Method and system for detecting self-compatibility of brassica rapa

Abstract

The application discloses a method and system for detecting self-compatibility of Brassica campestris L. and relates to the technical field of biological detection. The method comprises the following steps: collecting flower data of the Brassica campestris L.; quantitatively judging the flower data of the Brassica campestris L.; collecting structural feature data of the flower of the Brassica campestris L.; and quantitatively judging the structural feature data of the flower of the Brassica campestris L. The application obtains an image detection quantization value by acquiring an original image of the flower of the Brassica campestris L. and quantizing image quality, judges whether image quality optimization is to be performed according to the quantization value, acquires structural feature data of the flower of the Brassica campestris L. according to the result after optimization if the optimization is to be performed, and quantitatively judges whether structural feature optimization is to be performed based on the structural feature data of the flower of the Brassica campestris L., thereby improving the accuracy of self-compatibility detection, and solving the problem of low detection accuracy of self-compatibility of the Brassica campestris L. caused by differences in image quality and structural features of the flower of the Brassica campestris L. in the prior art.

Description

Technical Field

[0001] This invention relates to the field of biological detection technology, and in particular to a method and system for detecting the self-compatibility of Chinese cabbage-type rapeseed. Background Technology

[0002] In plant genetics and breeding, self-compatibility is an important agronomic trait. For rapeseed (Chinese cabbage type), understanding its self-compatibility helps breeders select suitable inbred lines, thereby improving breeding efficiency. In the breeding of hybrids, understanding the self-compatibility of parents helps predict the performance of hybrid offspring, thus selecting the optimal hybrid combination. Self-compatibility influences crop reproduction methods and field management strategies, and understanding it helps in developing reasonable planting and harvesting plans, improving agricultural production efficiency. Self-compatibility is also related to the ecological adaptability of plants. Under different environmental conditions, self-compatibility may affect the reproductive success rate of plants, thus affecting their distribution and survival in the natural environment.

[0003] The method for detecting self-compatibility in rapeseed involves pollinating the anthers and stigmas in vitro under in vitro conditions, observing pollen germination on the stigma and pollen tube growth, labeling pollen or stigmas with fluorescent dyes, and observing the interaction between pollen and stigmas using a fluorescence microscope, and analyzing genomic regions or gene expression profiles related to self-compatibility using genome sequencing technology.

[0004] For example, the invention patent with publication number CN119023638A discloses a method for detecting the self-pollination and fruit setting of macadamia nuts, which includes: firstly, sorting the inflorescences of self-pollinating pistils, then bagging the inflorescences of the macadamia nut variety to be tested, removing the inflorescences from the bag after 7-9 days, immersing all the pistils attached to the inflorescence axis together with the inflorescence axis in FAA fixative for fixation, washing and softening, then transversely cutting and retaining the ovary and the lower half of the style, then longitudinally cutting the retained part, staining it, observing the growth of pollen tubes in the lower half of the ovary and style under a fluorescence microscope, and counting PLS.

[0005] However, in the process of implementing the inventive technical solution in the embodiments of this application, it was found that the above-mentioned technology has at least the following technical problems:

[0006] In rapeseed flower microscopic images, problems such as blurred boundaries, reflections, and overlaps between the stigma and pollen grains lead to low image quality, making it difficult to effectively distinguish different target regions. This results in low segmentation accuracy of rapeseed flower images. The distribution of rapeseed flower image data in the feature space varies significantly among different varieties. Existing feature extraction methods may not be able to capture cross-variety differences, leading to imbalanced rapeseed flower samples. This increases the complexity of cross-variety data distribution differences and results in low detection accuracy of rapeseed self-compatibility due to differences in rapeseed flower image quality and flower structural features. Summary of the Invention

[0007] This application provides a method and system for detecting the self-compatibility of Chinese rapeseed, which solves the problem of low detection accuracy of rapeseed self-compatibility in the prior art due to differences in rapeseed flower image quality and flower structural features, and improves the accuracy of self-compatibility detection.

[0008] This application provides a method for detecting the self-compatibility of Chinese rapeseed (Brassica napus) type, comprising the following steps: acquiring the original image of the Chinese rapeseed flower corresponding to the Chinese rapeseed to be tested and extracting image data to obtain Chinese rapeseed flower data; quantizing the quality corresponding to the Chinese rapeseed flower data to obtain an image detection quantization value; determining whether to perform image quality optimization based on the obtained image detection quantization value and a preset image detection threshold in the self-compatibility detection database, where image quality optimization means improving the quality by processing the original image of the Chinese rapeseed flower; if image quality optimization is performed, then based on the optimized Chinese rapeseed flower... Feature extraction is performed on the original image; otherwise, feature extraction is performed directly to obtain rapeseed flower structural feature data. The structural features corresponding to the rapeseed flower structural feature data are quantized to obtain structural feature quantization values. Based on the obtained structural feature quantization values ​​and the preset structural feature thresholds in the self-compatibility detection database, it is determined whether to perform structural feature optimization. If structural feature optimization is performed, the self-compatibility of Chinese cabbage-type rapeseed is determined based on the optimized structural features; otherwise, the self-compatibility is determined directly to obtain the optimized structural features. Structural feature optimization means that the reliability of rapeseed pollen grain identification is improved by processing the extracted structural features of rapeseed flowers.

[0009] This application provides a system for detecting the self-compatibility of Chinese rapeseed (Brassica rapa) type, including a Chinese rapeseed flower data acquisition module, a Chinese rapeseed flower data quantization and judgment module, a rapeseed flower structural feature data acquisition module, and a rapeseed flower structural feature data quantization and judgment module. The Chinese rapeseed flower data acquisition module acquires the original image of the Chinese rapeseed flower corresponding to the Chinese rapeseed to be tested and extracts the image data to obtain Chinese rapeseed flower data. The Chinese rapeseed flower data quantization and judgment module obtains an image detection quantization value based on the quality corresponding to the quantized Chinese rapeseed flower data, and determines whether to perform image quality optimization based on the obtained image detection quantization value and a preset image detection threshold in the self-compatibility detection database. Image quality optimization means improving the quality of the original Chinese rapeseed flower image through processing. Quality; Rapeseed flower structural feature data acquisition module: used to extract features based on the optimized original image of the Chinese cabbage-type rapeseed flower if image quality optimization is required, otherwise directly extract features to obtain rapeseed flower structural feature data; Rapeseed flower structural feature data quantization judgment module: used to obtain the structural feature quantization value by quantifying the corresponding structural features through the rapeseed flower structural feature data, and judge whether to perform structural feature optimization based on the obtained structural feature quantization value and the preset structural feature threshold in the self-compatibility detection database. If structural feature optimization is performed, the self-compatibility of the Chinese cabbage-type rapeseed is judged based on the optimized structural feature, otherwise directly judge the self-compatibility to obtain structural feature optimization. Structural feature optimization means improving the reliability of rapeseed pollen grain recognition by processing the extracted rapeseed flower structural features.

