experiments. While deep learning-based scientific research-grade stomatal analysis systems based on architectures such as U-Net can achieve high-precision automatic stomatal segmentation and aperture calculation, these models have complex structures, rely on massive amounts of labeled data for training, and are relatively large, making it difficult to run in real time on teaching microscope terminals, which greatly hinders their implementation in teaching scenarios.

[0005] Overall, existing technical solutions generally suffer from problems such as lack of quantification capabilities, low measurement efficiency, disconnect from experimental data, high operational thresholds, and limited sample detection range. They are neither suitable for junior high school students' practical learning abilities nor can they meet the core teaching needs of biological inquiry experiments, such as data statistics, chart generation, and pattern analysis, which seriously restricts the improvement of the teaching effect of this inquiry experiment. Summary of the Invention

[0006] This application provides a method and related products for detecting plant stomatal aperture in exploratory experiments. It can be used for quantitative detection of stomatal aperture and to assist in the exploration of photosynthesis in junior high school teaching scenarios. It can realize automatic stomatal segmentation, automatic calculation of aperture index, light-aperture correlation analysis and visualization, and help students quantitatively explore the relationship between stomatal opening and closing and environmental factors.

[0007] In one aspect, this application provides a method for detecting plant stomatal aperture in exploratory experiments, the method comprising:

[0008] Images of the lower epidermis of leaves under different light intensities were acquired, and the images of the lower epidermis of leaves were preprocessed.

[0009] The preprocessed leaf epidermis image was segmented, and multiple stomatal regions were extracted from the segmented leaf epidermis image.

[0010] The pore opening index is calculated for each pore region under different light intensities; the pore opening index includes aspect ratio, opening area and opening angle.

[0011] Multiple fields of view are scanned, and the stomatal aperture data of each field of view are recorded based on the stomatal aperture index of the stomatal region in each field of view. Abnormal data in the stomatal aperture data are removed to obtain an effective set of stomata.

[0012] Based on the statistical average and standard deviation of the stomatal aperture data of the effective stomatal set under the same light intensity, the average and standard deviation are used as representative values ​​under the corresponding light intensity.

[0013] The fitting results are obtained based on the light intensity under each experimental condition and the representative values ​​under the corresponding light intensity, and the experimental conclusions and experimental reports are generated based on the fitting results; wherein, the fitting results include scatter plots and fitting curves for light intensity and aperture index.

[0014] In some embodiments of this application, the step of segmenting the preprocessed leaf epidermis image and extracting multiple stomatal regions from the segmented leaf epidermis image includes:

[0015] Threshold segmentation is performed on the preprocessed leaf epidermal image to separate the stomatal foreground region and the epidermal tissue background region;

[0016] Noise in the foreground region of the pores is removed by morphological opening operations;

[0017] Connectivity analysis was performed on the stomata foreground region after noise removal, and multiple candidate stomata regions were labeled based on the results of the connectivity analysis.

[0018] Each candidate stomatal region is filtered based on its area to obtain the final multiple stomatal regions.

[0019] In some embodiments of this application, the filtering of each candidate pore region based on the area of ​​each candidate pore region to obtain a final plurality of pore regions includes:

[0020] Candidate pore regions with an area smaller than a preset first area threshold are considered noise and are removed.

[0021] For candidate pore regions with an area greater than a preset second area threshold, pore adhesion is judged. If multiple pores are adhered, the watershed algorithm is used to separate the adhered pores to obtain multiple separated pore regions.

[0022] The candidate pore regions whose area is between the preset first area threshold and the preset second area threshold, as well as the separated multiple pore regions, are taken as the final pore regions.

[0023] In some embodiments of this application, the calculation of stomatal aperture indices for each stomatal region under different light intensities includes:

[0024] For each pore region under different light intensities, the aspect ratio of each pore region is calculated based on the long side and short side of the minimum bounding rectangle of each pore region.

[0025] The opening area of ​​each pore region is obtained by statistically analyzing the pixels of the opening area of ​​each pore region.

[0026] The opening angle of each pore region is calculated based on the minimum circumscribed rectangle angle of each pore region.

[0027] In some embodiments of this application, the pore aperture data includes aspect ratio data; the step of removing abnormal data from the pore aperture data to obtain a valid set of pores includes:

[0028] Calculate the first and third quartiles of the aspect ratio data for each field of view, and define the range of outliers for the aspect ratio data based on the first quartile, the third quartile, and a preset interquartile range.

[0029] By removing pore regions whose aspect ratio falls within the aforementioned outlier range, an effective set of pores is obtained.

[0030] In some embodiments of this application, the fitting result based on the light intensity under various experimental conditions and the representative value under the corresponding light intensity includes:

[0031] Using the light intensity under each experimental condition as the abscissa and the representative value under the corresponding light intensity as the ordinate, a scatter plot of light intensity versus aperture index is drawn.

[0032] Based on the light intensity under various experimental conditions and the representative values ​​under the corresponding light intensity, the preset linear / logarithmic model is fitted to obtain the fitting equation;

[0033] The fitted curve is obtained based on the fitted equation.

[0034] In some embodiments of this application, the fitting result further includes model coefficients, and the method further includes:

[0035] Based on the light intensity under various experimental conditions and the representative values ​​under the corresponding light intensity, the fitting equation is solved to obtain the model coefficients; the model coefficients are used to indicate the sensitivity of the aperture to changes in light intensity.

[0036] In some embodiments of this application, the fitting result further includes a coefficient of determination, and the method further includes:

[0037] The fitted equation is used to calculate the predicted aperture value under the illumination intensity of each experimental condition;

[0038] The coefficient of determination is calculated using the predicted aperture value under the light intensity of each experimental condition and the representative value under the corresponding light intensity; the coefficient of determination is used to evaluate the degree of agreement between the logarithmic model and the measured data.

[0039] On the other hand, this application provides a plant stomatal aperture detection device for exploratory experiments, the device comprising:

[0040] The image acquisition and preprocessing module is used to acquire images of the lower epidermis of leaves under different light intensities and to preprocess the images of the lower epidermis of leaves.

[0041] The stomatal extraction module is used to segment the preprocessed leaf epidermis image and extract multiple stomatal regions from the segmented leaf epidermis image.

