111 results about "Leaf disease" patented technology

The invention discloses a lightweight rice leaf disease identification method based on YOLO target detection. The method comprises the following steps: S1, inputting a rice leaf disease image; s2, carrying out super-resolution reconstruction on the image by using an improved Real-ESRGAN algorithm; s3, inputting the picture into an improved YOLOv8n target detection algorithm; s4, obtaining disease spot category and position information; and S5, visualizing the information on the image. The invention relates to the technical field of target detection, and has the beneficial effects that image super-resolution reconstruction is carried out aiming at the problems that a rice leaf scab target is relatively small and an image acquired in real time is relatively fuzzy, so that the resolution of the small target is improved, and the definition and texture features are improved. On the basis of a super-division model Real-ESRGAN, a group of residual dense modules containing five layers of cavity convolution layers are designed to help the network to acquire receptive fields and information of different scales.

The invention relates to the technical field of disease and insect pest image analysis, in particular to an AI image recognition and grading method for field crop leaf disease and insect pests, which comprises the following steps: under the irradiation of a field fixed light source, synchronously acquiring a plurality of polarized reflection images around crop leaves at preset angle intervals; extracting a pixel polarization degree matrix of a leaf area in each polarization reflection image; inputting the pixel polarization degree matrix into a polarization transmission model, outputting a cuticle anomaly coefficient graph, and marking an area exceeding a preset anomaly threshold in the cuticle anomaly coefficient graph as a highlight display area; matching an infection type template library according to a highlight display area distribution mode in the abnormal coefficient graph; and calculating an infection intensity value by combining the diffusion gradient of the highlight area, and outputting a pest grade. According to the method, the boundary of the optical mutation region of the focus region is depicted, so that the physical interpretation of disease detection is improved, and distinguishable feature spaces are provided for different infection mechanisms (such as fungal growth layers and insect pest piercing and sucking points).

The invention provides a multi-task identification method for strawberry diseases and insect pests, and belongs to the technical field of strawberry leaf disease identification. The method comprises the following steps: marking an enhanced original strawberry leaf image, and constructing a multi-task training data set; inserting a double attention unit on a semantic segmentation model decoder as a segmentation network, constructing a detection network based on a lightweight detection model, inputting a segmentation mask output by the segmentation network into the detection network to construct a cascade model, and performing preliminary training; performing multi-task joint learning on the cascade model; based on the multi-task data set, a progressive training strategy is combined with a cosine annealing learning rate adjustment strategy, and final training is carried out on the cascade model after joint learning; and inputting a to-be-detected strawberry leaf image into the finally trained cascade model, and outputting a disease type and a severity level. According to the method, the recognition sensitivity of tiny disease spots can be effectively improved, and the generalization ability of the model to complex illumination and shielding scenes is enhanced.

A system for classifying apple leaf diseases using deep learning and feature fusion, consisting of: A data input module, which includes a data storage module, is configured to store a data set created using various data sources, with the data set containing apple leaf images being derived from the data sets "Apple Leaf 9", "Kashmiri Apple Plant Disease" and "Plant Village Apple Leaf"; a data preprocessing module configured to perform preprocessing of the newly prepared dataset of apple leaves, wherein the data preprocessing module is configured to perform data decoding, expansion, resizing, segmentation, scaling and color conversion of the input image data; a feature extraction module that is operationally connected to the data processing module and is configured to receive preprocessed data and transfer the preprocessed data to one or more convolutional neural network models for feature extraction; a feature fusion module configured to combine the extracted features from the Convolutional Neural Networks to develop a fused feature vector; a hyperparameter optimization module configured to optimize the hyperparameters of the feature extraction models by implementing a particle swarm optimization algorithm; a classification module configured to classify the fused trait vector into 13 apple leaf disease classes using a random forest classifier; and a user interface connected to the classification module, configured to display the classification results.