[0010] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0011] 1. By quantifying the image quality of the original rapeseed flower images obtained after self-pollination of Chinese cabbage-type rapeseed, an image detection quantization value is obtained. Based on the quantization value, it is determined whether image quality optimization should be performed. If so, the structural feature data of rapeseed flowers is obtained based on the optimized result. Based on the quantization of the structural feature data of rapeseed flowers, it is determined whether structural feature optimization should be performed. This improves the accuracy of self-compatibility detection and solves the problem of low detection accuracy of rapeseed self-compatibility due to differences in rapeseed flower image quality and flower structural features in the existing technology.

[0012] 2. By quantifying image quality and flower structure, image detection and structural feature quantification values ​​are obtained, thereby providing accurate data on Chinese cabbage-type rapeseed flowers. This helps to more accurately analyze the image quality and structural features of flowers, and facilitates the comparison of image quality and structural features of different flowers or under different processing conditions.

[0013] 3. Based on the quantitative results, determine whether to optimize self-compatibility detection. If optimization is performed, then determine self-compatibility based on the optimized results. Improvements can be made to address deficiencies in image quality and structural features, thereby improving the accuracy of self-compatibility detection. Image quality optimization can improve the reliability of pollen grain identification, reduce false detections and false negatives, and thus improve the flexibility of detection. Attached Figure Description

[0014] Figure 1 This is a flowchart of a method for detecting self-compatibility of Chinese rapeseed (Brassica napus) provided in an embodiment of this application.

[0015] Figure 2 This is a flowchart illustrating the image quality optimization process for a method of detecting self-compatibility in Chinese rapeseed (Brassica napus) provided in an embodiment of this application.

[0016] Figure 3 A flowchart illustrating the structural feature optimization of the method for detecting self-compatibility of Chinese rapeseed (Brassica napus) provided in this application embodiment;

[0017] Figure 4 This is a schematic diagram of the structure of the detection system for self-compatibility of Chinese cabbage-type rapeseed provided in an embodiment of this application. Detailed Implementation

[0018] This application provides a method and system for detecting the self-compatibility of rapeseed (Brassica napus), solving the problem of low detection accuracy in existing technologies due to differences in rapeseed flower image quality and structural features. The method obtains an image detection quantization value by acquiring the original rapeseed flower image and quantizing its quality. Based on the quantization value, it determines whether image quality optimization is needed. If so, it obtains rapeseed flower structural feature data based on the optimized result. Then, based on the quantization of the rapeseed flower structural feature data, it determines whether structural feature optimization is needed, thus improving the accuracy of self-compatibility detection.

[0019] The technical solution in this application embodiment aims to address the aforementioned problem of low accuracy in detecting rapeseed self-compatibility due to differences in rapeseed flower image quality and flower structural features. The overall approach is as follows:

[0020] By acquiring original images of rapeseed flowers, preprocessing these images, including denoising, is performed to improve image quality. Image quality is then quantized to obtain image detection quantization values. Based on the quantization results, it is determined whether image quality optimization is needed. If optimization is required, feature extraction is performed on the optimized original images of the rapeseed flowers (of the Chinese cabbage type). Otherwise, feature extraction is performed directly to obtain structural feature data of the rapeseed flowers. This structural feature data is then quantized to obtain structural feature quantization values. Based on these quantization values ​​and a preset structural feature threshold in the self-compatibility detection database, it is determined whether structural feature optimization is needed. If optimization is required, self-compatibility of the Chinese cabbage type rapeseed is determined based on the optimized structural features. Otherwise, self-compatibility is determined directly, improving the efficiency and accuracy of self-compatibility detection.

[0021] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.

[0022] like Figure 1 The diagram shows a flowchart of a method for detecting the self-compatibility of Chinese cabbage-type rapeseed provided in this application embodiment. This method is used in a Chinese cabbage-type rapeseed self-compatibility detection system and includes the following steps: acquiring the original image of the Chinese cabbage-type rapeseed flower corresponding to the rapeseed to be tested and extracting image data to obtain Chinese cabbage-type rapeseed flower data; quantizing the quality corresponding to the Chinese cabbage-type rapeseed flower data to obtain an image detection quantization value; determining whether to perform image quality optimization based on the obtained image detection quantization value and a preset image detection threshold in the self-compatibility detection database; image quality optimization means improving the quality by processing the original image of the Chinese cabbage-type rapeseed flower; if image quality optimization is performed... For quality optimization, feature extraction is performed based on the original image of the rapeseed flower (Chinese cabbage type) after optimization; otherwise, feature extraction is performed directly to obtain rapeseed flower structural feature data. The structural features corresponding to the rapeseed flower structural feature data are quantized to obtain structural feature quantization values. Based on the obtained structural feature quantization values ​​and the preset structural feature thresholds in the self-compatibility detection database, it is determined whether to perform structural feature optimization. If structural feature optimization is performed, the self-compatibility of Chinese cabbage type rapeseed is determined based on the optimized structural features; otherwise, the self-compatibility is determined directly. Structural feature optimization means that the extraction of rapeseed flower structural features is processed to improve the reliability of rapeseed pollen grain identification.

[0023] It is important to understand that before obtaining the original image of the Chinese cabbage-type rapeseed flower, the process includes: removing the stamens from the Chinese cabbage-type rapeseed flower; after removing the stamens, covering the Chinese cabbage-type rapeseed flower with an isolation bag; and when the Chinese cabbage-type rapeseed flower matures, shaking the isolation bag to transfer the pollen from the same Chinese cabbage-type rapeseed flower to the stigma, thus achieving self-pollination.