[0042] The stomatal aperture index calculation module is used to calculate the stomatal aperture index for each stomatal region under different light intensities; the stomatal aperture index includes aspect ratio, aperture area and aperture angle.

[0043] The effective stoma set acquisition module is used to scan multiple fields of view, record the stoma opening data of each field of view based on the stoma opening index of the stoma region in each field of view, remove abnormal data in the stoma opening data, and obtain the effective stoma set.

[0044] The representative value generation module is used to statistically calculate the average value and standard deviation of the stomatal aperture data of the effective stomatal set under the same light intensity, and use the average value and the standard deviation as the representative value under the corresponding light intensity.

[0045] The fitting result generation module is used to obtain fitting results based on the light intensity under various experimental conditions and the representative values ​​under the corresponding light intensity; wherein, the fitting results include a scatter plot and a fitting curve for the light intensity and aperture index.

[0046] The experimental conclusion generation module is used to generate experimental conclusions and reports based on the fitting results.

[0047] In some embodiments of this application, the stoma extraction module includes:

[0048] The image segmentation submodule is used to perform threshold segmentation on the preprocessed leaf epidermal image to separate the stomatal foreground region and the epidermal tissue background region.

[0049] The noise removal submodule is used to remove noise from the pore foreground region through morphological opening operations.

[0050] The connected component analysis submodule is used to perform connected component analysis on the stoma foreground region after noise removal, and to label multiple candidate stoma regions based on the connected component analysis results.

[0051] The area filtering submodule is used to filter each candidate pore region based on its area to obtain the final multiple pore regions.

[0052] In some embodiments of this application, the area filtering submodule includes:

[0053] The area filtering unit is used to treat candidate pore regions with an area smaller than a preset first area threshold as noise and remove the candidate pore regions that are considered noise; and to determine the pore adhesion of candidate pore regions with an area larger than a preset second area threshold. If multiple pores are adhered, the watershed algorithm is used to separate the adhered pores to obtain multiple separated pore regions.

[0054] The stomatal region extraction unit is used to select candidate stomatal regions whose area is between the preset first area threshold and the preset second area threshold, as well as the separated multiple stomatal regions, as the final stomatal regions.

[0055] In some embodiments of this application, the pore aperture index calculation module includes:

[0056] The aspect ratio calculation submodule is used to calculate the aspect ratio of each pore region under different light intensities based on the long and short sides of the minimum bounding rectangle of each pore region.

[0057] The aperture area calculation submodule is used to obtain the aperture area of ​​each pore region based on the statistical pixel count of each pore region.

[0058] The aperture angle calculation submodule is used to calculate the aperture angle of each pore region based on the minimum circumscribed rectangle angle of each pore region.

[0059] In some embodiments of this application, the pore aperture data includes aspect ratio data; the effective pore set acquisition module includes:

[0060] The effective pore set acquisition submodule is used to calculate the first quartile and the third quartile in the aspect ratio data of each field of view, define the outlier range for the aspect ratio data based on the first quartile, the third quartile and the preset interquartile range, and remove the pore regions whose aspect ratio is located within the outlier range to obtain the effective pore set.

[0061] In some embodiments of this application, the fitting result generation module includes:

[0062] The scatter plot generation submodule is used to draw a scatter plot of light intensity and aperture index with light intensity as the x-axis and the representative value under each light intensity as the y-axis.

[0063] The fitting curve generation submodule is used to fit a preset linear / logarithmic model based on the light intensity under various experimental conditions and the representative value under the corresponding light intensity to obtain a fitting equation; and to obtain a fitting curve based on the fitting equation.

[0064] In some embodiments of this application, the fitting result further includes model coefficients, and the fitting result generation module further includes:

[0065] The model coefficient generation submodule is used to solve the fitting equation based on the light intensity under various experimental conditions and the representative value under the corresponding light intensity to obtain the model coefficients; the model coefficients are used to indicate the sensitivity of the aperture to changes in light intensity.

[0066] In some embodiments of this application, the fitting result further includes a coefficient of determination, and the fitting result generation module further includes:

[0067] The determination coefficient generation submodule is used to calculate the predicted aperture value under the light intensity of each experimental condition using the fitted equation; and to calculate the determination coefficient using the predicted aperture value under the light intensity of each experimental condition and the representative value under the corresponding light intensity; the determination coefficient is used to evaluate the degree of agreement between the logarithmic model and the measured data.

[0068] In another aspect, this application also provides an electronic device, including: a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program, when executed by the processor, implements any of the plant stomatal aperture detection methods for exploratory experiments described in the present application.

[0069] In another aspect, this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements any of the plant stomatal aperture detection methods for exploratory experiments described in the present application.

[0070] In another aspect, this application also provides a computer program product containing instructions that, when run on a computer, cause the computer to perform the plant stomatal aperture detection method for exploratory experiments described in the above aspects.

[0071] The plant stomatal aperture detection method and related products provided in this application for exploratory experiments preprocess leaf epidermal images collected under different light intensities, segment the preprocessed leaf epidermal images, extract multiple stomatal regions, and then calculate stomatal aperture indices for each stomatal region under different light intensities. Multiple fields of view can be scanned, stomatal aperture data for each field of view can be recorded, and outliers can be extracted to obtain an effective stomatal set. Then, the average value and standard deviation of the stomatal aperture data of the effective stomatal set under the same light intensity can be statistically analyzed and used as representative values ​​for the corresponding light intensities. Finally, based on the light intensities under various experimental conditions and the representative values ​​for the corresponding light intensities, scatter plots and fitting curves for light intensity and aperture indices are generated, and exploratory experimental conclusions and reports can be generated based on the aforementioned fitting results. This application achieves automatic stomatal segmentation and quantification based on morphology, and realizes correlation analysis and fitting between light intensity and stomatal opening based on multi-view stomatal opening statistics and outlier removal. Thus, it enables a lightweight quantitative study of the relationship between stomatal opening and closing and environmental factors without the need for deep learning. Attached Figure Description

[0072] Figure 1 This is a flowchart of the steps of a plant stomatal aperture detection method for exploratory experiments provided in an embodiment of this application;