The invention discloses an apple leaf disease segmentation method based on a lightweight dual-path network, an apple leaf disease segmentation device based on the lightweight dual-path network, an apple leaf disease segmentation device and a computer readable storage medium. The problems that an existing disease segmentation method is high in model complexity and insufficient in multi-scale recognition capability are effectively solved. The lightweight encoder adopts a depth separable convolution and channel recombination technology, so that the parameter quantity and the calculation complexity are greatly reduced while the feature extraction capability is maintained, and the model can be deployed on edge equipment such as an unmanned aerial vehicle and a field robot. The enhanced cavity space pyramid pooling module constructs abundant multi-scale receptive fields through multi-branch parallel cavity convolution with different expansion rates, and can capture feature information of initial tiny disease spots and later fused disease spots at the same time.

The invention discloses a tomato leaf disease and insect pest identification method, which comprises the following steps of: acquiring tomato leaf images in different planting environments by using a high-definition camera, performing data enhancement in modes of random overturning, rotation, brightness contrast adjustment, Gaussian noise addition and the like after the tomato leaf images are labeled by agricultural experts, and normalizing the images; constructing a recognition model which is based on a lightweight convolutional neural network such as MobileNetV3 and is fused with an SE attention mechanism module and an FPN multi-scale feature fusion module; dividing the data set into a training set, a verification set and a test set according to 8: 1: 1, training a model by adopting an Adam optimizer, adjusting parameters according to the performance of the verification set, evaluating the model by using the test set, and optimizing according to a result; during actual application, images are collected in real time, preprocessed and input into the model for recognition, and pest and disease type and position information are output and displayed for early warning. According to the method, the recognition accuracy rate exceeds 95%, the hardware requirement is reduced, the robustness and generalization ability are enhanced, real-time monitoring and early warning are achieved, and agricultural economic losses can be reduced.

The invention relates to the technical field of image recognition, in particular to a horticultural product fungal disease image recognition system and method, and the system comprises an image collection module, an image segmentation module, an anomaly detection module, a feature extraction module, a disease recognition module and a decision output module. In the prior art, the intensity of a light supplementing lamp is manually adjusted, and instantly changing illumination conditions (such as cloud layer shielding and tree shadow shaking) are difficult to deal with in an open-air plantation, so that leaf scab details are often submerged by strong light or dim light is blurred; according to the scheme, a closed-loop linkage system of ambient light perception and an annular LED is innovatively deployed, and the light supplementing intensity is reversely adjusted in a millisecond level by tracking ambient brightness in real time, so that purple gray hyphae of downy mildew in mist in the morning and anthracnose black spots under the noon burning sun present completely consistent color saturation and texture definition in imaging; and the problem of misdiagnosis caused by illumination fluctuation in the traditional method is thoroughly solved.

The invention relates to a potato leaf disease area positioning method, system and device.The method is applied to the potato leaf disease area positioning device.The method comprises the steps that a target infrared image of a potato leaf is segmented into a normal area and an abnormal area according to the environment temperature through a disease segmentation model obtained in advance; determining the water content of the target infrared image according to the leaf spectrum information through a pre-obtained water content prediction model; the leaf emissivity characteristic is calculated according to the water content through a pre-obtained temperature correction model, the temperature of the abnormal area is corrected based on the emissivity characteristic and the water content characteristic, and the temperature correction model is obtained based on potato leaf characteristic training; and through a pre-trained disease identification model, identifying a disease area from the abnormal area after temperature correction.

The invention discloses marine-derived penicillium as well as a fermentation method and application thereof. The marine source penicillium is named as Penicillium sp.DSF059, and the preservation number of the marine source penicillium is CCTCC (China Center For Type Culture Collection) NO: M 20232310. According to the invention, the culture conditions of the strain are optimized, the culture medium and culture conditions with high yield of antibacterial active compounds are selected for fermentation, more target products can be obtained, the operation is simple, the cost is low, and the method is suitable for industrial production. Meanwhile, the marine-derived penicillium sp. DSF059 can provide an excellent strain for the development of new drugs for resisting plant pathogens such as coffee leaf blight, coffee brown spot, grape gray mold, golden cypress brown spot, citrus black rot, phytophthora capsici, hickory leaf blight and coffee black spot as well as four pathogens separated from coffee leaf diseases and staphylococcus aureus; good application prospects are realized on prevention and treatment of phytopathogen and staphylococcus aureus.