[0024] In this embodiment, firstly, the stamens of the Chinese cabbage-type rapeseed flowers need to be removed. This is usually done before the rapeseed flowers are fully open to prevent interference from foreign pollen. Stamen removal can be done using fine tweezers or a destamening tool. After removing the stamens, the treated rapeseed flowers are covered with an isolation bag. The isolation bag is a transparent plastic or paper bag, designed to prevent foreign pollen from entering and ensure that subsequent pollination uses only the rapeseed flower's own pollen. The rapeseed flowers are then allowed to mature naturally. When mature, the isolation bag is shaken, allowing pollen from the same flower to fall onto the stigma of the pistil, achieving self-pollination. The original image quality of the Chinese cabbage-type rapeseed flowers suffers from inconsistent image contrast, leading to differences in brightness and darkness in different areas, which in turn affects subsequent analysis. Because the structural features of rapeseed flowers, including but not limited to the shape, size, color, and texture of petals, as well as the morphology of stigmas and pollen grains, vary, these differences in flower structural features increase the difficulty of image recognition, resulting in low accuracy in detecting rapeseed self-compatibility. Through image quality optimization in this application, the original image can be processed to improve image quality. Through structural feature optimization, the extraction and processing of flower structural features can be performed to improve the reliability of pollen grain recognition, ultimately improving the accuracy of self-compatibility detection.

[0025] Specifically, the data on Chinese cabbage-type rapeseed flowers includes rapeseed flower image contrast, rapeseed flower image pixel intensity, rapeseed flower image artifacts, and image noise intensity; the data on rapeseed flower structural features includes the maximum mean difference among rapeseed flower varieties, overlapping target missegmentation rate, image detection quantization value, and second intensity of image noise; the maximum mean difference among rapeseed flower varieties is used to measure the distribution distance of the Chinese cabbage-type rapeseed flower structure in the feature space; the overlapping target missegmentation rate represents the proportion of incorrect segmentation of the overlapping pollen grains and anther intersection regions in the original image of Chinese cabbage-type rapeseed flowers.

[0026] It should be added that the image detection quantization value is obtained by quantifying the quality corresponding to the rapeseed flower data of the Chinese cabbage type. Previously, it also included obtaining image detection thresholds, image detection corrections, structural feature thresholds, and structural feature corrections from the constructed self-compatibility detection database. The image detection thresholds include rapeseed flower image contrast thresholds, rapeseed flower image pixel intensity standard values, rapeseed flower image artifact thresholds, and image noise intensity thresholds. The image detection corrections include rapeseed flower image contrast corrections, rapeseed flower image pixel intensity corrections, rapeseed flower image artifact corrections, and image noise intensity corrections. The structural feature thresholds include rapeseed flower variety maximum mean difference thresholds, overlapping target missegmentation rate thresholds, and image noise intensity second thresholds. The structural feature corrections include rapeseed flower variety maximum mean difference corrections, overlapping target missegmentation rate corrections, image detection corrections, and image noise intensity second corrections.

[0027] It should be added that, before designing the frequency domain feature effectiveness optimization method, a self-compatibility detection database for storing various types of data is established by pre-designed personnel. The self-compatibility detection database includes, but is not limited to, rapeseed flower image contrast, rapeseed flower image pixel intensity, rapeseed flower image artifacts, and overlapping target missegmentation rate, etc. Among them, various values ​​are directly set by pre-designated personnel. For example, the rapeseed flower image contrast threshold is obtained by pre-designated personnel from the specific constraint expression of the image contrast threshold of rapeseed flower images in the historical database within the preset frequency range, the corresponding dataset is obtained by the mean operation of the dataset, and the rapeseed flower image contrast threshold is obtained in advance and stored in the pre-designated database.

[0028] Further, the specific steps for obtaining the image detection quantization value are as follows: The image contrast impact value is obtained by correcting the ratio analysis results of the rapeseed flower image contrast and contrast threshold using the rapeseed flower image contrast correction amount; the image pixel intensity impact value is obtained by correcting the ratio analysis results of the standard value of rapeseed flower image pixel intensity and the deviation degree of the standard value of rapeseed flower image pixel intensity using the rapeseed flower image pixel intensity correction amount; the image artifact impact value is obtained by correcting the ratio analysis results of the rapeseed flower image artifact threshold and artifacts using the rapeseed flower image artifact correction amount; the image noise intensity impact value is obtained by correcting the ratio analysis results of the image noise intensity threshold and noise intensity using the image noise intensity correction amount; the image contrast impact value, image pixel intensity impact value, image artifact impact value, and image noise intensity impact value are coupled and analyzed to obtain the image detection quantization value; the image detection quantization value represents the quantified data of the combined influence of rapeseed flower image contrast, rapeseed flower image pixel intensity, rapeseed flower image artifacts, and image noise intensity on the quality of the rapeseed flower image.

[0029] In this embodiment, the specific formula for obtaining the image detection quantization value is as follows:

[0030]

[0031] δ represents the image detection quantization value. D represents the rapeseed flower image contrast. The original image of the Chinese cabbage-type rapeseed flower is read using image processing software (such as OpenCV), and the difference between the maximum and minimum pixel intensity values ​​in the original image is recorded as the rapeseed flower image contrast. D1 represents the rapeseed flower image contrast threshold obtained from the self-compatibility detection database. Q represents the rapeseed flower image pixel intensity. The pixel intensity of the rapeseed flower image is quantized by calculating the histogram of the original Chinese cabbage-type rapeseed flower image. Further analysis of the histogram of the rapeseed flower image is used to calculate the average brightness value of the rapeseed flower image, i.e., the rapeseed flower image pixel intensity. Q1 represents the standard value of the rapeseed flower image pixel intensity obtained from the self-compatibility detection database. W1 represents the rapeseed flower image artifact threshold obtained from the self-compatibility detection database. W represents rapeseed flower image artifacts. Artifact detection algorithms (such as edge detection and morphological operations) are used to identify and quantify artifacts in rapeseed flower images. The gradient intensity and direction of the original image of the rapeseed flower (of the Chinese cabbage type) are calculated, the gradient magnitude of the edges in the original image is refined, edge pixels are determined, edge segments are connected, and the number of detected edge pixels, edge length, and edge density (the ratio of edge pixel count to the total image area) are calculated. Decision fusion techniques are used to obtain the rapeseed flower image artifacts. Z1 represents the image noise intensity threshold obtained from the self-compatibility detection database. Z represents the image noise intensity, which is obtained by extracting noise components from the original image of the rapeseed flower (of the Chinese cabbage type) using image processing software (such as Python's OpenCV library).

