CN112257702A - Crop disease identification method based on incremental learning - Google Patents
Crop disease identification method based on incremental learning Download PDFInfo
- Publication number
- CN112257702A CN112257702A CN202011262300.9A CN202011262300A CN112257702A CN 112257702 A CN112257702 A CN 112257702A CN 202011262300 A CN202011262300 A CN 202011262300A CN 112257702 A CN112257702 A CN 112257702A
- Authority
- CN
- China
- Prior art keywords
- image
- disease
- crop
- identification
- method based
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a crop disease identification method based on incremental learning, which relates to the technical field of crop cultivation and comprises the following steps: the method comprises the steps of establishing a convolutional neural network model for identifying disease image characteristics by adopting a target area for calibrating leaf diseases in advance, converting a preprocessed image into an HSI space image, extracting color characteristics and texture characteristics of the image, determining the Euclidean distance between each picture to be detected and a disease training set picture under each characteristic, correcting the extracted significant identification area to obtain a lesion image, and inputting the acquired lesion image into the convolutional neural network model for identification and classification. The invention realizes that the extracted color characteristics and texture characteristics have rotation invariance and illumination invariance, realizes the detection and positioning of crop disease parts in a real environment and the accurate identification of disease types, is suitable for the prevention and the early warning of crop diseases, and is convenient for workers to take targeted disease prevention measures.
Description
Technical Field
The invention relates to the technical field of crop cultivation, in particular to a crop disease identification method based on incremental learning.
Background
Crop diseases are one of the main agricultural disasters in China, have the characteristics of multiple varieties, large influence and frequent outbreak of disasters, not only cause loss to crop production, but also threaten food safety. Therefore, the diagnosis and identification of crop diseases play an important role in ensuring the crop yield and preventing food safety, and meanwhile, the realization of accurate detection of the crop diseases and the determination of the disease degree are the key to the prevention and control of the crop diseases. At present, the traditional crop disease identification mainly depends on experience accumulated by farmers in the agricultural production process in all generations for judgment, and is time-consuming and labor-consuming, and poor in real-time performance and accuracy.
In the current disease identification technology, a computer and an image processing technology are widely adopted, and the retrieval Chinese patent 201210235693.3 discloses a crop leaf disease detection method, which collects leaf images of crops to be detected and uploads the leaf images to an online detection platform, realizes segmentation and identification of the leaf disease spot images of the crops to be detected, outputs a detection result and gives a prevention and treatment suggestion. However, in the existing crop disease identification and classification, scab segmentation is mainly performed by using an edge detection method, a maximum inter-class variance method, a fuzzy C mean value method and a watershed segmentation method, which all need to perform complex field background segmentation and a series of preprocessing, thereby increasing the complexity of scab segmentation. Meanwhile, in feature extraction, texture features in the existing method mainly include correlation, energy, entropy, contrast, inverse difference and the like, a lot of texture feature quantities based on a statistical method are defined based on a gray level co-occurrence matrix to be global features, and local features have the remarkable advantages of rotation invariance, gray level invariance and the like compared with the global features; the method mainly utilizes a neural network, a support vector machine and an improved support vector machine method, and although the methods can identify the types of the diseases, the number of the types identified by the methods is small, only 3 types of diseases are generally identified, and the methods need many samples during training and have low identification rate.
An effective solution to the problems in the related art has not been proposed yet.
Disclosure of Invention
Aiming at the problems in the related technology, the invention provides a crop disease identification method based on incremental learning, which has rotation invariance and illumination invariance to extracted color characteristics and texture characteristics, realizes the detection and positioning of crop disease parts in a real environment and the accurate identification of disease types, is suitable for the prevention and the early warning of crop diseases, is convenient for workers to take targeted disease prevention and treatment measures, and further lays a foundation for improving the early warning of crop diseases so as to overcome the technical problems in the prior related technology.
The technical scheme of the invention is realized as follows:
a crop disease identification method based on incremental learning comprises the following steps:
step S1, collecting crop disease pictures in advance, preprocessing the pictures, calibrating target areas of leaf diseases, constructing a disease training set, and constructing a convolutional neural network model for identifying disease image characteristics;
step S2, converting the preprocessed image into an HSI space image, extracting color features and texture features of the image, and determining Euclidean distance between each picture to be detected and a disease training set picture under each feature as the identification feature significance;
step S3, converting the obtained identification feature saliency into a gray value to obtain a saliency map under each feature, and averaging the gray values of corresponding pixel points in the acquired saliency map under each feature to obtain a final saliency map;
step S4, dividing the final saliency map into K regions by adopting a K-means clustering method, extracting the regions with the average value of the pixel saliency larger than a set threshold value as saliency identification regions, and correcting the extracted saliency identification regions to obtain scab images;
and step S5, inputting the acquired lesion image into a convolutional neural network model for identifying disease image characteristics for identification and classification.