[0073] Figure 2 This is a schematic diagram of the process for detecting plant stomatal aperture in an exploratory experiment provided in an embodiment of this application;

[0074] Figure 3 This is a schematic diagram illustrating the implementation process of image acquisition and preprocessing provided in the embodiments of this application;

[0075] Figure 4 This is a schematic diagram illustrating the implementation process of pore detection and segmentation provided in the embodiments of this application;

[0076] Figure 5 This is a schematic diagram illustrating the implementation process of calculating the opening index provided in the embodiments of this application;

[0077] Figure 6 This is a schematic diagram illustrating the implementation process of multi-view statistics provided in the embodiments of this application;

[0078] Figure 7 This is a schematic diagram illustrating the implementation process of illumination correlation analysis provided in the embodiments of this application;

[0079] Figure 8 This is a schematic diagram illustrating the implementation process of the visualization report provided in this application embodiment;

[0080] Figure 9 This is a schematic diagram illustrating the implementation process of photo archiving provided in an embodiment of this application;

[0081] Figure 10 This is a structural block diagram of a plant stomatal aperture detection device for exploratory experiments provided in an embodiment of this application;

[0082] Figure 11 This is a structural block diagram of an electronic device provided in an embodiment of this application;

[0083] Figure 12 This is a structural block diagram of a computer-readable storage medium provided in an embodiment of this application. Detailed Implementation

[0084] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0085] To facilitate understanding of the embodiments of this application by those skilled in the art, the technical terms involved are explained as follows:

[0086] Stomata: These are small pores formed by guard cells on the epidermis of plant leaves, which are channels for gas exchange.

[0087] Guard cells: These are a pair of specialized cells that make up the stomata, and their shape changes can be used to control the opening and closing of the stomata.

[0088] Opening degree: refers to the degree to which the pores are open, which can be quantified by indicators such as aspect ratio, opening area, and opening angle.

[0089] Aspect ratio: refers to the ratio of the longer side to the shorter side of the rectangle circumscribed by the vent; the larger the opening, the smaller the aspect ratio.

[0090] Opening area: refers to the pixel area of ​​the actual opening region of the vent, which can be converted into the actual area by pixel equivalent, and the unit is μm².

[0091] The minimum area bounding rectangle is the rectangle with the smallest area that encloses all pixels of the target outline.

[0092] Light intensity: refers to the intensity of light received by the leaf during the experiment, measured in lux, and can be recorded by the brightness sensor of the microscope light source.

[0093] Automatic Global Optimal Threshold Segmentation Algorithm: Otsu Threshold Segmentation (Otsu Method) does not require manual threshold setting and can automatically divide images into foreground and background categories. Specifically, it can automatically distinguish between dark areas of pores and bright backgrounds of the epidermis in grayscale images.

[0094] This application's embodiments design a lightweight stomatal segmentation and aperture calculation scheme for teaching scenarios. Without requiring deep learning, it automatically correlates light intensity, generating scatter plots and fitted curves needed for exploratory experiments. This lightweight approach enables quantitative investigation of the relationship between stomatal opening and closing and environmental factors. Specifically, it can automatically identify all stomata in the field of view based on morphological or lightweight image segmentation algorithms, achieving automatic stomatal segmentation; it can design teaching-grade aperture quantification indicators based on multi-dimensional quantification such as aspect ratio, aperture area, and aperture angle; it can achieve multi-field statistical analysis and outlier removal by automatically scanning multiple fields of view and statistically analyzing averages and distributions; it can generate scatter plots and fitted curves based on automatically recording light intensity, enabling correlation analysis between light intensity and aperture indicators; and it can output analytical charts and experimental conclusions, generating a visual report.

[0095] Reference Figure 1 This document illustrates a flowchart of a plant stomatal aperture detection method for exploratory experiments, provided by an embodiment of this application. Applied to a plant stomatal aperture exploratory experiment auxiliary system, the method may specifically include the following steps:

[0096] Step S101: Collect images of the lower epidermis of leaves under different light intensities and preprocess the images.

[0097] In some embodiments of this application, such as Figure 2 The image acquisition and preprocessing stage shown can acquire images of the lower epidermis of leaves under different lighting conditions, i.e., different light intensities, and perform preprocessing such as denoising and enhancement on the images of the lower epidermis of leaves, so as to eliminate image noise and improve image clarity, thus providing a foundation for subsequent image recognition and analysis.

[0098] In practical applications, students can place leaves under different light intensities, such as darkness, low light, and strong light, and peel off the epidermis to make temporary slides; then the system can acquire images of the lower epidermis through a microscope, mainly 40× and 100× objectives.

[0099] Optional, such as Figure 3 As shown, the denoising process performed on the leaf epidermis image can be represented by removing noise through median filtering (such as 3×3 kernels); the enhancement process performed on the leaf epidermis image can be represented by adaptive histogram equalization to enhance contrast, specifically enhancing the contrast between cells and background, which is helpful for subsequent stomatal detection and segmentation.

[0100] Step S102: Segment the preprocessed leaf epidermis image and extract multiple stomatal regions from the segmented leaf epidermis image.

[0101] In some embodiments of this application, such as Figure 2 The stoma detection and segmentation stage shown can extract the stomatal region through morphological or lightweight segmentation algorithms to lock the target stomatal region, remove irrelevant background interference, and achieve effective extraction of individual stomatal cells.

[0102] Optional, such as Figure 4 As shown, firstly, threshold segmentation can be performed on the preprocessed leaf epidermal image to separate the stomatal foreground region from the epidermal tissue background region. Then, noise in the stomatal foreground region can be removed by morphological opening operation, and connected component analysis can be performed on the noise-removed stomatal foreground region. Based on the connected component analysis results, multiple candidate stomatal regions are labeled.

[0103] In some embodiments of this application, each candidate pore region can be filtered based on its area to obtain a pore mask, thus obtaining multiple final pore regions. Here, a pore region refers to the area of ​​a single pore; that is, multiple pore regions correspond to multiple individual pores.