The invention belongs to the technical field of crop disease and insect pest recognition, and particularly discloses a crop disease and insect pest recognition analysis method based on image processing, and the method comprises the steps: collecting a state image of a plant in a dynamic environment, and eliminating the interference of the dynamic environment on the state image recognition of a plant leaf; differentiated analysis is carried out on disease and insect pest characteristics of different areas corresponding to each leaf area, so that leaf disease and insect pest types and defect data thereof are accurately identified; the color value distribution health state of leaves near a leaf vein distribution area is detected by simulating the leaf vein distribution contour of the interference area, the corresponding leaf vein structure stability of each leaf area is analyzed, and the leaf state of the remaining area after the interference area and the pest and disease damage area of the leaves are removed is identified. And assisting in evaluating the leaf risk area condition in each leaf area, and judging the pest and disease damage state in the plant leaf according to the condition. The recognition precision of the crop state image is improved, and targeted prevention and control measures can be taken.

The invention provides a crop leaf disease image recognition method, which comprises the following steps: collecting crop leaves to capture a scab area image, obtaining original pixel-level data and a boundary contour, and obtaining an initial data set containing a scab form; angle matching and direction comparison are carried out on the extracted contour coordinates and the main extension direction angle and a preset vein trend template, and the coincidence degree of the extension direction and the vein trend is evaluated; according to the coincidence degree of the expansion direction and the leaf vein trend, identifying the difference between the expansion rate of the disease spot along the leaf vein direction and the expansion rate vertical to the leaf vein direction, and analyzing to obtain a directivity judgment standard after dynamic adjustment; performing diagnosis specificity strong characterization identification classification processing on the morphological characteristics of the non-uniform disease spots according to the dynamically adjusted directivity judgment standard, and determining the tightness degree of judgment between the disease spot morphology and the pathogen species; and integrating the main expansion direction and the vein trend distribution data according to pathogen types, and generating a disease type discrimination report.

The invention discloses a rice leaf disease detection method and system based on improved YOLOv11, belongs to the technical field of agricultural intelligent detection, and solves the problems that fine-grained features are lost due to traditional downsampling, a spatial pyramid pooling module is limited in perception of diseases of different sizes, neck network feature fusion is insufficient, and the detection accuracy is poor. Therefore, the problems of complex background interference and low small target disease recognition precision are solved. According to the method, a data set containing eight types of rice leaf diseases is constructed, YOLOv11 is improved, a model is trained to detect the diseases, a PyQt5 visualization system containing six modules is further developed, and detection and prevention and treatment recommendation is supported. According to the method, the detection precision is high, the mAP of the improved model reaches 94.5% and is improved by 3% compared with the original YOLOv11, and the accuracy of diseases difficult to recognize is remarkably improved; the robustness is high, and the omission ratio is reduced by 2.5%; the system is simple to operate, supports multi-input and parameter configuration, provides a control strategy, and can be efficiently used for field detection.

The invention discloses a leaf disease and insect pest detection method based on multi-scale feature enhancement. Accurate detection of leaf diseases and insect pests is realized by constructing a multi-scale feature enhancement model and a fusion pyramid. The method comprises the steps of firstly collecting a leaf disease and pest data set and performing image preprocessing, and then constructing a leaf disease and pest detection model. The method comprises the following specific steps: introducing a DP-ACAM module, and effectively extracting feature information of leaf diseases and insect pests; a fourth minimum target network layer and a DAAM attention mechanism are newly added in the Neck network, a multi-scale receptive field is constructed through depth separable convolution, and context information of different scales is effectively captured; an original detection head is changed into an AMDA-Head detection head, attention fusion of different sizes and space and channel attention output are combined, and the recognition accuracy is effectively improved. And after model construction is completed, training, testing and performance evaluation are carried out. The method is suitable for an actual scene with densely overlapped leaves, changeable illumination conditions and diverse scab forms.