Further, the step of preprocessing the crop disease picture comprises the following steps:
acquiring an image of a crop in advance, wherein the image at least comprises leaves of the crop;
extracting a leaf region in the image based on an interactive image segmentation method;
and carrying out filtering, denoising and smoothing treatment on the extracted image of the blade region.
Further, the interactive image segmentation method comprises the following steps:
pre-performing segmentation points of a standard image in the image;
dividing the image based on the calibrated dividing point, dividing the image into a plurality of regional subunit images, and extracting the color histogram characteristics of each regional subunit image;
and determining a first similarity of each area subunit image and the leaf area image and a second similarity of the area subunit image and the non-leaf area image, wherein if the first similarity is greater than the second similarity, the area subunit image is taken as the image of the target area.
Further, the convolutional neural network model for identifying the disease image features comprises 10 convolutional layers with the size of 3 × 3, 3 convolutional layers with the size of 1 × 1 and 3 full-connection layers, wherein an activation function operation is added after each convolutional layer, and a maximum pooling layer is added after each two layers of the convolutional layers with the size of 3 × 3; after the image enters the network, the image characteristic matrix obtained by convolution operation is:
wherein, I is an input image, m and n are coordinates of each pixel point in I, K is a two-dimensional weight parameter corresponding to a convolution kernel, I and j are coordinates of the pixel points of an image characteristic matrix, an output result of each convolution layer of the network needs to pass through an activation function, and the relationship between the input of each layer and the output of the activation function is expressed as:
Sn(i,j)＝max(0,Sn(i,j)),n＝1,2,…,N-1。
further, the step of converting the preprocessed image into an HSI spatial image includes the following steps:
acquiring the RGB color information of the preprocessed image;
converting the image RGB color information into HSI spatial image information, expressed as:
further, the identification of the lesion image comprises color feature information, local texture feature information, hole feature information, spot feature information and pest track feature information.
The invention has the beneficial effects that:
the crop disease identification method based on incremental learning comprises the steps of collecting crop disease pictures in advance, calibrating target areas of leaf diseases, constructing a disease training set, constructing a convolutional neural network model for identifying disease image characteristics, converting the preprocessed images into HSI space images, extracting color characteristics and texture characteristics of the images, determining Euclidean distance between each picture to be detected and the disease training set picture under each characteristic as the identification characteristic saliency, obtaining a saliency map under each characteristic, correcting the extracted saliency identification areas to obtain scab images, inputting the acquired scab images into the convolutional neural network model for identifying the disease image characteristics for identification and classification, realizing that the extracted color characteristics and texture characteristics have rotation invariance and illumination invariance, and realizing detection and positioning of the crop disease parts in a real environment, and the method is suitable for preventing and early warning of crop diseases, is convenient for workers to take targeted disease prevention measures, further lays a foundation for improving the early warning of the crop diseases, and has strong adaptability and wide limitation.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a schematic flow chart of a crop disease identification method based on incremental learning according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments that can be derived by one of ordinary skill in the art from the embodiments given herein are intended to be within the scope of the present invention.
According to the embodiment of the invention, a crop disease identification method based on incremental learning is provided.
As shown in fig. 1, the crop disease identification method based on incremental learning according to the embodiment of the present invention includes the following steps:
step S1, collecting crop disease pictures in advance, preprocessing the pictures, calibrating target areas of leaf diseases, constructing a disease training set, and constructing a convolutional neural network model for identifying disease image characteristics;
step S2, converting the preprocessed image into an HSI space image, extracting color features and texture features of the image, and determining Euclidean distance between each picture to be detected and a disease training set picture under each feature as the identification feature significance;
step S3, converting the obtained identification feature saliency into a gray value to obtain a saliency map under each feature, and averaging the gray values of corresponding pixel points in the acquired saliency map under each feature to obtain a final saliency map;
step S4, dividing the final saliency map into K regions by adopting a K-means clustering method, extracting the regions with the average value of the pixel saliency larger than a set threshold value as saliency identification regions, and correcting the extracted saliency identification regions to obtain scab images;
and step S5, inputting the acquired lesion image into a convolutional neural network model for identifying disease image characteristics for identification and classification.