[0104] The purpose of area filtering is to eliminate areas that are too small or too large. In practical applications, candidate pore areas with an area smaller than a preset first area threshold (i.e., too small) can be considered noise and removed. Candidate pore areas with an area larger than a preset second area threshold (i.e., too large) are then filtered as follows: Figure 4 The stomatal adhesion determination shown can be performed by using a watershed algorithm to separate the adhered pores if multiple pores are adhered. This results in multiple separated pore regions. Finally, the candidate pore regions with areas between a preset first area threshold and a preset second area threshold, along with the multiple separated pore regions, can be used as the final pore regions.

[0105] For example, the threshold segmentation performed can be Otsu threshold segmentation. After Otsu segmentation, multiple connected components are obtained. Assuming a preset first area threshold of 50 pixels and a preset second area threshold of 2000 pixels, candidate pore regions with an area less than 50 pixels can be considered as noise, while candidate pore regions with an area greater than 2000 pixels are considered to have multiple pores adhering together, requiring further segmentation. Specifically, adhering pores can be separated using a watershed algorithm, ultimately resulting in, for example, 15 individual pores. It should be noted that the preset first and second area thresholds can be set based on actual needs, and this embodiment does not impose any limitations on this.

[0106] Step S103: Calculate the stomatal aperture index for each stomatal region under different light intensities.

[0107] In some embodiments of this application, such as Figure 2 In the stage of calculating the opening index shown, for each pore region under different light intensities, a multi-dimensional pore opening index can be calculated for each pore region. Specifically, it can include aspect ratio, opening area and opening angle, thereby quantifying the pore morphological characteristics and intuitively representing the degree of pore opening and closing in numerical form.

[0108] Among them, the length-to-width ratio can be used to indicate the shape of stomata. The larger the opening, the smaller the length-to-width ratio, that is, the stomata of plants tend to be circular. The opening area can be used to indicate the actual gas exchange area. The opening angle can be used to indicate the degree of expansion of guard cells.

[0109] Optionally, for aspect ratio calculation, such as Figure 5 As shown, it can be calculated based on the long and short sides of the minimum bounding rectangle of each pore region. For example, the specific calculation formula is as follows:

[0110]

[0111] In the formula, R is the aspect ratio of the pore region; L is the long side of the minimum bounding rectangle of the pore region; and W is the short side of the minimum bounding rectangle of the pore region.

[0112] Optionally, for calculating the opening area, such as Figure 5 As shown, this can be obtained based on the number of pixels in the opening area of ​​each pore region. For example, the specific calculation formula is as follows:

[0113]

[0114] In the formula, A is the opening area of ​​the pore region; N is the total number of pixels in the pore region, which can be obtained by counting the pixels in the opening region; d is the pixel equivalent (unit: μm / pixel), which can be automatically calculated using the microscope scale or a known objective lens magnification.

[0115] Optionally, for the calculation of the opening angle, such as Figure 5 As shown, the angle can be calculated based on the minimum bounding rectangle angle of each pore region. For example, the specific calculation formula is as follows:

[0116]

[0117] In the formula, θ is the opening angle of the pore region; L is the long side of the minimum circumscribed rectangle; and W is the short side of the minimum circumscribed rectangle.

[0118] For example, assuming the minimum bounding rectangle of a pore region has a length and width of L = 15 μm and W = 10 μm, the calculated aspect ratio is R = 1.5. The opening area can be obtained by multiplying the number of pixels in the opening region by the pixel equivalent, for example, A = 120. .

[0119] Step S104: Scan multiple fields of view, record the stomatal aperture data of each field of view based on the stomatal aperture index of the stomatal region in each field of view, remove abnormal data in the stomatal aperture data, and obtain the effective set of stomata.

[0120] In some embodiments of this application, such as Figure 2 The multi-field statistical stage shown can scan multiple fields of view, calculate the average value and standard deviation, and remove outliers, thereby avoiding single-sample random errors, reducing data noise and purifying the data, and ensuring that the test results are objective and reliable.

[0121] Specifically, multiple fields of view (recommended ≥5) can be collected and the stomatal aperture data of each field of view can be recorded. The field of view refers to the complete circular visible area that can be seen in the eyepiece after the microscope is focused. In other words, the stomatal aperture index of the stomatal area contained in multiple visible areas can be collected.

[0122] After collecting stomatal aperture data from multiple fields of view, outliers can be removed. Specifically, box plots can be used to remove outliers.

[0123] Optional, such as Figure 6 As shown, the first quartile, third quartile, and preset interquartile range of all stomatal aperture indices in each field of view can be calculated. Based on the first quartile, third quartile, and preset interquartile range, the outlier range for aspect ratio data is defined, and stomatal regions located within the outlier range are removed to obtain the effective set of stomatal apertures, thus completing the removal of outliers.

[0124] In practical applications, aspect ratio can be used as the primary indicator. That is, the first quartile (Q1) and third quartile (Q3) of the aspect ratio data for each field of view can be calculated. Then, based on the first quartile (Q1), the third quartile (Q3), and a preset interquartile range (IQR), the range of outliers for the aspect ratio data can be defined. ,in, At this point, pore regions with aspect ratios in the outlier range can be directly removed to obtain an effective set of pores.

[0125] It should be noted that the pore area is the actual gas exchange area, mainly used in exploratory experiments to help understand gas exchange. For example, students need to understand the causal chain of "larger stomatal opening—more gas exchange—stronger photosynthesis." The pore angle is used to calculate the degree of guard cell expansion, mainly helping to identify false opening and measurement anomalies. For example, students need to know that the understanding that "guard cell expansion = stomatal opening" is incorrect. That is, apart from the aspect ratio, the other two aperture indicators are mainly used as auxiliary verification indicators to serve teaching scenarios, and this application embodiment does not limit them.

[0126] Step S105: Calculate the average value and standard deviation of the stomatal aperture data of the effective stomatal set under the same light intensity, and use the average value and standard deviation as the representative value under the corresponding light intensity.

[0127] The effective set of pores can include the pore regions corresponding to the remaining aspect ratio data after removing outliers.

[0128] In some embodiments of this application, after removing outliers, the mean and standard deviation of the remaining data can be calculated as representative values ​​under the lighting conditions.

[0129] Optionally, the representative value is a composite data structure, which may include three indicators for each pore region in the effective pore set: the aspect ratio, the pore area, and the mean and standard deviation of the pore angle.