[0032] This is the preset contrast correction amount for rapeseed flower images obtained from the self-compatibility testing database. This refers to the pixel intensity correction amount for rapeseed flower images obtained from the self-compatibility testing database.

[0033] This is the amount of artifact correction for rapeseed flower images obtained from the self-compatibility testing database.

[0034] This is the preset image noise intensity correction amount obtained from the self-compatibility detection database.

[0035] A mapping table for correction values ​​is obtained through a self-compatibility detection database. For example, a mapping table is constructed based on historical rapeseed flower image contrast, pixel intensity, artifacts, and noise levels, along with their corresponding correction values. This mapping table defines a specific set of association rules that converts the specific values ​​of rapeseed flower image contrast, pixel intensity, artifacts, and noise levels into their corresponding correction values. Under this mechanism, dynamic acquisition of correction values ​​can be effectively achieved, whether for precise one-to-one matching or for multiple parameters to converge into a many-to-one relationship.

[0036] The higher the image artifact, the more it interferes with the normal brightness distribution of the image, making the target and background, which should be clearly distinguishable in the image, blurry, and the lower the contrast of the rapeseed flower image. The higher the image noise intensity, the more random brightness fluctuations will be introduced, blurring the boundaries between different areas in the image, making the image look even more blurry, and the lower the contrast of the rapeseed flower image. The larger the rapeseed flower image artifact, the more image noise will be, and the higher the image noise intensity.

[0037] There is a positive correlation between the contrast of rapeseed flower images and the image detection quantization value. The higher the contrast of the rapeseed flower image, the clearer the structural features of the rapeseed flower are displayed, and the higher the image detection quantization value is. There is a negative correlation between the absolute value of the difference between the pixel intensity of the rapeseed flower image and the standard value of the pixel intensity and the image detection quantization value. The larger the absolute value of the difference between the pixel intensity of the rapeseed flower image and the standard value of the pixel intensity, the more details in the highlight areas are lost, and the lower the image detection quantization value is. There is a negative correlation between the image artifacts of rapeseed flower images and the image detection quantization value. The larger the image artifacts, the more they interfere with the true information of the image, making feature extraction more difficult, and the lower the image detection quantization value is. There is a negative correlation between the image noise intensity and the image detection quantization value. The higher the image noise intensity, the more random brightness fluctuations are introduced, and these fluctuations interfere with the accuracy of feature extraction, and the lower the image detection quantization value is.

[0038] By analyzing the correlation between rapeseed flower image contrast, rapeseed flower image pixel intensity, rapeseed flower image artifacts, image noise intensity, and image detection quantization value, we can more accurately evaluate rapeseed flower image detection, optimize image detection methods, and enhance the accuracy of image detection.

[0039] After performing image detection contrast optimization and image channel optimization, the quality of the Chinese cabbage-type rapeseed flower image is evaluated again. If the image detection quantization value is greater than or equal to the preset image detection threshold obtained from the self-compatibility detection database, it indicates that the Chinese cabbage-type rapeseed flower image quality is qualified, and the next step of feature extraction is carried out; otherwise, the Chinese cabbage-type rapeseed flower image data is re-acquired.

[0040] Further, the specific steps for obtaining the structural feature quantification value are as follows: The analysis results of the ratio of the maximum mean difference threshold and the maximum mean difference of rapeseed flower varieties are corrected using the maximum mean difference correction amount for rapeseed flower varieties to obtain the influence value of the maximum mean difference of structural features; the analysis results of the ratio of the missegmentation rate and the threshold of the missegmentation rate of overlapping targets are corrected using the overlapping target missegmentation rate correction amount to obtain the influence value of the missegmentation rate of structural features; the result of the multiplication inverse of the image detection quantization value is corrected using the image detection quantization value correction amount to obtain the image detection influence value; the analysis results of the ratio of the second intensity of image noise and the second threshold of image noise intensity are corrected using the second image noise intensity correction amount to obtain the second influence value of the noise intensity of structural features; the influence value of the maximum mean difference of structural features, the influence value of the missegmentation rate of structural features, the influence value of image detection, and the second influence value of the noise intensity of structural features are coupled and calculated to obtain the structural feature quantification value; the structural feature quantification value represents the quantification data of the degree of influence of the maximum mean difference of rapeseed flower varieties, the missegmentation rate of overlapping targets, the image detection quantification value, and the image noise intensity on the extraction of structural features of rapeseed flowers.

[0041] In this embodiment, the specific formula for obtaining the quantification value of structural features is as follows:

[0042]

[0043] ρ1+ρ2+ρ3+ρ4=1;

[0044] θ represents the quantified value of structural features. C represents the maximum mean difference between rapeseed flower varieties, measuring the distribution distance in feature space between the currently detected Chinese cabbage-type rapeseed flower image and the preset self-compatible Chinese cabbage-type rapeseed flower images obtained from the self-compatibility detection database. A pre-trained model (such as ResNet) is used to extract deep features of the rapeseed flower images (such as stigma geometry: spots, stripes, veins, etc.; petal texture features: leaves, stems, etc.). A Gaussian kernel is applied to the deep features, and the distribution distance is calculated based on the kernel matrix to obtain the maximum mean difference between rapeseed flower varieties. C1 represents the threshold for the maximum mean difference between rapeseed flower varieties obtained from the self-compatibility detection database. F represents the missegmentation rate of overlapping targets, quantifying the proportion of incorrect segmentation of overlapping targets such as adhered pollen grains and the intersection of stigma and anther. Annotated image data is used, including the category and boundary of each target. A segmentation algorithm (such as U-Net) is used to segment the image, and the overlap between the segmentation result and the labeled data is calculated. F1 represents the threshold for the missegmentation rate of overlapping targets obtained from the self-compatibility detection database. δ represents the image detection quantization value. P represents the second intensity of image noise, which refers to the image noise intensity of the segmented rapeseed flower image, obtained by calculating the signal-to-noise ratio using a signal processing library such as SciPy. P1 represents the second threshold of image noise intensity obtained from the self-compatibility detection database.

[0045] ρ1 is the maximum mean difference correction amount for rapeseed flower varieties obtained from the self-compatibility test database.

[0046] ρ2 is the preset overlap target missegmentation rate correction amount obtained from the self-compatibility detection database.

[0047] ρ3 is the correction amount for the preset image detection quantization value obtained from the self-compatibility detection database.

[0048] ρ4 is the second correction factor for preset image noise intensity obtained from the self-compatibility detection database.