The invention discloses a method for constructing a diagnostic model for identifying leaf diseases. The method comprises the following steps: constructing a leaf disease original image set; preprocessing the leaf disease original image set to generate a leaf disease image sample set; the content of the leaf disease image sample set comprises leaf disease classification, leaf disease stages and a corresponding image set; the method comprises the following steps: defining a network model of which the basic structure is ResNet50, and adding an IB module to form a ResNet50-FIB structure; the IB module is used for performing multi-scale fusion and enhancement processing and outputting deep semantic features and spatial detail information, the deep semantic features are used for matching leaf disease classification, and the spatial detail information is used for matching leaf disease stages; the output layer outputs disease classification and disease stages according to image recognition; and training the network model, and constructing and generating a diagnosis model for identifying leaf diseases. According to the technical scheme, the bottlenecks of a traditional model in precision and speed balance, early disease misjudgment and cross-crop adaptability can be broken through, and the method has industrial popularization potential.

The invention discloses a tomato leaf disease detection method, which is based on an improved lightweight target detection model MWD-YOLO11n to improve the accuracy and efficiency of disease identification. According to the method, three key improvements are carried out on the basis of an original YOLO11 model: firstly, a multi-scale dynamic attention mechanism (MSDA) is introduced, and the perception ability of the model to different-scale disease features is enhanced; secondly, wavelet convolution (WTConv) is adopted to replace part of a traditional convolution structure, and the capturing capacity of the model for disease edges and texture details is effectively improved; and finally, integrating a dynamic up-sampling operator (DySample), optimizing the resolution of the feature map, and further enhancing the characterization capability of the disease area. The method has high precision and low calculation amount, is suitable for deployment of edge equipment, shows excellent performance in tomato leaf disease detection tasks, and has good application prospects and popularization value.

The application discloses a marine source penicillium and a fermentation method and application thereof. The marine source penicillium is named Penicillium sp. DSF059, and the preservation number is CCTCC NO: M 20232310. Penicilliu The application optimizes the culture condition of the strain, selects a culture medium and culture condition with high yield of antibacterial active compounds to carry out fermentation, so that more target products can be obtained, the operation is simple, the cost is low, and meanwhile, the marine source penicillium Penicilliu Penicillium sp. DSF059 can provide an excellent strain for new drug development of resisting plant pathogenic fungi such as coffee leaf blight, coffee brown spot disease, grape gray mold disease, Chinese cinnamon brown spot disease, citrus black rot disease, pepper late blight, hickory leaf blight, coffee black spot disease and four pathogenic fungi separated from coffee leaf diseases and Staphylococcus aureus, and has a good application prospect for preventing and treating the plant pathogenic fungi and Staphylococcus aureus.

The application discloses a bacillus velezensis A13 wettable powder and application thereof, and belongs to the technical field of biological pesticides. The application aims to solve the problems of limited prevention and treatment effect of existing seed treatment, high labor intensity of foliar spraying and short effective period. The wettable powder comprises a mother powder prepared from fermentation liquor and diatomite, and a dispersant, a wetting agent, a stabilizer and a protective agent, wherein the total addition amount of the dispersant and the wetting agent is 5%-14% of the mass of the mother powder, the addition amount of the protective agent is 0.5%-2% of the mass of the mother powder, and the addition amount of the stabilizer is 1%-3% of the mass of the mother powder. The application can be used for preventing and treating root diseases caused by panax quinquefolius rust rot fungus and leaf diseases caused by panax quinquefolius alternaria leaf spot fungus, and promoting plant growth.

The invention discloses a rice leaf disease identification method used in an open scene, and relates to the technical field of computer vision, and the method specifically comprises the steps: 1, constructing an image enhancement set based on an antagonistic attention mask; 2, an entropy toughness index is defined, and a dynamic high-reliability sample library is constructed according to the index; and step 3, realizing steady-state linear transformation through dynamic weight distribution. And step 4, forming a final rice leaf disease identification model through the pre-training classifier after combination optimization and the linear transformation matrix. According to the method, by combining the antagonistic mask, the dynamic high-reliability sample library and the steady-state linear transformation, the problems that the model is poor in robustness and difficult in field self-adaption in an open farmland environment are effectively solved, and the performance of the rice leaf disease recognition model in an open scene is improved.