[0130] For example, assuming the aspect ratio of 50 pore regions is measured under 1000 lux illumination, the calculated first quartile Q1 = 1.2, the third quartile Q3 = 1.8, and the interquartile range IQR = 0.6, while setting the outlier range to <0.3 or >2.7, if no pores fall within the aforementioned outlier range, the average value μ = 1.52 and the standard deviation σ = 0.24 can be obtained, for example. This application does not impose any limitations on this.

[0131] Step S106: Based on the light intensity under each experimental condition and the representative value under the corresponding light intensity, obtain the fitting result, and generate the experimental conclusion and experimental report based on the fitting result.

[0132] In some embodiments of this application, such as Figure 2 The illumination correlation analysis stage shown can record illumination intensity and generate scatter plots and fitting curves to explore the variation patterns of illumination intensity and stomatal opening, and clarify the intrinsic correlation characteristics between the two.

[0133] In practical applications, the system can record the light intensity under various experimental conditions, specifically through a microscope light source brightness sensor or student input, and then generate data such as... Figure 7 The scatter plot and fitted curve of "opening degree - illumination intensity" are shown.

[0134] Optionally, for generating a scatter plot of light intensity and aperture index, the light intensity under each experimental condition can be used as the abscissa and the representative value under the corresponding light intensity as the ordinate to draw a scatter plot of light intensity and aperture index.

[0135] Optionally, for generating the fitted curve, a preset linear / logarithmic model can be fitted based on the light intensity under each experimental condition and the representative value under the corresponding light intensity to obtain the fitted equation, and then the fitted curve can be obtained based on the fitted equation.

[0136] For example, to help students understand the stimulus-response relationship in biology, the system can use a logarithmic model for fitting, and the specific fitting equation can be as follows:

[0137]

[0138] In the formula, R is the stomatal aperture index, such as aspect ratio; I is the light intensity, in lux; ln is the natural logarithm function, which can be based on the natural constant e (≈2.718); for I+1, when I=0, ln(1) can make the model give a reasonable intercept b when there is no light, that is, the value of b can be equal to the measured value of the stomatal aperture index (such as aspect ratio) when the light intensity is 0 lux; a is the model coefficient.

[0139] Optionally, the fitted equation can be solved based on the light intensity under various experimental conditions and the representative value under the corresponding light intensity to obtain the model coefficient 'a'. The model coefficient 'a' can be used to indicate the sensitivity of the aperture to changes in light intensity. Optionally, when 'a' < 0, the aperture can decrease as the light intensity increases; for example, the aspect ratio can decrease as the light intensity increases.

[0140] Optional, such as Figure 7 As shown, the coefficient of determination can also be calculated. Specifically, the predicted aperture value under the light intensity of each experimental condition can be calculated using the fitting equation, and then the predicted aperture value under the light intensity of each experimental condition and the representative value under the corresponding light intensity can be used to calculate the coefficient of determination.

[0141] For example, the specific calculation formula can be as follows:

[0142]

[0143] In the formula, R 2 R is the coefficient of determination; i These are measured values; This is a predicted value; This is the overall average.

[0144] The coefficient of determination is used to evaluate the good agreement between the logarithmic model and the measured data. 2 The closer the value is to 1, the better the model fit and the stronger its explanatory power. Optionally, the system can set threshold conditions for judgment, such as R... 2 A value ≥0.8 is considered reliable; R0.8 2 A value less than 0.6 is considered unreliable. In cases where the value is unreliable, the system may prompt you to check the experimental conditions. This application does not impose any restrictions on this.

[0145] For example, suppose that in a certain experiment, the average aspect ratio data under different light intensities were measured as shown in Table 1 below:

[0146] Table 1. Average Aspect Ratio Measurement Data

[0147]

[0148] The system can perform logarithmic model fitting on data ranging from 0 to 500 lux, and the resulting fitting equation is: At this point, the predicted values ​​for each point can be calculated. For example, the aspect ratio at 0 lux is 2.85, which matches the above measurement data; the aspect ratio at 500 lux is 2.85 - 0.48 × 6.22 = 2.85 - 2.99 = -0.14, which is a negative predicted value and is unreasonable. At this time, the system can provide a prompt stating "The system has detected that the predicted value at 500 lux has exceeded the reasonable range," and automatically indicate "The logarithmic model predicts well within the 0~500 lux range (R²)." 2 The teaching prompt states that "the predicted value is 0.96, but becomes negative after 500 lux".

[0149] This process helps students establish the connection between mathematical models and cellular physiological phenomena, clarifying that the fitted equation is a form of expression, and the fundamental reason is the essential mismatch between biological saturation phenomena and the logarithmic function's unbounded nature. This manifests as the logarithmic model being effective in the 0~500 lux range, but failing when extrapolated to higher illumination levels because it cannot describe the saturation plateau.

[0150] It should be noted that, since stronger light results in more rounded stomata (i.e., smaller aspect ratio), and ln(I+1) increases with increasing light intensity, a negative number 'a' can be used in practical applications to lower the aspect ratio, making the formula consistent with biological facts. Furthermore, because stomatal aperture has a physiological saturation limit, the logarithmic function cannot describe the plateau phase after saturation; therefore, this mathematical model has an applicable range and cannot be directly extrapolated to higher light intensity ranges. Also, while stomatal aperture increases with increasing light intensity, it cannot increase indefinitely. When the light intensity reaches a certain value, the stomata are fully open, and the aperture enters a saturation plateau phase. At this point, even if the light intensity continues to increase, the aspect ratio will not decrease but will tend to stabilize, such as approaching 1.0. This application's embodiments do not impose any limitations on this.

[0151] In some embodiments of this application, such as Figure 2 The visualization report generation stage shown can output analysis charts and experimental conclusions to present the analysis data and research results intuitively, and systematically output judgment conclusions to facilitate the review and evaluation of results.

[0152] In practical applications, such as Figure 8 As shown, the automatically generated experiment report can include the following teaching content: fitting results, statistical tables, and conclusions and suggestions. Optionally, the fitting results can include scatter plots, fitting curves, model coefficients, and coefficients of determination.