[0049] A mapping table for correction values ​​is obtained through a self-compatibility detection database. For example, a mapping table is constructed based on historical maximum mean difference among rapeseed flower varieties, overlapping target missegmentation rate, image detection quantization value, and the second intensity of image noise, along with corresponding correction values. This mapping table defines a clear set of association rules, converting the specific values ​​of the maximum mean difference among rapeseed flower varieties, overlapping target missegmentation rate, image detection quantization value, and the second intensity of image noise into their corresponding correction values. Under this mechanism, dynamic acquisition of correction values ​​can be effectively achieved, whether for precise one-to-one matching or for multiple parameters to converge into a many-to-one relationship.

[0050] The greater the maximum mean difference in rapeseed flower varieties, the easier it is to distinguish between different varieties of flowers, and the lower the missegmentation rate of overlapping targets. The greater the second intensity of image noise, the more it will interfere with the accuracy of image segmentation algorithms, making it difficult for the algorithms to correctly distinguish overlapping flowers, which will increase the missegmentation rate of overlapping targets. The higher the missegmentation rate of overlapping targets, the more likely it is to be missegmented.

[0051] There is a negative correlation between the maximum mean difference of rapeseed flower varieties and the quantified value of structural features. The greater the maximum mean difference of rapeseed flower varieties, the greater the difference between varieties, the clearer the structural features, and the smaller the quantified value of structural features. There is a positive correlation between the missegmentation rate of overlapping targets and the quantified value of structural features. The greater the missegmentation rate of overlapping targets, the less clear the structural features or the higher the similarity, and the larger the quantified value of structural features. There is a negative correlation between the quantified value of image detection and the quantified value of structural features. The greater the quantified value of image detection, the better the image quality, and the smaller the quantified value of structural features. There is a positive correlation between the image noise intensity and the quantified value of structural features. The greater the image noise intensity, the more difficult it is to clearly capture the structural features of the flowers, and the larger the quantified value of structural features.

[0052] By analyzing the correlation between the maximum mean difference of rapeseed flower varieties, the missegmentation rate of overlapping targets, the image detection quantization value, and the image noise intensity and structural feature quantization value, the structural features of rapeseed flowers can be evaluated more accurately, the method for extracting structural features of rapeseed flowers can be optimized, and the extraction of structural features of rapeseed flowers can be enhanced.

[0053] Furthermore, based on the obtained image detection quantization value and the preset image detection threshold in the self-compatibility detection database, it is determined whether to perform image quality optimization. The specific steps are as follows: compare the image detection quantization value with the preset image detection threshold obtained from the self-compatibility detection database. If the image detection quantization value is greater than or equal to the preset image detection threshold obtained from the self-compatibility detection database, then no image quality optimization is performed; otherwise, image quality optimization is performed. If the structural feature quantization value is lower than or equal to the preset structural feature threshold obtained from the self-compatibility detection database, then no structural feature optimization is performed; otherwise, structural feature optimization is performed.

[0054] Specifically, the steps for image quality optimization are as follows: First, an image detection deviation value is obtained based on the image detection quantization value and a preset image detection threshold. This deviation value measures the degree of quality deviation in the rapeseed flower image. If the image detection deviation value is lower than or equal to the safe image detection deviation threshold in the self-compatibility detection database, the rapeseed flower image is designated as a Level 1 sample. Second, if the image detection deviation value is greater than the safe image detection deviation threshold but less than the preset image detection deviation threshold, the rapeseed flower image is designated as a Level 2 sample. Image detection contrast optimization is then performed on the Level 2 sample. This optimization involves increasing the brightness of areas with pixel values ​​below a preset pixel value threshold using the obtained image brightness adjustment amount, and decreasing the brightness of areas with pixel values ​​above the preset pixel value threshold to improve image contrast. The image brightness adjustment amount is obtained by mapping the image detection quantization value into the preset self-compatibility detection database. Third, if the image detection deviation value is greater than or equal to the preset image detection deviation threshold, the rapeseed flower image is designated as a Level 3 sample. Image channel optimization is then performed on the Level 3 sample to improve the visual quality of the rapeseed flower image. Image quality optimization includes both image detection contrast optimization and image channel optimization.

[0055] In this embodiment, as Figure 2 The diagram shows an image quality optimization flowchart for a method for detecting self-compatibility of rapeseed (Brassica napus) provided in this application embodiment. The specific logic is as follows: If the image detection quantization value is lower than a preset image detection threshold, image quality optimization is performed: The image detection quantization value is compared with the preset image detection threshold to obtain an image deviation value. If the image deviation value is lower than a safe image deviation threshold, it indicates high sample quality, and the rapeseed flower image is classified as a first-level sample, requiring no further processing feedback, indicating it is within a controllable range. If the image deviation value is greater than the safe image deviation threshold but less than the preset image deviation threshold, the rapeseed flower image is classified as a second-level sample. If the image deviation value is greater than the preset image deviation threshold, the rapeseed flower image is classified as a third-level sample. If the sample is a second-level sample, it is adjusted through image contrast optimization. The specific process of image contrast optimization is as follows: Multi-scale gamma correction is used to process the dark and bright parts of the rapeseed flower image separately, classifying areas with image pixel values ​​lower than a preset pixel value threshold as dark areas and areas with image pixel values ​​greater than a preset pixel value threshold as bright areas. Adjust the brightness of the dark and bright areas of the rapeseed flower image based on the image detection quantization value.

[0056] For areas in the rapeseed flower image where the image pixel value is lower than the preset pixel value threshold obtained from the self-compatibility detection database, the brightness of the dark area is adjusted according to the image detection quantization value. The brightness of the dark area corresponding to the preset image detection quantization value in the database is obtained based on the current image detection quantization value as the adjustment value for brightness increase. An adjustment value is matched based on the image detection quantization value, and this adjustment value is added to the original brightness of the dark area.

[0057] For regions in a rapeseed flower image where the pixel value is greater than a preset pixel value threshold obtained from the self-compatibility detection database, the brightness of the bright areas of the image is adjusted based on the image detection quantization value. The brightness of the bright areas corresponding to the preset image detection quantization value in the database is obtained based on the current image detection quantization value as the adjustment value for brightness reduction. An adjustment value is matched based on the image detection quantization value, and this adjustment value is added to the original brightness of the bright areas of the image.