The method for preprocessing the crop disease picture comprises the following steps:
acquiring an image of a crop in advance, wherein the image at least comprises leaves of the crop;
extracting a leaf region in the image based on an interactive image segmentation method;
and carrying out filtering, denoising and smoothing treatment on the extracted image of the blade region.
By means of the technical scheme, the method comprises the steps of collecting crop disease pictures in advance, calibrating target areas of leaf diseases, constructing a disease training set, constructing a convolutional neural network model for identifying disease image characteristics, converting the preprocessed images into HSI space images, extracting color characteristics and texture characteristics of the images, determining Euclidean distance between each picture to be detected and the disease training set picture under each characteristic to serve as the identification characteristic significance degree, obtaining a significant image under each characteristic, correcting the extracted significant identification areas to obtain lesion images, inputting the obtained lesion images into the convolutional neural network model for identifying the disease image characteristics for identification and classification, achieving rotation invariance and illumination invariance of the extracted color characteristics and texture characteristics, and achieving detection and positioning of crop disease parts in a real environment, and the method is suitable for preventing and early warning of crop diseases, is convenient for workers to take targeted disease prevention measures, further lays a foundation for improving the early warning of the crop diseases, and has strong adaptability and wide limitation.
The interactive image segmentation method comprises the following steps:
pre-performing segmentation points of a standard image in the image;
dividing the image based on the calibrated dividing point, dividing the image into a plurality of regional subunit images, and extracting the color histogram characteristics of each regional subunit image;
and determining a first similarity of each area subunit image and the leaf area image and a second similarity of the area subunit image and the non-leaf area image, wherein if the first similarity is greater than the second similarity, the area subunit image is taken as the image of the target area.
The convolutional neural network model for identifying the disease image features comprises 10 convolutional layers with the size of 3 multiplied by 3, 3 convolutional layers with the size of 1 multiplied by 1 and 3 full-connection layers, wherein an activation function operation is added after each convolutional layer, and a maximum pooling layer is added after each two layers of the convolutional layers with the size of 3 multiplied by 3; after the image enters the network, the image characteristic matrix obtained by convolution operation is:
wherein, I is an input image, m and n are coordinates of each pixel point in I, K is a two-dimensional weight parameter corresponding to a convolution kernel, I and j are coordinates of the pixel points of an image characteristic matrix, an output result of each convolution layer of the network needs to pass through an activation function, and the relationship between the input of each layer and the output of the activation function is expressed as:
Sn(i,j)＝max(0,Sn(i,j)),n＝1,2,…,N-1。
wherein, the image after the preprocessing is converted into an HSI space image, and the method comprises the following steps:
acquiring the RGB color information of the preprocessed image;
converting the image RGB color information into HSI spatial image information, expressed as:
and identifying the scab image, wherein the identification comprises color characteristic information, local texture characteristic information, hole characteristic information, spot characteristic information and pest track characteristic information.
In addition, specifically, the HSI (Hue-Saturation-Intensity) color model reflects the way in which the human visual system perceives color, and separates color information from grayscale information, and is insensitive to light source variations. H. S, I represent hue, saturation, and brightness, respectively. Its chroma (Hue): reflecting the perception of color attributes such as red, green, yellow by the human eye. Saturation (Saturation): indicating the purity of the color. Luminance (Intensity): the degree of lightness and darkness of the color.
In conclusion, by means of the technical scheme of the invention, the method comprises the steps of collecting crop disease pictures in advance, calibrating target areas of leaf diseases, constructing a disease training set, constructing a convolutional neural network model for identifying disease image characteristics, converting the preprocessed images into HSI space images, extracting color characteristics and texture characteristics of the images, determining Euclidean distance between each picture to be detected and the disease training set picture under each characteristic, taking the Euclidean distance as the identification characteristic saliency, obtaining a saliency map under each characteristic, correcting the extracted saliency identification areas to obtain scab images, inputting the obtained scab images into the convolutional neural network model for identifying the disease image characteristics for identification and classification, realizing that the extracted color characteristics and texture characteristics have rotation invariance and illumination invariance, and realizing the detection and positioning of the crop disease parts in a real environment, and the method is suitable for preventing and early warning of crop diseases, is convenient for workers to take targeted disease prevention measures, further lays a foundation for improving the early warning of the crop diseases, and has strong adaptability and wide limitation.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (6)
1. A crop disease identification method based on incremental learning is characterized by comprising the following steps:
acquiring a crop disease picture in advance, preprocessing the crop disease picture, calibrating a target area of leaf diseases, constructing a disease training set, and constructing a convolutional neural network model for identifying disease image characteristics;
converting the preprocessed image into an HSI space image, extracting color features and texture features of the image, and determining Euclidean distance between each picture to be detected and a disease training set picture under each feature as the identification feature significance;
converting the acquired identification feature saliency into a gray value to obtain a saliency map under each feature, and averaging the gray values of corresponding pixel points in the acquired saliency map under each feature to obtain a final saliency map;
dividing the final saliency map into K regions by adopting a K-means clustering method, extracting the regions with the average value of the pixel saliency larger than a set threshold value as saliency identification regions, and correcting the extracted saliency identification regions to obtain lesion images;
and inputting the acquired lesion image into a convolutional neural network model for identifying the characteristics of the lesion image to identify and classify.