[0153] The scatter plot can be drawn with light intensity on the x-axis and stomatal aperture index on the y-axis; the fitted curve can be obtained based on the fitted equation; the model coefficients and coefficients of determination can be calculated based on the fitted equation; the statistical table can record the number of stomata, average aperture, and standard deviation under each light condition; the conclusion suggestion can refer to the experimental conclusions automatically generated based on the fitting results. An example is shown in Table 2 below:

[0154] Table 2. Conclusions of the exploratory experiment automatically generated based on the fitting results.

[0155]

[0156] It should be noted that, as Figure 2 The stage flow shown is the execution flow of a single experiment. The system can be directly deployed and reused after development, and teachers and students do not need to rebuild the software system every time. The conclusion examples shown in Table 2 are only a demonstration of ideal conditions. In the actual system, the conclusions of the exploratory experiment can be dynamically generated based on the fitting parameters of the current experiment and the rationality of the prediction. This application embodiment does not limit this.

[0157] In some embodiments of this application, such as Figure 2 During the photo saving stage, as shown, the system can respond to the user's touch command to save the photo, and then the system can perform actions such as... Figure 9The system saves the original images (i.e., images of the leaf epidermis under various light conditions), labeled images (including stomatal boundaries and aperture values), statistical data (in CSV format), analysis reports (in PDF format), and metadata (such as time, objective magnification, plant species, student ID, etc.). Optionally, the system can also classify and store the data according to light groups during the saving process.

[0158] In the embodiments of this application, automatic stomatal segmentation can be achieved in a lightweight manner based on morphological and connected component analysis, without the need for deep learning. Specifically, the stomatal aperture of plants can be quantified based on aperture indices by defining and calculating aspect ratio, aperture area, and aperture angle; data reliability can be improved and the overall stomatal distribution can be reflected through multi-view statistics and outlier removal; light conditions can be automatically recorded and scatter plots and fitted curves can be generated through light-aperture correlation analysis; and educational-grade visualization reports can be provided to intuitively display the results of exploratory experiments.

[0159] Optionally, the stomatal segmentation alternative in this application embodiment can also adopt U-Net semantic segmentation, which is implemented through end-to-end segmentation via deep learning. This segmentation scheme has high accuracy and is suitable for scientific research-level analysis, but it requires labeled data and has a large model size. The stomatal segmentation alternative can also adopt the watershed algorithm, which is implemented based on gradient segmentation. This segmentation scheme does not require training, but it is prone to oversegmentation and is suitable for scenarios with large stomatal spacing.

[0160] The alternative scheme for the aperture index in this application embodiment can also use the equivalent diameter, which is achieved by calculating the equivalent circle diameter of the pore area. This calculation method is simple, but it cannot reflect shape changes. The alternative scheme for the aperture index can also use the Fourier descriptor, which is achieved by describing the boundary with Fourier coefficients. This calculation method is accurate, but the amount of calculation is large.

[0161] The alternative to association analysis in this application can also be linear regression, which is achieved by directly fitting a straight line. This analysis method is simple, but may not conform to biological laws. Another alternative to association analysis can be an exponential model, which is achieved through... In this model, R is the dependent variable (corresponding to light intensity), I is the independent variable (corresponding to light intensity), a is the initial amplitude coefficient, and b is the attenuation coefficient. The aforementioned exponential model represents the exponential decay of light intensity as light intensity increases. This analytical approach has a simple mathematical form and is suitable for describing a process that tends to stabilize after rapid changes, but its parameters are nonlinear, making the fitting process slightly complex. Another alternative to correlation analysis is piecewise linear regression, which involves dividing the data into low-light and high-light segments and fitting straight lines to each segment. This approach can intuitively explain the phenomenon of "rapid response under low light and gradual change under high light," but it has the disadvantage of potentially subjective bias due to the manual division of intervals. Another alternative to correlation analysis is machine learning models, such as random forests and support vector machines. These models do not require a pre-defined function form and automatically learn the nonlinear relationships in the data. This approach has high fitting accuracy and can capture complex patterns, but its model is not interpretable and is not suitable for teaching.

[0162] This application does not limit the scope of the embodiments.

[0163] It should be noted that, for the sake of simplicity, the method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments of this application are not limited to the described order of actions, because according to the embodiments of this application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of this application.

[0164] Reference Figure 10 The diagram shows a structural block diagram of a plant stomatal aperture detection device for exploratory experiments provided in an embodiment of this application, which may specifically include the following modules:

[0165] The image acquisition and preprocessing module 1001 is used to acquire images of the lower epidermis of leaves under different light intensities, preprocess the images of the lower epidermis of leaves, and obtain preprocessed images of the lower epidermis of leaves.

[0166] The stomatal extraction module 1002 is used to segment the preprocessed leaf epidermis image and extract multiple stomatal regions from the segmented leaf epidermis image.

[0167] The stomatal aperture index calculation module 1003 is used to calculate the stomatal aperture index for each stomatal region under different light intensities; the stomatal aperture index includes aspect ratio, opening area and opening angle.

[0168] The effective stoma set acquisition module 1004 is used to scan multiple fields of view, record the stoma opening data of each field of view based on the stoma opening index of the stoma region in each field of view, remove abnormal data in the stoma opening data, and obtain the effective stoma set.

[0169] The representative value generation module 1005 is used to statistically calculate the average value and standard deviation of the stomatal aperture data of the effective stomatal set under the same light intensity, and use the average value and standard deviation as the representative value under the corresponding light intensity.

[0170] The fitting result generation module 1006 is used to obtain fitting results based on the light intensity under various experimental conditions and the representative values ​​under the corresponding light intensity; wherein, the fitting results include scatter plots and fitting curves for the light intensity and aperture index.

[0171] The experimental conclusion generation module 1007 is used to generate experimental conclusions and reports based on the fitting results.

[0172] In some embodiments of this application, the stoma extraction module 1002 may include the following sub-modules:

[0173] The image segmentation submodule is used to perform threshold segmentation on the preprocessed leaf epidermal image to separate the stomatal foreground region from the epidermal tissue background region.