[0058] Furthermore, image channel optimization means stretching image channels with image contrast lower than the preset image contrast by obtaining the changes in the red and blue channels, and compressing image channels with image contrast higher than the preset image contrast by obtaining the changes in the red and blue channels to improve the accuracy of image detection; image contrast is used to reflect the degree of color difference in the original image of Chinese cabbage-type rapeseed flowers; channel changes are obtained by mapping the image detection quantization value into a preset self-compatibility detection database.

[0059] In this embodiment, if the sample is a level 3 sample, the target rapeseed flower color parameters are set according to the color of the rapeseed flower (such as the RGB value of yellow petals). Multi-scale gamma correction is used to eliminate color deviation caused by illumination, so that the white or neutral gray areas can be restored to their true colors. White balance is achieved by adjusting the mean of the RGB (Red, Green, Blue) channels based on the image detection quantization value. The mean values ​​(R1, R2, R3) of the three channels R, G, and B of the rapeseed flower image are calculated respectively. Based on the G channel, the R and B channels of each pixel of the image detection quantization value are scaled (scaling is applied to the petal area), while the G channel remains unchanged.

[0060] If the image contrast is lower than the preset image contrast, the distribution of the red and blue channels is stretched. The stretching range is adjusted according to the image detection quantization value to expand the range of the red and blue channels. The expansion standard is to obtain the range of the red and blue channels corresponding to the preset image detection quantization value in the database based on the current image detection quantization value as the adjustment value for expanding the range of the red and blue channels. An adjustment value is matched according to the image detection quantization value. The adjustment value is determined based on the amount of the image detection quantization value and is added to the original size of the red and blue channel range.

[0061] If the image contrast is greater than the preset image contrast, the red and blue channels are compressed to reduce the deviation. The compression range is adjusted according to the image detection quantization value. The compression standard is to obtain the red and blue channel range corresponding to the preset image detection quantization value in the database based on the current image detection quantization value as the red and blue channel range compression adjustment value. An adjustment value is matched according to the image detection quantization value. The adjustment value is determined based on the amount of image detection quantization value. This adjustment value is added to the original red and blue channel range size.

[0062] Through the above steps, the dynamic range of the red and blue channels can be dynamically adjusted based on the image deviation value, thereby enhancing image contrast and color accuracy in a targeted manner. Gamma correction is used to enhance the contrast of the G channel, and the enhanced G channel is merged with the original R and B channels to make target areas such as pollen grains more clearly visible and improve image quality.

[0063] Further, the specific steps for structural feature optimization are as follows: First, obtain the pollen grain number density and compare it with a corresponding preset pollen grain number density threshold. If the pollen grain number density is less than or equal to the preset pollen grain number density threshold, then adjust the pixel number range of the pollen grain region. This adjustment means expanding the initial pixel number range of the pollen grain region by the obtained pixel number range change to improve pollen grain recognition accuracy. The pixel number range change is obtained by mapping the structural feature quantization value into a preset self-compatibility detection database. Second, if the pollen grain number density is greater than the preset pollen grain number density threshold, then optimize the pixel number range of the pollen grain region. This optimization means narrowing the pixel number range of the pollen grain region by the obtained pixel number range adjustment to improve pollen grain recognition accuracy. The pixel number range adjustment is obtained by mapping the structural feature quantization value into a preset self-compatibility detection database.

[0064] In this embodiment, as Figure 3The diagram shows a flowchart of the structural feature optimization method for detecting self-compatibility of Chinese cabbage-type rapeseed provided in this application embodiment. The stigma morphology features and pollen grain distribution features are extracted from the segmented rapeseed flower image. In image analysis, overlapping pollen grains lead to missegmentation, which affects the accurate counting of pollen grains. The higher the pollen grain density, the greater the possibility of overlap, and the missegmentation rate will increase accordingly.

[0065] Image processing software (such as ImageJ, Matlab, Python, etc.) is used to analyze pollen images taken under a microscope. Pollen grains and non-pollen grains are distinguished by setting a range of pixel counts in the pollen grain region. The minimum value in the range of pixel counts in the pollen grain region represents the minimum number of pixels occupied by the pollen grain region, and the maximum value in the range of pixel counts in the pollen grain region represents the maximum number of pixels occupied by the pollen grain region.

[0066] If the pollen grain density is less than or equal to a preset pollen grain density threshold, it indicates that pollen grains have been missed. By expanding the pixel count range of the pollen grain region, pollen grains are re-identified using the adjusted pixel count range to supplement the missed parts. The pixel count range of the pollen grain region is adjusted according to the structural feature quantization value. The pixel count range change corresponding to the preset structural feature quantization value in the database is obtained based on the current structural feature quantization value. A pixel count range change is matched based on the structural feature quantization value. The pixel count range change is determined based on the amount of structural feature quantization value. This pixel count range change is added to the maximum value of the original pixel count range of the pollen grain region. The minimum value of the pixel count range of the pollen grain region is subtracted from the pixel count range change to obtain the adjusted pixel count range of the pollen grain region.

[0067] If the pollen grain density exceeds a preset pollen grain density threshold, it indicates that the pollen grains are too dense. By narrowing the pixel count range of the pollen grain region, the number of small particles identified as pollen grains is reduced. A spatial grid is established, local density is statistically analyzed, and pollen points in overly dense areas are filtered out. The pixel count range of the pollen grain region is adjusted based on the structural feature quantization value. The pixel count range adjustment amount corresponding to the preset structural feature quantization value in the database is obtained based on the current structural feature quantization value. A pixel count range adjustment amount is matched based on the structural feature quantization value. The pixel count range adjustment amount is determined based on the amount of structural feature quantization value. This pixel count range adjustment amount is added to the minimum value in the original pixel count range of the pollen grain region. The maximum value in the pixel count range of the pollen grain region is subtracted from the pixel count range adjustment amount to obtain the adjusted pixel count range of the pollen grain region.

[0068] After the above optimization and adjustment steps, observation was conducted using a fluorescence microscope. Pollen and stigma were labeled with fluorescent dyes, and the interaction between pollen and stigma was observed under the fluorescence microscope to determine self-compatibility. The determination process was as follows: Under the fluorescence microscope, pollen tubes could be observed extending from the pollen grains and growing along the stigma tissue, indicating successful germination of pollen on the stigma. The pollen tubes were able to grow normally and penetrate the stigma tissue, indicating that this Chinese cabbage-type rapeseed variety was self-compatible. Under the fluorescence microscope, pollen grains could be observed accumulating on the stigma, but the pollen tubes failed to grow normally or their growth was inhibited, preventing germination of pollen on the stigma. Alternatively, pollen tube growth was inhibited, preventing penetration of the stigma tissue, indicating that this Chinese cabbage-type rapeseed variety was self-incompatible.