The invention discloses a grape leaf disease intelligent classification method based on computer vision, and relates to the technical field of agricultural intellectualization, and the method comprises the steps: carrying out the preprocessing of visible light images according to a fixed sequence; establishing a pixel-level model in the HSV space and the LAB space, and fusing to generate a leaf mask; block modeling, low-bit robust projection and asynchronous block attention of sparse masks are carried out based on masks; features are formed through mask-guided channel attention fusion, classification is completed, and area and edge constraints are applied; multi-modal entropy weight gating is constructed, and a color space weight is returned in a closed loop mode; federated training and aggregation are adopted, and end side recalibration and rollback processing are completed. According to the method, stable and reproducible disease classification output is realized under the condition that privacy and computing power are limited.

The invention discloses a corn leaf disease detection method based on an improved YOLOv11 algorithm. The method comprises the following steps: S1, collecting image data of different disease types of corn leaf diseases; s2, preprocessing a corn leaf disease data set formed by the collected image data of the corn leaf disease, wherein preprocessing comprises cutting, rotation, color enhancement and scaling; s3, labeling the corn leaf disease data set; s4, randomly dividing the corn leaf disease data set into a training set and a test set; s5, building a corn leaf disease detection model based on an improved YOLOv11 algorithm; s6, training the corn leaf disease detection model by using the training set to obtain a trained corn leaf disease detection model; s7, verifying the trained corn leaf disease detection model by using the test set; and S8, detecting the maize leaf disease by using the trained maize leaf disease detection model verified in the step S7.

This invention discloses a method for detecting rice leaf disease lesions based on the computing power of mobile devices. It utilizes an improved detection model based on YOLOv5 to detect rice diseases. This detection model introduces a ternary attention mechanism to enhance the attention feature extraction capability of YOLOv5, replaces the C3 module in the neck network of YOLOv5 with a C3CBAM module, and replaces the convolutional Conv in the backbone network of YOLOv5 with a lightweight convolutional GhostConv. Deployed on a Raspberry Pi mobile device and accelerated using MNN, the method detects input rice leaf images and obtains the detection results. This invention maintains the detection accuracy for common rice leaf diseases while maintaining a relatively fast inference speed on a mobile Raspberry Pi.

The utility model relates to the technical field of disease recognition devices, in particular to an apple leaf disease recognition device carried by an unmanned aerial vehicle, which comprises an unmanned aerial vehicle platform, an image acquisition camera and a mounting mechanism, the mounting mechanism comprises a mounting seat, a sliding rail, a clamping ring and two fixing assemblies, and each fixing assembly comprises a mounting plate, a limiting rod and a telescopic sleeve. The mounting seat is provided with a plurality of limiting holes, the image acquisition camera is arranged below the unmanned aerial vehicle platform, the mounting seat is slidably connected with the unmanned aerial vehicle platform, the sliding rail is fixedly connected with the unmanned aerial vehicle platform, the clamping ring is fixedly connected with the mounting seat, the clamping ring is slidably connected with the sliding rail, the image acquisition camera is fixedly connected with the mounting seat, and the mounting plate is fixedly connected with one end of the sliding rail. The limiting rod is slidably connected with the mounting plate, and the image acquisition camera can be dismounted and mounted below the unmanned aerial vehicle platform through the mounting mechanism, so that an operator can conveniently maintain the image acquisition camera, and the practicability of the device is further improved.