[0174] The noise removal submodule is used to remove noise in the pore foreground region through morphological opening operations;

[0175] The connected component analysis submodule is used to perform connected component analysis on the stoma foreground region after noise removal, and to label multiple candidate stoma regions based on the connected component analysis results.

[0176] The area filtering submodule is used to filter each candidate pore region based on its area to obtain the final multiple pore regions.

[0177] In some embodiments of this application, the area filtering submodule may include the following units:

[0178] The area filtering unit is used to treat candidate pore regions with an area smaller than a preset first area threshold as noise and remove the candidate pore regions that are considered noise; and to determine the pore adhesion of candidate pore regions with an area larger than a preset second area threshold. If multiple pores are adhered, the watershed algorithm is used to separate the adhered pores to obtain multiple separated pore regions.

[0179] The stomatal region extraction unit is used to select candidate stomatal regions whose area is between a preset first area threshold and a preset second area threshold, as well as the separated multiple stomatal regions, as the final stomatal regions.

[0180] In some embodiments of this application, the stomatal aperture index calculation module 1003 may include the following sub-modules:

[0181] The aspect ratio calculation submodule is used to calculate the aspect ratio of each pore region under different light intensities based on the long and short sides of the minimum bounding rectangle of each pore region.

[0182] The aperture area calculation submodule is used to obtain the aperture area of ​​each pore region based on the statistical pixel count of each pore region.

[0183] The aperture angle calculation submodule is used to calculate the aperture angle of each pore region based on the minimum circumscribed rectangle angle of each pore region.

[0184] In some embodiments of this application, the stomata aperture data includes aspect ratio data; the effective stomata set acquisition module 1004 may include the following sub-modules:

[0185] The effective pore set acquisition submodule is used to calculate the first and third quartiles of the aspect ratio data in each field of view, define the outlier range for the aspect ratio data based on the first and third quartiles and the preset interquartile range, and remove pore regions whose aspect ratios are within the outlier range to obtain the effective pore set.

[0186] In some embodiments of this application, the fitting result generation module 1006 may include the following sub-modules:

[0187] The scatter plot generation submodule is used to draw a scatter plot of light intensity and aperture index with light intensity as the x-axis and the representative value under each light intensity as the y-axis.

[0188] The curve fitting generation submodule is used to fit a preset linear / logarithmic model based on the light intensity under various experimental conditions and the representative value under the corresponding light intensity to obtain the fitting equation; and to obtain the fitting curve based on the fitting equation.

[0189] In some embodiments of this application, the fitting result further includes model coefficients, and the fitting result generation module 306 may further include the following sub-modules:

[0190] The model coefficient generation submodule is used to solve the fitting equation based on the light intensity under various experimental conditions and the representative value under the corresponding light intensity to obtain the model coefficients; the model coefficients are used to indicate the sensitivity of the aperture to changes in light intensity.

[0191] In some embodiments of this application, the fitting result further includes a coefficient of determination, and the fitting result generation module 1006 may further include the following sub-modules:

[0192] The coefficient of determination generation submodule is used to calculate the predicted aperture value under the light intensity of each experimental condition using the fitted equation; the coefficient of determination is calculated using the predicted aperture value under the light intensity of each experimental condition and the representative value under the corresponding light intensity; the coefficient of determination is used to evaluate the degree of agreement between the logarithmic model and the measured data.

[0193] In this embodiment, leaf epidermal images under different light intensities are preprocessed, segmented, and multiple stomatal regions are extracted. Stomatal aperture indices are then calculated for each stomatal region under different light intensities. Multiple fields of view are scanned, stomatal aperture data are recorded for each field of view, and outliers are extracted to obtain an effective stomatal set. The average and standard deviation of the stomatal aperture data of the effective stomatal set under the same light intensity are then statistically analyzed and used as representative values ​​for the corresponding light intensities. Finally, scatter plots and fitting curves for light intensity and aperture indices are generated based on the light intensities under various experimental conditions and the representative values ​​for the corresponding light intensities. Experimental conclusions and reports can be generated based on the aforementioned fitting results. This application achieves automatic stomatal segmentation and aperture quantification based on morphology, and realizes correlation analysis and fitting between light intensity and stomatal aperture based on multi-field stomatal aperture statistics and outlier removal. This allows for a lightweight quantitative investigation of the relationship between stomatal opening and closing and environmental factors without the need for deep learning.

[0194] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0195] This application also provides an electronic device, see embodiments thereof. Figure 11 The provided electronic device 1100 includes a memory 1110, a processor 1120, and a computer program 1111 stored in the memory 1110 and capable of running on the processor 1120. When the computer program 1111 is executed by the processor, it implements the various processes of the above-described embodiment of the plant stomatal aperture detection method for exploratory experiments and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0196] This application also provides a computer-readable storage medium, see embodiments thereof. Figure 12 The computer-readable storage medium 1200 provided stores a computer program 1111. When the computer program 1111 is executed by the processor, it implements the various processes of the above-described embodiment of the plant stomatal aperture detection method for exploratory experiments and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0197] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0198] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of the embodiments of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or modules is not necessarily limited to those steps or modules explicitly listed, but may include other steps or modules not explicitly listed or inherent to these processes, methods, products, or devices. The division of modules in the embodiments of this application is merely a logical division; in actual applications, there may be other division methods. For example, multiple modules may be combined into or integrated into another system, or some features may be ignored or not performed. Additionally, the shown or discussed mutual coupling or direct coupling or communication connection may be through some interface, and the indirect coupling or communication connection between modules may be electrical or other similar forms, none of which are limited in the embodiments of this application. Furthermore, the modules or sub-modules described as separate components may or may not be physically separated, may or may not be physical modules, or may be distributed among multiple circuit modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the embodiments of this application.

[0199] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0200] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and modules described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0201] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between devices or modules through some interfaces, and may be electrical, mechanical, or other forms.

[0202] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0203] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium.

[0204] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product.

[0205] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0206] This application describes embodiments with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0207] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The functions specified in one or more boxes; these computer program instructions may also be loaded onto a computer or other programmable data processing terminal equipment to cause a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0208] Although preferred embodiments of the present application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present application.

[0209] Finally, it should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation portals are provided for users to choose to authorize or refuse.