[0069] like Figure 4 The diagram shows a structural schematic of a system for detecting the self-compatibility of Chinese cabbage-type rapeseed provided in this application embodiment. The system includes: a Chinese cabbage-type rapeseed self-pollination module, a Chinese cabbage-type rapeseed flower data acquisition module, a Chinese cabbage-type rapeseed flower data quantification and judgment module, a rapeseed flower structural feature data acquisition module, and a rapeseed flower structural feature data quantification and judgment module. The Chinese cabbage-type rapeseed self-pollination module removes the stamens from the flowers of the Chinese cabbage-type rapeseed. After removing the stamens, the flowers are covered with an isolation bag. When the flowers mature, the isolation bag is shaken to transfer pollen from the same flower to the stigma, achieving self-pollination. The Chinese cabbage-type rapeseed flower data acquisition module acquires the original image of the Chinese cabbage-type rapeseed flower corresponding to the tested Chinese cabbage-type rapeseed and extracts the image data to obtain the Chinese cabbage-type rapeseed flower data. The Chinese cabbage-type rapeseed flower data quantification and judgment module obtains the image detection quantity based on the quality corresponding to the quantified Chinese cabbage-type rapeseed flower data. The system employs several methods: a quantization module and a self-compatibility detection database. The first method involves processing the original image of a rapeseed flower to improve its quality. The second method involves extracting structural features from the original image. The third method involves quantizing the structural features to obtain quantized values. The first method uses these quantized values ​​and a self-compatibility threshold in the database to determine whether structural feature optimization is needed. If optimization is required, the system performs self-compatibility testing on the rapeseed flower. Otherwise, it performs self-compatibility testing directly. Structural feature extraction improves the reliability of rapeseed pollen identification by processing extracted structural features. The fourth method involves quantizing the structural features of the rapeseed flower to obtain structural feature data. The fifth method involves quantizing the structural features to obtain quantized values. If optimization is required, the system performs self-compatibility testing on the optimized images. If optimization is required, the system performs self-compatibility testing directly. Structural feature extraction improves the reliability of rapeseed pollen identification by processing extracted structural features.

[0070] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0071] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will 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 apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0072] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function 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 function specified in one or more boxes.

[0073] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable 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.

[0074] Although preferred embodiments of the invention 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 both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0075] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for testing self-compatibility in Brassica campestris, characterized in that, The method comprises the following steps: Obtaining a white cabbage type rape flower original image corresponding to a to-be-tested white cabbage type rape and performing image data extraction to obtain white cabbage type rape flower data; Obtaining an image detection quantization value through white cabbage type rape flower data quantization corresponding to quality, and judging whether to perform image quality optimization based on the obtained image detection quantization value and a preset image detection threshold value in a self-compatibility detection database, wherein the image quality optimization represents processing of the white cabbage type rape flower original image to improve quality; If the image quality optimization is performed, performing feature extraction based on the optimized white cabbage type rape flower original image, otherwise, directly performing feature extraction to obtain rape flower structure feature data; Obtaining a structure feature quantization value through rape flower structure feature data quantization corresponding to structure feature, and judging whether to perform structure feature optimization based on the obtained structure feature quantization value and a preset structure feature threshold value in the self-compatibility detection database, wherein if the structure feature optimization is performed, performing white cabbage type rape self-compatibility determination based on structure feature optimization, otherwise, directly performing self-compatibility determination, wherein the structure feature optimization represents processing of rape flower structure feature extraction to improve reliability of rape pollen grain identification; The specific acquisition steps of the image detection quantization value are as follows: Obtaining an image detection contrast influence value by modifying an analysis result of a proportion of a rape flower image contrast to a rape flower image contrast threshold value through a rape flower image contrast modification amount; Obtaining an image detection pixel intensity influence value by modifying an analysis result of a proportion of a rape flower image pixel intensity standard value to a rape flower image pixel intensity deviation degree through a rape flower image pixel intensity modification amount; Obtaining an image detection artifact influence value by modifying an analysis result of a proportion of a rape flower image artifact threshold value to a rape flower image artifact through a rape flower image artifact modification amount; Obtaining an image detection noise intensity influence value by modifying an analysis result of a proportion of an image noise intensity threshold value to an image noise intensity through an image noise intensity modification amount; Coupling analysis is performed on the image detection contrast influence value, the image detection pixel intensity influence value, the image detection artifact influence value and the image detection noise intensity influence value to obtain the image detection quantization value; The image detection quantization value represents influence degree quantization data of the rape flower image contrast, the rape flower image pixel intensity, the rape flower image artifact and the image noise intensity on the rape flower image quality; The specific acquisition steps of the structure feature quantization value are as follows: Obtaining a structure feature maximum mean value difference influence value by modifying an analysis result of a proportion of a rape flower variety maximum mean value difference threshold value to a rape flower variety maximum mean value difference through a rape flower variety maximum mean value difference modification amount; Obtaining a structure feature missegmentation rate influence value by modifying an analysis result of a proportion of an overlapping target missegmentation rate to an overlapping target missegmentation rate threshold value through an overlapping target missegmentation rate modification amount; Obtaining an image detection influence value by modifying a result of a multiplicative inverse of the image detection quantization value through an image detection quantization value modification amount; The proportion analysis result of the second image noise intensity and the second image noise intensity threshold is corrected by a second image noise intensity correction amount, to obtain a second structural feature noise intensity influence value; The structural feature maximum mean difference influence value, the structural feature missegmentation rate influence value, the image detection influence value and the second structural feature noise intensity influence value are coupled to obtain a structural feature quantization value; The structural feature quantization value represents the influence degree quantization data of the maximum mean difference of rape flower varieties, the missegmentation rate of overlapping targets, the image detection quantization value and the image noise intensity on the extraction of rape flower structure features; The specific steps of the structure feature optimization are: Obtain the pollen grain number density, and compare it with the corresponding preset pollen grain number density threshold value; If the pollen grain number density is less than or equal to the preset pollen grain number density threshold value, the pixel number interval of the pollen grain region is adjusted, which represents that the initial pixel number interval of the pollen grain region is expanded by the obtained pixel number interval change amount to improve the pollen grain recognition accuracy, and the pixel number interval change amount is mapped into the preset self-compatibility detection database based on the structural feature quantization value; If the pollen grain number density is greater than the preset pollen grain number density threshold value, the pixel number interval of the pollen grain region is optimized, which represents that the pixel number interval of the pollen grain region is reduced by the obtained pixel number interval adjustment amount to improve the pollen grain recognition accuracy, and the pixel number interval adjustment amount is mapped into the preset self-compatibility detection database based on the structural feature quantization value.