2. The crop disease identification method based on incremental learning of claim 1, wherein the step of preprocessing the crop disease picture comprises the following steps:
acquiring an image of a crop in advance, wherein the image at least comprises leaves of the crop;
extracting a leaf region in the image based on an interactive image segmentation method;
and carrying out filtering, denoising and smoothing treatment on the extracted image of the blade region.
3. The crop disease identification method based on incremental learning of claim 2, wherein the interactive image segmentation method comprises the following steps:
pre-performing segmentation points of a standard image in the image;
dividing the image based on the calibrated dividing point, dividing the image into a plurality of regional subunit images, and extracting the color histogram characteristics of each regional subunit image;
and determining a first similarity of each area subunit image and the leaf area image and a second similarity of the area subunit image and the non-leaf area image, wherein if the first similarity is greater than the second similarity, the area subunit image is taken as the image of the target area.
4. The crop disease identification method based on incremental learning of claim 3, wherein the convolutional neural network model for identifying disease image features comprises 10 convolutional layers with the size of 3 x 3, 3 convolutional layers with the size of 1 x 1 and 3 fully-connected layers, wherein an activation function operation is added after each convolutional layer, and a maximum pooling layer is added after each two layers of convolutional layers with the size of 3 x 3; after the image enters the network, the image characteristic matrix obtained by convolution operation is:
wherein, I is an input image, m and n are coordinates of each pixel point in I, K is a two-dimensional weight parameter corresponding to a convolution kernel, I and j are coordinates of the pixel points of an image characteristic matrix, an output result of each convolution layer of the network needs to pass through an activation function, and the relationship between the input of each layer and the output of the activation function is expressed as:
Sn(i，j)＝max(0，Sn(i，j))，n＝1，2，…，N-1。
5. the crop disease identification method based on incremental learning of claim 1, wherein the step of converting the preprocessed image into an HSI spatial image comprises the following steps:
acquiring the RGB color information of the preprocessed image;
converting the image RGB color information into HSI spatial image information, expressed as:
6. the crop disease identification method based on incremental learning of claim 1, wherein the lesion image identification step comprises color feature information, local texture feature information, hole feature information, spot feature information and pest track feature information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011262300.9A CN112257702A (en) | 2020-11-12 | 2020-11-12 | Crop disease identification method based on incremental learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011262300.9A CN112257702A (en) | 2020-11-12 | 2020-11-12 | Crop disease identification method based on incremental learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112257702A true CN112257702A (en) | 2021-01-22 |
Family
ID=74265701
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011262300.9A Withdrawn CN112257702A (en) | 2020-11-12 | 2020-11-12 | Crop disease identification method based on incremental learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112257702A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113040034A (en) * | 2021-03-26 | 2021-06-29 | 西京学院 | Water-saving irrigation control system and control method |
| CN113112498A (en) * | 2021-05-06 | 2021-07-13 | 东北农业大学 | Grape leaf scab identification method based on fine-grained countermeasure generation network |
| CN113255440A (en) * | 2021-04-13 | 2021-08-13 | 山东农业大学 | Crop leaf abnormity detection method and system based on machine learning |
| CN113989509A (en) * | 2021-12-27 | 2022-01-28 | 衡水学院 | Crop insect pest detection method, crop insect pest detection system and crop insect pest detection equipment based on image recognition |
| CN114283308A (en) * | 2022-03-02 | 2022-04-05 | 科大天工智能装备技术（天津）有限公司 | Crop disease and pest identification method and device based on incremental learning and storage medium |