[0210] The technical solutions provided in the embodiments of this application have been described in detail above. Specific examples have been used in the embodiments of this application to illustrate the principles and implementation methods of the embodiments of this application. The description of the above embodiments is only for the purpose of helping to understand the methods and core ideas of the embodiments of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the embodiments of this application. Therefore, the content of this specification should not be construed as a limitation on the embodiments of this application.

Claims

1. A method for detecting plant stomatal aperture in exploratory experiments, characterized in that, The method includes: Images of the lower epidermis of leaves under different light intensities were acquired, and the images of the lower epidermis of leaves were preprocessed. The preprocessed leaf epidermis image was segmented, and multiple stomatal regions were extracted from the segmented leaf epidermis image. The pore opening index is calculated for each pore region under different light intensities; wherein the pore opening index includes aspect ratio, opening area and opening angle. Multiple fields of view are scanned, and the stomatal aperture data of each field of view are recorded based on the stomatal aperture index of the stomatal region in each field of view. Abnormal data in the stomatal aperture data are removed to obtain an effective set of stomata. Based on the statistical average and standard deviation of the stomatal aperture data of the effective stomatal set under the same light intensity, the average and standard deviation are used as representative values ​​under the corresponding light intensity. The fitting results are obtained based on the light intensity under each experimental condition and the representative values ​​under the corresponding light intensity, and the experimental conclusions and experimental reports are generated based on the fitting results; wherein, the fitting results include scatter plots and fitting curves for light intensity and aperture index.

2. The method according to claim 1, characterized in that, The preprocessed leaf epidermis image is segmented, and multiple stomatal regions are extracted from the segmented leaf epidermis image, including: Threshold segmentation is performed on the preprocessed leaf epidermal image to separate the stomatal foreground region and the epidermal tissue background region; Noise in the foreground region of the pores is removed by morphological opening operations; Connectivity analysis was performed on the stomata foreground region after noise removal, and multiple candidate stomata regions were labeled based on the results of the connectivity analysis. Each candidate stomatal region is filtered based on its area to obtain the final multiple stomatal regions.

3. The method according to claim 2, characterized in that, The process of filtering candidate stomatal regions based on their area yields a final set of multiple stomatal regions, including: Candidate pore regions with an area smaller than a preset first area threshold are considered noise and are removed. For candidate pore regions with an area greater than a preset second area threshold, pore adhesion is judged. If multiple pores are adhered, the watershed algorithm is used to separate the adhered pores to obtain multiple separated pore regions. The candidate pore regions whose area is between the preset first area threshold and the preset second area threshold, as well as the separated multiple pore regions, are taken as the final pore regions.

4. The method according to claim 1, characterized in that, The calculation of stomatal aperture indices for each stomatal region under different light intensities includes: For each pore region under different light intensities, the aspect ratio of each pore region is calculated based on the long side and short side of the minimum bounding rectangle of each pore region. The opening area of ​​each pore region is obtained by statistically analyzing the pixels of the opening area of ​​each pore region. The opening angle of each pore region is calculated based on the minimum circumscribed rectangle angle of each pore region.

5. The method according to claim 1, characterized in that, The stomatal aperture data includes aspect ratio data; the process of removing outlier data from the stomatal aperture data to obtain a valid set of stomata includes: Calculate the first and third quartiles of the aspect ratio data for each field of view, and define the range of outliers for the aspect ratio data based on the first quartile, the third quartile, and a preset interquartile range. By removing pore regions whose aspect ratio falls within the aforementioned outlier range, an effective set of pores is obtained.

6. The method according to claim 1, characterized in that, The fitting results are obtained based on the light intensity under various experimental conditions and the representative values ​​under the corresponding light intensity, including: Using the light intensity under each experimental condition as the abscissa and the representative value under the corresponding light intensity as the ordinate, a scatter plot of light intensity versus aperture index is drawn. Based on the light intensity under various experimental conditions and the representative values ​​under the corresponding light intensity, the preset linear / logarithmic model is fitted to obtain the fitting equation; The fitted curve is obtained based on the fitted equation.

7. The method according to claim 6, characterized in that, The fitting result also includes model coefficients, and the method further includes: Based on the light intensity under various experimental conditions and the representative values ​​under the corresponding light intensity, the fitting equation is solved to obtain the model coefficients; the model coefficients are used to indicate the sensitivity of the aperture to changes in light intensity. The fitting result also includes a coefficient of determination, and the method further includes: The fitted equation is used to calculate the predicted aperture value under the illumination intensity of each experimental condition; The coefficient of determination is calculated using the predicted aperture value under the light intensity of each experimental condition and the representative value under the corresponding light intensity; the coefficient of determination is used to evaluate the degree of agreement between the logarithmic model and the measured data.

8. A plant stomatal aperture detection device for exploratory experiments, characterized in that, The device includes: The image acquisition and preprocessing module is used to acquire images of the lower epidermis of leaves under different light intensities and to preprocess the images of the lower epidermis of leaves. The stomatal extraction module is used to segment the preprocessed leaf epidermis image and extract multiple stomatal regions from the segmented leaf epidermis image. The stomatal aperture index calculation module is used to calculate the stomatal aperture index for each stomatal region under different light intensities; the stomatal aperture index includes aspect ratio, aperture area and aperture angle. The effective stoma set acquisition module is used to scan multiple fields of view, record the stoma opening data of each field of view based on the stoma opening index of the stoma region in each field of view, remove abnormal data in the stoma opening data, and obtain the effective stoma set. The representative value generation module is used to statistically calculate the average value and standard deviation of the stomatal aperture data of the effective stomatal set under the same light intensity, and use the average value and the standard deviation as the representative value under the corresponding light intensity. The fitting result generation module is used to obtain fitting results based on the light intensity under various experimental conditions and the representative values ​​under the corresponding light intensity; wherein, the fitting results include a scatter plot and a fitting curve for the light intensity and aperture index. The experimental conclusion generation module is used to generate experimental conclusions and reports based on the fitting results.

9. An electronic device, characterized in that, include: A processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program, when executed by the processor, implements the plant stomatal aperture detection method for exploratory experiments as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the plant stomatal aperture detection method for exploratory experiments as described in any one of claims 1 to 7.

Images