The invention discloses an intelligent drug delivery method and system for fruit tree leaves. The method comprises the following steps: receiving a fruit tree leaf picture collected by a high-definition camera arranged in a tree-side monitoring drug administration device; inputting the fruit tree leaf picture into a preset OfficientNet-B1 convolutional neural network model to obtain an identification result matched with the fruit tree leaf picture; an identification result is sent to an upper computer; receiving a drug administration instruction which is sent by the upper computer and corresponds to the identification result; a drug administration module is controlled to spray drugs according to the drug administration instruction, the drug administration module is arranged in the tree-side monitoring drug administration device, and the drug administration module at least comprises a drug storage box, an electric control adjustable nozzle, a piezoelectric micro pressure pump and a control circuit; and the control circuit controls the direction of the electrically-controlled adjustable nozzle and controls the piezoelectric micro pressure pump to push the medicament in the medicament bottle out to the electrically-controlled adjustable nozzle to be sprayed out. The technical problems that in the prior art, the fruit tree leaf disease monitoring and drug administration efficiency is low, and the drug administration intelligence degree is poor are solved.

The application relates to the technical field of disease and pest detection, and particularly discloses a tomato leaf disease and pest detection method based on an improved YOLOv8, which comprises the following steps: constructing a tomato leaf image dataset containing each type of disease and pest; fusing a GhostNet and an RFA attention mechanism, modifying a loss function into a Wise IOU, and constructing an improved YOLOv8 model; configuring training hyperparameters, updating model weights based on the tomato leaf image dataset, and obtaining a trained improved YOLOv8 model; performing disease and pest detection on a to-be-detected tomato leaf image based on the trained improved YOLOv8 model, and obtaining a disease and pest detection result of the to-be-detected tomato leaf image; and the method can improve the efficiency and real-time performance of the model, reduce the number of parameters, enhance the attention ability of the model to features, and improve the detection precision, so that more accurate disease and pest detection can be realized.

The invention discloses a cross-variety plant leaf disease recognition method and system based on multi-source knowledge fusion, and belongs to the technical field of computer vision and plant disease recognition. According to the method, a multi-source feature extraction network is constructed to perform feature extraction on data of each source domain, and source domain features are adaptively adjusted based on a variety difference perception mechanism; a knowledge quality evaluation module is constructed to calculate the knowledge credibility score of each source domain, a dynamic weight fusion strategy is adopted to distribute a sample-level adaptive weight for each source domain according to the knowledge credibility and the sample feature similarity, a cross-domain alignment network is constructed to realize feature distribution alignment, a joint loss function training model is generated, and the self-adaptive weight of each source domain is obtained. According to the method, the problems of negative migration, poor cross-variety generalization ability and the like caused by insufficient self-adaptive utilization of multi-source information in a single-source domain and lack of knowledge quality evaluation are effectively solved, and the accuracy and robustness of cross-variety plant leaf disease recognition are remarkably improved.

The invention relates to the technical field of agricultural disease detection, and particularly discloses a ConvNeXt-GAN model generation method and system for blueberry leaf disease data set expansion. The method comprises the following steps: acquiring blueberry leaf disease images under different illumination conditions and weather environments in a blueberry cultivation base, preprocessing the acquired images, and further dividing to obtain a training set, a verification set and a test set; the StyleGAN3 generative adversarial network is improved; training the improved StyleGAN3 model by using the training set, continuously monitoring the performance of the model through the verification set, carrying out hyper-parameter tuning according to a monitoring result, and carrying out comprehensive evaluation on the performance of the model by using the test set to obtain an optimal improved StyleGAN3 model; and generating a blueberry leaf disease image by using the optimal improved StyleGAN3 model, thereby realizing construction of a high-quality blueberry leaf disease data set. The image generated by the method is accurate in scab reduction, high in semantic consistency, diversified in sample and low in redundancy, can be migrated to other plant disease scenes, and is wide in popularization prospect.