2. The method for detecting self-compatibility of Brassica campestris according to claim 1, wherein The cabbage-type rape flower data includes rape flower image contrast, rape flower image pixel intensity, rape flower image artifact and image noise intensity; The rape flower structure feature data includes the maximum mean difference of rape flower varieties, the missegmentation rate of overlapping targets, the image detection quantization value and the second image noise intensity; The maximum mean difference of rape flower varieties is used to measure the distribution distance of cabbage-type rape flower structure in the feature space. The missegmentation rate of overlapping targets represents the error segmentation proportion of the pollen grain and anther intersection region adhered in the cabbage-type rape flower original image.

3. The method for detecting self-compatibility of Brassica campestris according to claim 2, wherein The image detection quantization value obtained by quantizing the corresponding quality of the cabbage-type rape flower data further includes an image detection threshold value, an image detection correction amount, a structural feature threshold value and a structural feature correction amount obtained from the constructed self-compatibility detection database; The image detection threshold value includes a rape flower image contrast threshold value, a rape flower image pixel intensity standard value, a rape flower image artifact threshold value and an image noise intensity threshold value; The image detection correction amount includes a rape flower image contrast correction amount, a rape flower image pixel intensity correction amount, a rape flower image artifact correction amount and an image noise intensity correction amount; The structural feature threshold value includes a maximum mean difference threshold value of rape flower varieties, a missegmentation rate threshold value of overlapping targets and a second image noise intensity threshold value; The structure feature correction quantity comprises a maximum average difference correction quantity of a rape flower variety, an overlapping target mis-segmentation rate correction quantity, an image detection correction quantity, and a second image noise intensity correction quantity.

4. The method for detecting self-compatibility of Brassica campestris according to claim 1, wherein The obtained image detection quantitative value is compared with a preset image detection threshold value obtained from the self-compatibility detection database, and if the image detection quantitative value is greater than or equal to the preset image detection threshold value obtained from the self-compatibility detection database, no image quality optimization is performed, otherwise, image quality optimization is performed. If the structure feature quantitative value is lower than or equal to a preset structure feature threshold value obtained from the self-compatibility detection database, no structure feature optimization is performed, otherwise, structure feature optimization is performed. The specific steps of performing image quality optimization are as follows:

5. The method for detecting self-compatibility of Chinese cabbage-type rapeseed as described in claim 4, characterized in that, An image detection deviation value is obtained based on the image detection quantitative value and the preset image detection threshold value, and the image detection deviation value is used to measure the quality deviation degree of the rape flower image. If the image detection deviation value is lower than or equal to a safe image detection deviation threshold value in the self-compatibility detection database, the rape flower image is recorded as a first-level sample. If the image detection deviation value is greater than the safe image detection deviation threshold value and less than a preset image detection deviation threshold value, the rape flower image is recorded as a second-level sample, and image detection contrast optimization is performed on the second-level sample, the image detection contrast optimization indicating that the image brightness adjustment quantity is obtained to increase the brightness of the region with an image pixel value lower than a preset pixel value threshold value, and the image brightness adjustment quantity is obtained to decrease the brightness of the region with an image pixel value greater than the preset pixel value threshold value to improve the image contrast, the image brightness adjustment quantity being obtained by inputting the image detection quantitative value into the preset self-compatibility detection database for mapping. If the image detection deviation value is greater than or equal to the preset image detection deviation threshold value, the rape flower image is recorded as a third-level sample, and image channel optimization is performed on the third-level sample to improve the visual quality of the rape flower image. The image channel optimization indicates that the image red-blue channel variation quantity is obtained to stretch the image channel with an image contrast lower than a preset image contrast, and the image red-blue channel variation quantity is obtained to compress the image channel with an image contrast greater than the preset image contrast to improve the accuracy of image detection. The image contrast is used to reflect the difference degree of colors in the white cabbage type rape flower original image.

6. The method for detecting self-compatibility of Brassica campestris according to claim 5, wherein The channel variation quantity is obtained by inputting the image detection quantitative value into the preset self-compatibility detection database for mapping. The white cabbage type rape flower data acquisition module is configured to obtain a white cabbage type rape flower original image corresponding to the white cabbage type rape to be detected, and perform image data extraction to obtain white cabbage type rape flower data. The white cabbage type rape flower data acquisition module is configured to obtain a white cabbage type rape flower original image corresponding to the white cabbage type rape to be detected, and perform image data extraction to obtain white cabbage type rape flower data.

7. A system for testing self-compatibility in Brassica campestris using the method for testing self-compatibility in Brassica campestris according to any one of claims 1 to 6, characterized in that, ​ ​ The quantitative judgment module of the flower data of Brassica rapa L. is used for obtaining image detection quantitative values through the quality corresponding to the quantitative flower data of Brassica rapa L., and judging whether image quality optimization is performed based on the obtained image detection quantitative values and preset image detection threshold values in the self-compatibility detection database. The image quality optimization represents that the quality of the original image of the flower of Brassica rapa L. is improved through processing. The structure feature data collection module of the flower of Brassica rapa L. is used for performing feature extraction based on the original image of the flower of Brassica rapa L. after optimization if the image quality optimization is performed, or directly performing feature extraction, and obtaining structure feature data of the flower of Brassica rapa L. The quantitative judgment module of the structure feature data of the flower of Brassica rapa L. is used for obtaining structure feature quantitative values through the structure feature corresponding to the quantitative structure feature data of the flower of Brassica rapa L., and judging whether structure feature optimization is performed based on the obtained structure feature quantitative values and preset structure feature threshold values in the self-compatibility detection database. If the structure feature optimization is performed, self-compatibility judgment of Brassica rapa L. is performed based on the structure feature after optimization, otherwise, self-compatibility judgment is directly performed, and structure feature optimization is obtained. The structure feature optimization represents that the reliability of Brassica pollen grain recognition is improved through processing of the structure feature extraction of the flower of Brassica rapa L.

Images