| CN116363519A (en) * | 2023-04-10 | 2023-06-30 | 上海华维可控农业科技集团股份有限公司 | Cloud computing-based controllable agricultural disease prevention cultivation system and method |
-
2020
- 2020-11-12 CN CN202011262300.9A patent/CN112257702A/en not_active Withdrawn
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113040034A (en) * | 2021-03-26 | 2021-06-29 | 西京学院 | Water-saving irrigation control system and control method |
| CN113040034B (en) * | 2021-03-26 | 2023-10-24 | 西京学院 | Water-saving irrigation control system and control method |
| CN113255440A (en) * | 2021-04-13 | 2021-08-13 | 山东农业大学 | Crop leaf abnormity detection method and system based on machine learning |
| CN113255440B (en) * | 2021-04-13 | 2022-11-25 | 山东农业大学 | Crop leaf abnormity detection method and system based on machine learning |
| CN113112498A (en) * | 2021-05-06 | 2021-07-13 | 东北农业大学 | Grape leaf scab identification method based on fine-grained countermeasure generation network |
| CN113112498B (en) * | 2021-05-06 | 2024-01-19 | 东北农业大学 | Grape leaf spot identification method based on fine-grained countermeasure generation network |
| CN113989509A (en) * | 2021-12-27 | 2022-01-28 | 衡水学院 | Crop insect pest detection method, crop insect pest detection system and crop insect pest detection equipment based on image recognition |
| CN113989509B (en) * | 2021-12-27 | 2022-03-04 | 衡水学院 | Crop insect pest detection method, crop insect pest detection system and crop insect pest detection equipment based on image recognition |
| CN114283308A (en) * | 2022-03-02 | 2022-04-05 | 科大天工智能装备技术（天津）有限公司 | Crop disease and pest identification method and device based on incremental learning and storage medium |
| CN116363519A (en) * | 2023-04-10 | 2023-06-30 | 上海华维可控农业科技集团股份有限公司 | Cloud computing-based controllable agricultural disease prevention cultivation system and method |
| CN116363519B (en) * | 2023-04-10 | 2024-01-09 | 上海华维可控农业科技集团股份有限公司 | Cloud computing-based controllable agricultural disease prevention cultivation system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112257702A (en) | Crop disease identification method based on incremental learning | |
| Qureshi et al. | Machine vision for counting fruit on mango tree canopies | |
| CN109308697B (en) | Leaf disease identification method based on machine learning algorithm | |
| Hamuda et al. | Automatic crop detection under field conditions using the HSV colour space and morphological operations | |
| Parikh et al. | Disease detection and severity estimation in cotton plant from unconstrained images | |
| CN105938564B (en) | Rice disease identification method and system based on principal component analysis and neural network | |
| Archana et al. | Automatic rice leaf disease segmentation using image processing techniques | |
| Yun et al. | PNN based crop disease recognition with leaf image features and meteorological data | |
| Kamlapurkar | Detection of plant leaf disease using image processing approach | |
| Jadhav et al. | Soybean leaf disease detection and severity measurement using multiclass SVM and KNN classifier | |
| Xu et al. | Recognition method for apple fruit based on SUSAN and PCNN | |
| CN108596195B (en) | Scene recognition method based on sparse coding feature extraction | |
| Samanta et al. | Scab diseases detection of potato using image processing | |
| Ji et al. | In-field automatic detection of maize tassels using computer vision | |
| CN115861721B (en) | Livestock and poultry breeding spraying equipment state identification method based on image data | |
| CN113269191A (en) | Crop leaf disease identification method and device and storage medium | |
| Patki et al. | Cotton leaf disease detection & classification using multi SVM | |
| Patil | Pomegranate fruit diseases detection using image processing techniques: a review | |
| Sahoo et al. | Automatic Dead zone detection in 2-D leaf image using clustering and segmentation technique | |
| Ashok Kumar et al. | A review on crop and weed segmentation based on digital images | |
| Hu et al. | Agricultural robot for intelligent detection of pyralidae insects | |
| Deisy et al. | Image segmentation for feature extraction: A study on disease diagnosis in agricultural plants | |
| Abbas et al. | Maize leaf images segmentation using color threshold and K-means clustering methods to identify the percentage of the affected areas | |
| CN116524224A (en) | Machine vision-based method and system for detecting type of cured tobacco leaves | |
| CN110135481B (en) | Crop lesion detection method and detection device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210122 |