This invention provides a method for identifying plant leaf diseases based on FasterNet. First, original plant leaf disease identification images for corresponding categories are acquired and stored in corresponding image folders. Then, Python is used to iterate through the original plant leaf disease identification images in each category's image folder, dividing them proportionally into training images, validation images, and test images, and performing preprocessing to obtain a plant leaf disease identification image dataset. Subsequently, the original FasterNet model is constructed and improved to obtain FasterNet. Improved Model; Obtain FasterNet Improved The model needs to iteratively train and validate the model parameter tensors and initialize them; then FasterNet... Improved The model undergoes iterative training and validation to obtain the optimal model parameter tensor ω. FI And save; for the trained and validated FasterNet Improved The model was tested. This invention aims to improve the accuracy of plant leaf disease identification and reduce the time cost of the associated bounding box annotation.

The invention discloses a penicillium griseofulvum FZ61 strain and application thereof in prevention and treatment of panax notoginseng leaf diseases, and belongs to the technical field of microorganisms. The penicillium griseofulvum FZ61 strain (the preservation number is CGMCC (China General Microbiological Culture Collection Center) No.41462). Compared with penicillium griseofulvum strains FZ37 and FZ46 obtained through separation in the same batch, the penicillium griseofulvum strain FZ37 and FZ46 has excellent bacteriostasis, siderophore production, IAA production, cellulase production, nitrogen fixation and inorganic phosphorus dissolving capacities, easily and rapidly occupies a beneficial ecological niche at plant phyllosphere, can directly inhibit growth of main pathogenic bacteria of panax notoginseng leaves, can also improve the activity of related defensive enzymes of panax notoginseng leaves after foliage spraying, and has a wide application prospect. The leaf resistance is enhanced, the panax notoginseng black spot, the panax notoginseng round spot and the panax notoginseng anthracnose are prevented and treated, and the harm of leaf diseases to panax notoginseng planting is effectively reduced. In addition, the strain also has a remarkable inhibition effect on pathogenic bacteria of leaf diseases such as soybean blight, potato early blight and corn southern leaf blight which are seriously harmful in agricultural production, and can be used as a high-quality biocontrol bacterium resource for biological control of leaf diseases of crops.

The invention provides a hyperspectrum-based citrus leaf lesion diagnosis system and a hyperspectrum-based citrus leaf lesion diagnosis method, and the hyperspectrum-based citrus leaf lesion diagnosis system and the hyperspectrum-based citrus leaf lesion diagnosis method disclosed by the invention have the advantages that on the basis of analyzing hyperspectral imaging data of citrus leaves without diseases, lack of nutrients, black spots and yellow shoot; three parameters of yellow wave band reflectivity, infrared wave band slope and inflection point wavelength are used as characteristic quantities, and classification of four types of blades is realized by applying a support vector machine (RBF-SVM) classification model based on a Gaussian radial basis kernel function. The method solves the problems that when citrus tree disease information is detected through a field detection method at present, long-time observation with eyes is needed, subjective judgment of observers is depended, and misjudgment is likely to be caused; according to the present invention, the problem that the citrus tree disease information detection by using the chemical detection method needs the special person to detect by using the professional equipment so as not to accurately and rapidly detect each production stage of the citrus tree can be solved, and the citrus leaf disease can be rapidly and accurately diagnosed.

The invention discloses a sugarcane leaf disease susceptibility degree classification method, device and equipment based on SSA optimization and a medium. The method comprises the steps of obtaining plant data sets of sugarcane leaf disease susceptibility areas of a plurality of planting areas and sugarcane disease susceptibility grades; constructing a plurality of sugarcane leaf susceptibility degree classification prediction models; based on a sparrow search algorithm, optimizing hyper-parameters of each sugarcane leaf susceptibility degree classification prediction model; obtaining an evaluation parameter corresponding to each optimized sugarcane leaf susceptibility degree classification prediction model; and according to the evaluation parameters, determining a target sugarcane leaf susceptibility degree classification prediction model from the plurality of optimized sugarcane leaf susceptibility degree classification prediction models, and performing susceptibility degree prediction on the sugarcane leaf susceptible region by using the target sugarcane leaf susceptibility degree classification prediction model. The invention belongs to the field of sugarcane leaf infection degree prediction. According to the invention, the accuracy of predicting the susceptibility degree of the sugarcane leaves can be improved.